Compare commits

..

6 Commits

Author SHA1 Message Date
4a09ad8dca ComfyUI v0.19.4 2026-04-21 21:08:31 -04:00
c135d9f74a Add gpt-image-2 as version option (#13501) 2026-04-21 21:07:09 -04:00
ec62a307a2 Bump comfyui-frontend-package to 1.42.14 (#13493) 2026-04-21 21:06:57 -04:00
685f3db99d Bump comfyui-frontend-package to 1.42.12 (#13489) 2026-04-21 21:06:45 -04:00
58744ac533 [Partner Nodes] added 4K resolution for Veo models; added Veo 3 Lite model (#13330)
* feat(api nodes): added 4K resolution for Veo models; added Veo 3 Lite model

Signed-off-by: bigcat88 <bigcat88@icloud.com>

* increase poll_interval from 5 to 9

---------

Signed-off-by: bigcat88 <bigcat88@icloud.com>
Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>
2026-04-21 21:06:19 -04:00
e6f1b1e6be feat(api-nodes): add automatic downscaling of videos for ByteDance 2 nodes (#13465) 2026-04-21 21:05:59 -04:00
284 changed files with 3582 additions and 90862 deletions

View File

@ -1,2 +1,2 @@
.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --enable-dynamic-vram
.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --disable-smart-memory
pause

View File

@ -1,31 +0,0 @@
name: OpenAPI Lint
on:
pull_request:
paths:
- 'openapi.yaml'
- '.spectral.yaml'
- '.github/workflows/openapi-lint.yml'
permissions:
contents: read
jobs:
spectral:
name: Run Spectral
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v4
- name: Set up Node.js
uses: actions/setup-node@v4
with:
node-version: '20'
- name: Install Spectral
run: npm install -g @stoplight/spectral-cli@6
- name: Lint openapi.yaml
run: spectral lint openapi.yaml --ruleset .spectral.yaml --fail-severity=error

View File

@ -145,8 +145,6 @@ jobs:
cp -r ComfyUI/.ci/windows_${{ inputs.rel_name }}_base_files/* ./
cp ../update_comfyui_and_python_dependencies.bat ./update/
echo 'local-portable' > ComfyUI/.comfy_environment
cd ..
"C:\Program Files\7-Zip\7z.exe" a -t7z -m0=lzma2 -mx=9 -mfb=128 -md=768m -ms=on -mf=BCJ2 ComfyUI_windows_portable.7z ComfyUI_windows_portable

View File

@ -1,45 +0,0 @@
name: Tag Dispatch to Cloud
on:
push:
tags:
- 'v*'
jobs:
dispatch-cloud:
runs-on: ubuntu-latest
steps:
- name: Send repository dispatch to cloud
env:
DISPATCH_TOKEN: ${{ secrets.CLOUD_REPO_DISPATCH_TOKEN }}
RELEASE_TAG: ${{ github.ref_name }}
run: |
set -euo pipefail
if [ -z "${DISPATCH_TOKEN:-}" ]; then
echo "::error::CLOUD_REPO_DISPATCH_TOKEN is required but not set."
exit 1
fi
RELEASE_URL="https://github.com/${{ github.repository }}/releases/tag/${RELEASE_TAG}"
PAYLOAD="$(jq -n \
--arg release_tag "$RELEASE_TAG" \
--arg release_url "$RELEASE_URL" \
'{
event_type: "comfyui_tag_pushed",
client_payload: {
release_tag: $release_tag,
release_url: $release_url
}
}')"
curl -fsSL \
-X POST \
-H "Accept: application/vnd.github+json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DISPATCH_TOKEN}" \
https://api.github.com/repos/Comfy-Org/cloud/dispatches \
-d "$PAYLOAD"
echo "✅ Dispatched ComfyUI tag ${RELEASE_TAG} to Comfy-Org/cloud"

2
.gitignore vendored
View File

@ -21,6 +21,6 @@ venv*/
*.log
web_custom_versions/
.DS_Store
openapi.yaml
filtered-openapi.yaml
uv.lock
.comfy_environment

View File

@ -1,100 +0,0 @@
extends:
- spectral:oas
# Severity levels: error, warn, info, hint, off
# Rules from the built-in "spectral:oas" ruleset are active by default.
# Below we tune severity and add custom rules for our conventions.
#
# This ruleset mirrors Comfy-Org/cloud/.spectral.yaml so specs across the
# organization are linted against a single consistent standard.
rules:
# -----------------------------------------------------------------------
# Built-in rule severity overrides
# -----------------------------------------------------------------------
operation-operationId: error
operation-description: warn
operation-tag-defined: error
info-contact: off
info-description: warn
no-eval-in-markdown: error
no-$ref-siblings: error
# -----------------------------------------------------------------------
# Custom rules: naming conventions
# -----------------------------------------------------------------------
# Property names should be snake_case
property-name-snake-case:
description: Property names must be snake_case
severity: warn
given: "$.components.schemas.*.properties[*]~"
then:
function: pattern
functionOptions:
match: "^[a-z][a-z0-9]*(_[a-z0-9]+)*$"
# Operation IDs should be camelCase
operation-id-camel-case:
description: Operation IDs must be camelCase
severity: warn
given: "$.paths.*.*.operationId"
then:
function: pattern
functionOptions:
match: "^[a-z][a-zA-Z0-9]*$"
# -----------------------------------------------------------------------
# Custom rules: response conventions
# -----------------------------------------------------------------------
# Error responses (4xx, 5xx) should use a consistent shape
error-response-schema:
description: Error responses should reference a standard error schema
severity: hint
given: "$.paths.*.*.responses[?(@property >= '400' && @property < '600')].content['application/json'].schema"
then:
field: "$ref"
function: truthy
# All 2xx responses with JSON body should have a schema
response-schema-defined:
description: Success responses with JSON content should define a schema
severity: warn
given: "$.paths.*.*.responses[?(@property >= '200' && @property < '300')].content['application/json']"
then:
field: schema
function: truthy
# -----------------------------------------------------------------------
# Custom rules: best practices
# -----------------------------------------------------------------------
# Path parameters must have a description
path-param-description:
description: Path parameters should have a description
severity: warn
given:
- "$.paths.*.parameters[?(@.in == 'path')]"
- "$.paths.*.*.parameters[?(@.in == 'path')]"
then:
field: description
function: truthy
# Schemas should have a description
schema-description:
description: Component schemas should have a description
severity: hint
given: "$.components.schemas.*"
then:
field: description
function: truthy
overrides:
# /ws uses HTTP 101 (Switching Protocols) — a legitimate response for a
# WebSocket upgrade, but not a 2xx, so operation-success-response fires
# as a false positive. OpenAPI 3.x has no native WebSocket support.
- files:
- "openapi.yaml#/paths/~1ws"
rules:
operation-success-response: off

View File

@ -1,2 +1,2 @@
# Admins
* @comfyanonymous @kosinkadink @guill @alexisrolland @rattus128 @kijai
* @comfyanonymous @kosinkadink @guill

View File

@ -1,7 +1,7 @@
<div align="center">
# ComfyUI
**The most powerful and modular AI engine for content creation.**
**The most powerful and modular visual AI engine and application.**
[![Website][website-shield]][website-url]
@ -31,16 +31,10 @@
[github-downloads-latest-shield]: https://img.shields.io/github/downloads/comfyanonymous/ComfyUI/latest/total?style=flat&label=downloads%40latest
[github-downloads-link]: https://github.com/comfyanonymous/ComfyUI/releases
<img width="1590" height="795" alt="ComfyUI Screenshot" src="https://github.com/user-attachments/assets/36e065e0-bfae-4456-8c7f-8369d5ea48a2" />
<br>
![ComfyUI Screenshot](https://github.com/user-attachments/assets/7ccaf2c1-9b72-41ae-9a89-5688c94b7abe)
</div>
ComfyUI is the AI creation engine for visual professionals who demand control over every model, every parameter, and every output. Its powerful and modular node graph interface empowers creatives to generate images, videos, 3D models, audio, and more...
- ComfyUI natively supports the latest open-source state of the art models.
- API nodes provide access to the best closed source models such as Nano Banana, Seedance, Hunyuan3D, etc.
- It is available on Windows, Linux, and macOS, locally with our [desktop application](https://www.comfy.org/download), our [portable install](#installing) or on our [cloud](https://www.comfy.org/cloud).
- The most sophisticated workflows can be exposed through a simple UI thanks to App Mode.
- It integrates seamlessly into production pipelines with our API endpoints.
ComfyUI lets you design and execute advanced stable diffusion pipelines using a graph/nodes/flowchart based interface. Available on Windows, Linux, and macOS.
## Get Started
@ -83,7 +77,6 @@ See what ComfyUI can do with the [newer template workflows](https://comfy.org/wo
- [Hunyuan Image 2.1](https://comfyanonymous.github.io/ComfyUI_examples/hunyuan_image/)
- [Flux 2](https://comfyanonymous.github.io/ComfyUI_examples/flux2/)
- [Z Image](https://comfyanonymous.github.io/ComfyUI_examples/z_image/)
- Ernie Image
- Image Editing Models
- [Omnigen 2](https://comfyanonymous.github.io/ComfyUI_examples/omnigen/)
- [Flux Kontext](https://comfyanonymous.github.io/ComfyUI_examples/flux/#flux-kontext-image-editing-model)
@ -133,7 +126,7 @@ Workflow examples can be found on the [Examples page](https://comfyanonymous.git
ComfyUI follows a weekly release cycle targeting Monday but this regularly changes because of model releases or large changes to the codebase. There are three interconnected repositories:
1. **[ComfyUI Core](https://github.com/comfyanonymous/ComfyUI)**
- Releases a new major stable version (e.g., v0.7.0) roughly every 2 weeks.
- Releases a new stable version (e.g., v0.7.0) roughly every week.
- Starting from v0.4.0 patch versions will be used for fixes backported onto the current stable release.
- Minor versions will be used for releases off the master branch.
- Patch versions may still be used for releases on the master branch in cases where a backport would not make sense.
@ -200,15 +193,11 @@ If you have trouble extracting it, right click the file -> properties -> unblock
The portable above currently comes with python 3.13 and pytorch cuda 13.0. Update your Nvidia drivers if it doesn't start.
#### All Official Portable Downloads:
#### Alternative Downloads:
[Portable for AMD GPUs](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_amd.7z)
[Experimental portable for AMD GPUs](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_amd.7z)
[Portable for Intel GPUs](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_intel.7z)
[Portable for Nvidia GPUs](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_nvidia.7z) (supports 20 series and above).
[Portable for Nvidia GPUs with pytorch cuda 12.6 and python 3.12](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_nvidia_cu126.7z) (Supports Nvidia 10 series and older GPUs).
[Portable with pytorch cuda 12.6 and python 3.12](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_nvidia_cu126.7z) (Supports Nvidia 10 series and older GPUs).
#### How do I share models between another UI and ComfyUI?
@ -429,8 +418,6 @@ Use `--tls-keyfile key.pem --tls-certfile cert.pem` to enable TLS/SSL, the app w
See also: [https://www.comfy.org/](https://www.comfy.org/)
> _psst — we're hiring!_ Help build ComfyUI: [comfy.org/careers](https://www.comfy.org/careers)
## Frontend Development
As of August 15, 2024, we have transitioned to a new frontend, which is now hosted in a separate repository: [ComfyUI Frontend](https://github.com/Comfy-Org/ComfyUI_frontend). This repository now hosts the compiled JS (from TS/Vue) under the `web/` directory.

View File

@ -1,44 +0,0 @@
# Security Policy
## Scope
ComfyUI is designed to run locally. By default, the server binds to `127.0.0.1`, meaning only the user's own machine can reach it. Our threat model assumes:
- The user installed ComfyUI through a supported channel: the desktop application, the portable build, or a manual install following the README.
- The user has not installed untrusted custom nodes. Custom nodes are arbitrary Python code and are trusted as much as any other software the user chooses to install.
- Anyone with access to the ComfyUI URL is trusted (a direct consequence of the localhost-only default).
- PyTorch and other dependencies are at the versions we ship or recommend in the README.
A report is in scope only if it affects a user operating within this threat model.
## What We Consider a Vulnerability
We want to hear about issues where a **reasonable user** — someone who does not install random untrusted nodes and who reads UI prompts and warnings before clicking through them — can be harmed by ComfyUI itself.
The clearest example: a workflow file that such a user might plausibly load and run, using only built-in nodes, that results in **untrusted code execution, arbitrary file read/write outside expected directories, or credential/data exfiltration**.
When submitting a report, please include a clear description of *why this is a problem for a typical local ComfyUI user*. Reports without this context are difficult to act on.
## What We Do Not Consider a Security Vulnerability
Please report the following through our regular [GitHub issues](https://github.com/comfyanonymous/ComfyUI/issues) instead. Filing them as security reports will likely cause them to be deprioritized or closed.
- **Issues requiring `--listen` or any non-default network exposure.** ComfyUI binds to localhost by default. If a remote attacker needs to reach the server for the attack to work, the user has chosen to expose it and is responsible for securing that deployment (firewall, reverse proxy, authentication, etc.). These are bugs, not vulnerabilities.
- **`torch.load` and related deserialization issues in old PyTorch versions.** These are upstream PyTorch issues. Our distributions ship with — and our documentation recommends — recent PyTorch versions where these are addressed.
- **Vulnerabilities that depend on outdated library versions** that we neither ship nor recommend (e.g., requiring PyTorch 2.6 or older).
- **Issues that require a specific custom node to be installed.** Custom nodes are third-party code. Report these to the maintainer of that node.
- **Crashes, hangs, or resource exhaustion from a loaded workflow.** Annoying, but not a security issue in our model. File a regular bug.
- **Social-engineering scenarios** where the user is expected to ignore an explicit UI warning or prompt.
## Reporting
If you believe you have found an issue that falls within the scope above, please report it privately via GitHub's [Report a vulnerability](https://github.com/comfyanonymous/ComfyUI/security/advisories/new) feature rather than opening a public issue.
Please include:
1. A description of the vulnerability and the affected component.
2. Reproduction steps, ideally with a minimal workflow file or proof-of-concept.
3. The ComfyUI version, install method (desktop / portable / manual), and OS.
4. An explanation of how this affects a typical local user as described in the threat model.
We will acknowledge valid reports and coordinate a fix and disclosure timeline with you.

View File

@ -67,7 +67,7 @@ class InternalRoutes:
(entry for entry in os.scandir(directory) if is_visible_file(entry)),
key=lambda entry: -entry.stat().st_mtime
)
return web.json_response([f"{entry.name} [{directory_type}]" for entry in sorted_files], status=200)
return web.json_response([entry.name for entry in sorted_files], status=200)
def get_app(self):

View File

@ -27,7 +27,7 @@ def frontend_install_warning_message():
return f"""
{get_missing_requirements_message()}
The ComfyUI frontend is shipped in a pip package so it needs to be updated separately from the ComfyUI code.
This error is happening because the ComfyUI frontend is no longer shipped as part of the main repo but as a pip package instead.
""".strip()
def parse_version(version: str) -> tuple[int, int, int]:
@ -38,54 +38,40 @@ def is_valid_version(version: str) -> bool:
pattern = r"^(\d+)\.(\d+)\.(\d+)$"
return bool(re.match(pattern, version))
def get_installed_frontend_version():
"""Get the currently installed frontend package version."""
frontend_version_str = version("comfyui-frontend-package")
return frontend_version_str
def get_required_frontend_version():
return get_required_packages_versions().get("comfyui-frontend-package", None)
COMFY_PACKAGE_VERSIONS = []
def get_comfy_package_versions():
"""List installed/required versions for every comfy* package in requirements.txt."""
if COMFY_PACKAGE_VERSIONS:
return COMFY_PACKAGE_VERSIONS.copy()
out = COMFY_PACKAGE_VERSIONS
for name, required in (get_required_packages_versions() or {}).items():
if not name.startswith("comfy"):
continue
try:
installed = version(name)
except Exception:
installed = None
out.append({"name": name, "installed": installed, "required": required})
return out.copy()
def check_frontend_version():
"""Check if the frontend version is up to date."""
def check_comfy_packages_versions():
"""Warn for every comfy* package whose installed version is below requirements.txt."""
from packaging.version import InvalidVersion, parse as parse_pep440
for pkg in get_comfy_package_versions():
installed_str = pkg["installed"]
required_str = pkg["required"]
if not installed_str or not required_str:
continue
try:
outdated = parse_pep440(installed_str) < parse_pep440(required_str)
except InvalidVersion as e:
logging.error(f"Failed to check {pkg['name']} version: {e}")
continue
if outdated:
try:
frontend_version_str = get_installed_frontend_version()
frontend_version = parse_version(frontend_version_str)
required_frontend_str = get_required_frontend_version()
required_frontend = parse_version(required_frontend_str)
if frontend_version < required_frontend:
app.logger.log_startup_warning(
f"""
________________________________________________________________________
WARNING WARNING WARNING WARNING WARNING
Installed {pkg["name"]} version {installed_str} is lower than the recommended version {required_str}.
Installed frontend version {".".join(map(str, frontend_version))} is lower than the recommended version {".".join(map(str, required_frontend))}.
{get_missing_requirements_message()}
{frontend_install_warning_message()}
________________________________________________________________________
""".strip()
)
else:
logging.info("{} version: {}".format(pkg["name"], installed_str))
logging.info("ComfyUI frontend version: {}".format(frontend_version_str))
except Exception as e:
logging.error(f"Failed to check frontend version: {e}")
REQUEST_TIMEOUT = 10 # seconds
@ -215,11 +201,6 @@ class FrontendManager:
def get_required_templates_version(cls) -> str:
return get_required_packages_versions().get("comfyui-workflow-templates", None)
@classmethod
def get_comfy_package_versions(cls):
"""List installed/required versions for every comfy* package in requirements.txt."""
return get_comfy_package_versions()
@classmethod
def default_frontend_path(cls) -> str:
try:
@ -360,7 +341,7 @@ comfyui-workflow-templates is not installed.
main error source might be request timeout or invalid URL.
"""
if version_string == DEFAULT_VERSION_STRING:
check_comfy_packages_versions()
check_frontend_version()
return cls.default_frontend_path()
repo_owner, repo_name, version = cls.parse_version_string(version_string)
@ -422,7 +403,7 @@ comfyui-workflow-templates is not installed.
except Exception as e:
logging.error("Failed to initialize frontend: %s", e)
logging.info("Falling back to the default frontend.")
check_comfy_packages_versions()
check_frontend_version()
return cls.default_frontend_path()
@classmethod
def template_asset_handler(cls):

View File

@ -1,7 +1,5 @@
from __future__ import annotations
import logging
from aiohttp import web
from typing import TYPE_CHECKING, TypedDict
@ -33,22 +31,8 @@ class NodeReplaceManager:
self._replacements: dict[str, list[NodeReplace]] = {}
def register(self, node_replace: NodeReplace):
"""Register a node replacement mapping.
Idempotent: if a replacement with the same (old_node_id, new_node_id)
is already registered, the duplicate is ignored. This prevents stale
entries from accumulating when custom nodes are reloaded in the same
process (e.g. via ComfyUI-Manager).
"""
existing = self._replacements.setdefault(node_replace.old_node_id, [])
for entry in existing:
if entry.new_node_id == node_replace.new_node_id:
logging.debug(
"Node replacement %s -> %s already registered, ignoring duplicate.",
node_replace.old_node_id, node_replace.new_node_id,
)
return
existing.append(node_replace)
"""Register a node replacement mapping."""
self._replacements.setdefault(node_replace.old_node_id, []).append(node_replace)
def get_replacement(self, old_node_id: str) -> list[NodeReplace] | None:
"""Get replacements for an old node ID."""

View File

@ -28,8 +28,8 @@ def get_file_info(path: str, relative_to: str) -> FileInfo:
return {
"path": os.path.relpath(path, relative_to).replace(os.sep, '/'),
"size": os.path.getsize(path),
"modified": int(os.path.getmtime(path) * 1000),
"created": int(os.path.getctime(path) * 1000),
"modified": os.path.getmtime(path),
"created": os.path.getctime(path)
}

View File

@ -2,6 +2,7 @@
precision mediump float;
uniform sampler2D u_image0;
uniform vec2 u_resolution;
uniform int u_int0; // Blend mode
uniform int u_int1; // Color tint
uniform float u_float0; // Intensity
@ -74,7 +75,7 @@ void main() {
float t0 = threshold - 0.15;
float t1 = threshold + 0.15;
vec2 texelSize = 1.0 / vec2(textureSize(u_image0, 0));
vec2 texelSize = 1.0 / u_resolution;
float radius2 = radius * radius;
float sampleScale = clamp(radius * 0.75, 0.35, 1.0);

View File

@ -12,6 +12,7 @@ const int RADIAL_SAMPLES = 12;
const float RADIAL_STRENGTH = 0.0003;
uniform sampler2D u_image0;
uniform vec2 u_resolution;
uniform int u_int0; // Blur type (BLUR_GAUSSIAN, BLUR_BOX, BLUR_RADIAL)
uniform float u_float0; // Blur radius/amount
uniform int u_pass; // Pass index (0 = horizontal, 1 = vertical)
@ -24,7 +25,7 @@ float gaussian(float x, float sigma) {
}
void main() {
vec2 texelSize = 1.0 / vec2(textureSize(u_image0, 0));
vec2 texelSize = 1.0 / u_resolution;
float radius = max(u_float0, 0.0);
// Radial (angular) blur - single pass, doesn't use separable

View File

@ -2,13 +2,14 @@
precision highp float;
uniform sampler2D u_image0;
uniform vec2 u_resolution;
uniform float u_float0; // strength [0.0 2.0] typical: 0.31.0
in vec2 v_texCoord;
layout(location = 0) out vec4 fragColor0;
void main() {
vec2 texel = 1.0 / vec2(textureSize(u_image0, 0));
vec2 texel = 1.0 / u_resolution;
// Sample center and neighbors
vec4 center = texture(u_image0, v_texCoord);

View File

@ -2,6 +2,7 @@
precision highp float;
uniform sampler2D u_image0;
uniform vec2 u_resolution;
uniform float u_float0; // amount [0.0 - 3.0] typical: 0.5-1.5
uniform float u_float1; // radius [0.5 - 10.0] blur radius in pixels
uniform float u_float2; // threshold [0.0 - 0.1] min difference to sharpen
@ -18,7 +19,7 @@ float getLuminance(vec3 color) {
}
void main() {
vec2 texel = 1.0 / vec2(textureSize(u_image0, 0));
vec2 texel = 1.0 / u_resolution;
float radius = max(u_float1, 0.5);
float amount = u_float0;
float threshold = u_float2;

View File

@ -431,10 +431,9 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust",
"description": "Adjusts image brightness and contrast using a real-time GPU fragment shader."
"category": "Image Tools/Color adjust"
}
]
},
"extra": {}
}
}

View File

@ -162,7 +162,7 @@
},
"revision": 0,
"config": {},
"name": "Canny to Image (Z-Image-Turbo)",
"name": "local-Canny to Image (Z-Image-Turbo)",
"inputNode": {
"id": -10,
"bounding": [
@ -1553,8 +1553,7 @@
"VHS_MetadataImage": true,
"VHS_KeepIntermediate": true
},
"category": "Image generation and editing/Canny to image",
"description": "Generates an image from a Canny edge map using Z-Image-Turbo, with text conditioning."
"category": "Image generation and editing/Canny to image"
}
]
},
@ -1575,4 +1574,4 @@
}
},
"version": 0.4
}
}

View File

@ -192,7 +192,7 @@
},
"revision": 0,
"config": {},
"name": "Canny to Video (LTX 2.0)",
"name": "local-Canny to Video (LTX 2.0)",
"inputNode": {
"id": -10,
"bounding": [
@ -3600,8 +3600,7 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Video generation and editing/Canny to video",
"description": "Generates video from Canny edge maps using LTX-2, with optional synchronized audio."
"category": "Video generation and editing/Canny to video"
}
]
},
@ -3617,4 +3616,4 @@
}
},
"version": 0.4
}
}

View File

@ -377,9 +377,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust",
"description": "Adds lens-style chromatic aberration (color fringing) using a real-time GPU fragment shader."
"category": "Image Tools/Color adjust"
}
]
}
}
}

View File

@ -596,8 +596,7 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust",
"description": "Adjusts saturation, temperature, tint, and vibrance using a real-time GPU fragment shader."
"category": "Image Tools/Color adjust"
}
]
}

View File

@ -1129,8 +1129,7 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust",
"description": "Balances colors across shadows, midtones, and highlights using a real-time GPU fragment shader."
"category": "Image Tools/Color adjust"
}
]
}

View File

@ -608,8 +608,7 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust",
"description": "Fine-tunes tone and color with per-channel curve adjustments using a real-time GPU fragment shader."
"category": "Image Tools/Color adjust"
}
]
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@ -160,7 +160,7 @@
},
"revision": 0,
"config": {},
"name": "Depth to Image (Z-Image-Turbo)",
"name": "local-Depth to Image (Z-Image-Turbo)",
"inputNode": {
"id": -10,
"bounding": [
@ -1579,8 +1579,7 @@
"VHS_MetadataImage": true,
"VHS_KeepIntermediate": true
},
"category": "Image generation and editing/Depth to image",
"description": "Generates an image from a depth map using Z-Image-Turbo with text conditioning."
"category": "Image generation and editing/Depth to image"
},
{
"id": "458bdf3c-4b58-421c-af50-c9c663a4d74c",
@ -2462,8 +2461,7 @@
]
},
"workflowRendererVersion": "LG"
},
"description": "Estimates a monocular depth map from an input image using the Lotus depth estimation model."
}
}
]
},
@ -2484,4 +2482,4 @@
"VHS_KeepIntermediate": true
},
"version": 0.4
}
}

View File

@ -261,7 +261,7 @@
},
"revision": 0,
"config": {},
"name": "Depth to Video (LTX 2.0)",
"name": "local-Depth to Video (LTX 2.0)",
"inputNode": {
"id": -10,
"bounding": [
@ -4233,8 +4233,7 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Video generation and editing/Depth to video",
"description": "Generates depth-controlled video with LTX-2: motion and structure follow a depth-reference video alongside text prompting, optional first-frame image conditioning, with optional synchronized audio."
"category": "Video generation and editing/Depth to video"
},
{
"id": "38b60539-50a7-42f9-a5fe-bdeca26272e2",
@ -5193,8 +5192,7 @@
],
"extra": {
"workflowRendererVersion": "LG"
},
"description": "Estimates a monocular depth map from an input image using the Lotus depth estimation model."
}
}
]
},
@ -5210,4 +5208,4 @@
"workflowRendererVersion": "LG"
},
"version": 0.4
}
}

View File

@ -450,10 +450,9 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Blur",
"description": "Applies bilateral (edge-preserving) blur to soften images while retaining detail."
"category": "Image Tools/Blur"
}
]
},
"extra": {}
}
}

View File

@ -580,9 +580,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust",
"description": "Adds procedural film grain texture for a cinematic look via GPU fragment shader."
"category": "Image Tools/Color adjust"
}
]
}
}
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@ -1,858 +0,0 @@
{
"revision": 0,
"last_node_id": 16,
"last_link_id": 0,
"nodes": [
{
"id": 16,
"type": "022693be-2baa-4009-870a-28921508a7ef",
"pos": [
-2990,
-3240
],
"size": [
410,
200
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"localized_name": "video",
"name": "video",
"type": "VIDEO",
"link": null
},
{
"label": "multiplier",
"name": "value",
"type": "INT",
"widget": {
"name": "value"
},
"link": null
},
{
"label": "enable_fps_multiplier",
"name": "value_1",
"type": "BOOLEAN",
"widget": {
"name": "value_1"
},
"link": null
},
{
"name": "model_name",
"type": "COMBO",
"widget": {
"name": "model_name"
},
"link": null
}
],
"outputs": [
{
"label": "VIDEO",
"name": "VIDEO_1",
"type": "VIDEO",
"links": []
},
{
"name": "IMAGE",
"type": "IMAGE",
"links": null
}
],
"properties": {
"proxyWidgets": [
[
"9",
"value"
],
[
"13",
"value"
],
[
"1",
"model_name"
]
],
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65,
"cnr_id": "comfy-core",
"ver": "0.19.3"
},
"widgets_values": [],
"title": "Frame Interpolation"
}
],
"links": [],
"version": 0.4,
"definitions": {
"subgraphs": [
{
"id": "022693be-2baa-4009-870a-28921508a7ef",
"version": 1,
"state": {
"lastGroupId": 0,
"lastNodeId": 17,
"lastLinkId": 28,
"lastRerouteId": 0
},
"revision": 0,
"config": {},
"name": "Frame Interpolation",
"inputNode": {
"id": -10,
"bounding": [
-2810,
-3070,
159.7421875,
120
]
},
"outputNode": {
"id": -20,
"bounding": [
-1270,
-3075,
120,
80
]
},
"inputs": [
{
"id": "05e31c51-dcb6-4a1e-9651-1b9ad4f7a287",
"name": "video",
"type": "VIDEO",
"linkIds": [
2
],
"localized_name": "video",
"pos": [
-2670.2578125,
-3050
]
},
{
"id": "feecb409-7d1c-4a99-9c63-50c5fecdd3c9",
"name": "value",
"type": "INT",
"linkIds": [
22
],
"label": "multiplier",
"pos": [
-2670.2578125,
-3030
]
},
{
"id": "0b8a861b-b581-4068-9e8c-f8d15daf1ca6",
"name": "value_1",
"type": "BOOLEAN",
"linkIds": [
23
],
"label": "enable_fps_multiplier",
"pos": [
-2670.2578125,
-3010
]
},
{
"id": "a22b101e-8773-4e17-a297-7ee3aae09162",
"name": "model_name",
"type": "COMBO",
"linkIds": [
24
],
"pos": [
-2670.2578125,
-2990
]
}
],
"outputs": [
{
"id": "ef2ada05-d5aa-492a-9394-6c3e71e39ebb",
"name": "VIDEO_1",
"type": "VIDEO",
"linkIds": [
26
],
"label": "VIDEO",
"pos": [
-1250,
-3055
]
},
{
"id": "5aacc622-2a07-4983-b31c-e04461f7f953",
"name": "IMAGE",
"type": "IMAGE",
"linkIds": [
28
],
"pos": [
-1250,
-3035
]
}
],
"widgets": [],
"nodes": [
{
"id": 1,
"type": "FrameInterpolationModelLoader",
"pos": [
-2510,
-3370
],
"size": [
370,
90
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [
{
"localized_name": "model_name",
"name": "model_name",
"type": "COMBO",
"widget": {
"name": "model_name"
},
"link": 24
}
],
"outputs": [
{
"localized_name": "INTERP_MODEL",
"name": "INTERP_MODEL",
"type": "INTERP_MODEL",
"links": [
1
]
}
],
"properties": {
"Node name for S&R": "FrameInterpolationModelLoader",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65,
"cnr_id": "comfy-core",
"ver": "0.19.3",
"models": [
{
"name": "film_net_fp16.safetensors",
"url": "https://huggingface.co/Comfy-Org/frame_interpolation/resolve/main/frame_interpolation/film_net_fp16.safetensors",
"directory": "frame_interpolation"
}
]
},
"widgets_values": [
"film_net_fp16.safetensors"
]
},
{
"id": 2,
"type": "FrameInterpolate",
"pos": [
-2040,
-3370
],
"size": [
270,
110
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [
{
"localized_name": "interp_model",
"name": "interp_model",
"type": "INTERP_MODEL",
"link": 1
},
{
"localized_name": "images",
"name": "images",
"type": "IMAGE",
"link": 3
},
{
"localized_name": "multiplier",
"name": "multiplier",
"type": "INT",
"widget": {
"name": "multiplier"
},
"link": 8
}
],
"outputs": [
{
"localized_name": "IMAGE",
"name": "IMAGE",
"type": "IMAGE",
"links": [
4,
28
]
}
],
"properties": {
"Node name for S&R": "FrameInterpolate",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65,
"cnr_id": "comfy-core",
"ver": "0.19.3"
},
"widgets_values": [
2
]
},
{
"id": 5,
"type": "CreateVideo",
"pos": [
-1600,
-3370
],
"size": [
270,
110
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"localized_name": "images",
"name": "images",
"type": "IMAGE",
"link": 4
},
{
"localized_name": "audio",
"name": "audio",
"shape": 7,
"type": "AUDIO",
"link": 5
},
{
"localized_name": "fps",
"name": "fps",
"type": "FLOAT",
"widget": {
"name": "fps"
},
"link": 12
}
],
"outputs": [
{
"localized_name": "VIDEO",
"name": "VIDEO",
"type": "VIDEO",
"links": [
26
]
}
],
"properties": {
"Node name for S&R": "CreateVideo",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65,
"cnr_id": "comfy-core",
"ver": "0.19.3"
},
"widgets_values": [
30
]
},
{
"id": 9,
"type": "PrimitiveInt",
"pos": [
-2500,
-2970
],
"size": [
270,
90
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"localized_name": "value",
"name": "value",
"type": "INT",
"widget": {
"name": "value"
},
"link": 22
}
],
"outputs": [
{
"localized_name": "INT",
"name": "INT",
"type": "INT",
"links": [
8,
19
]
}
],
"title": "Int (Multiplier)",
"properties": {
"Node name for S&R": "PrimitiveInt",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65,
"cnr_id": "comfy-core",
"ver": "0.19.3"
},
"widgets_values": [
2,
"fixed"
]
},
{
"id": 10,
"type": "ComfySwitchNode",
"pos": [
-1610,
-3120
],
"size": [
270,
130
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"localized_name": "on_false",
"name": "on_false",
"type": "*",
"link": 11
},
{
"localized_name": "on_true",
"name": "on_true",
"type": "*",
"link": 13
},
{
"localized_name": "switch",
"name": "switch",
"type": "BOOLEAN",
"widget": {
"name": "switch"
},
"link": 15
}
],
"outputs": [
{
"localized_name": "output",
"name": "output",
"type": "*",
"links": [
12
]
}
],
"properties": {
"Node name for S&R": "ComfySwitchNode",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65,
"cnr_id": "comfy-core",
"ver": "0.19.3"
},
"widgets_values": [
true
]
},
{
"id": 13,
"type": "PrimitiveBoolean",
"pos": [
-2500,
-2770
],
"size": [
310,
90
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"localized_name": "value",
"name": "value",
"type": "BOOLEAN",
"widget": {
"name": "value"
},
"link": 23
}
],
"outputs": [
{
"localized_name": "BOOLEAN",
"name": "BOOLEAN",
"type": "BOOLEAN",
"links": [
15
]
}
],
"title": "Boolean (Apply multiplier to FPS?)",
"properties": {
"Node name for S&R": "PrimitiveBoolean",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65,
"cnr_id": "comfy-core",
"ver": "0.19.3"
},
"widgets_values": [
true
]
},
{
"id": 3,
"type": "GetVideoComponents",
"pos": [
-2500,
-3170
],
"size": [
230,
100
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"localized_name": "video",
"name": "video",
"type": "VIDEO",
"link": 2
}
],
"outputs": [
{
"localized_name": "images",
"name": "images",
"type": "IMAGE",
"links": [
3
]
},
{
"localized_name": "audio",
"name": "audio",
"type": "AUDIO",
"links": [
5
]
},
{
"localized_name": "fps",
"name": "fps",
"type": "FLOAT",
"links": [
11,
18
]
}
],
"properties": {
"Node name for S&R": "GetVideoComponents",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65,
"cnr_id": "comfy-core",
"ver": "0.19.3"
}
},
{
"id": 11,
"type": "ComfyMathExpression",
"pos": [
-2090,
-3070
],
"size": [
400,
210
],
"flags": {
"collapsed": false
},
"order": 6,
"mode": 0,
"inputs": [
{
"label": "a",
"localized_name": "values.a",
"name": "values.a",
"type": "FLOAT,INT",
"link": 18
},
{
"label": "b",
"localized_name": "values.b",
"name": "values.b",
"shape": 7,
"type": "FLOAT,INT",
"link": 19
},
{
"label": "c",
"localized_name": "values.c",
"name": "values.c",
"shape": 7,
"type": "FLOAT,INT",
"link": null
},
{
"localized_name": "expression",
"name": "expression",
"type": "STRING",
"widget": {
"name": "expression"
},
"link": null
}
],
"outputs": [
{
"localized_name": "FLOAT",
"name": "FLOAT",
"type": "FLOAT",
"links": [
13
]
},
{
"localized_name": "INT",
"name": "INT",
"type": "INT",
"links": null
}
],
"properties": {
"Node name for S&R": "ComfyMathExpression",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65,
"cnr_id": "comfy-core",
"ver": "0.19.3"
},
"widgets_values": [
"min(abs(b), 16) * a"
]
}
],
"groups": [],
"links": [
{
"id": 1,
"origin_id": 1,
"origin_slot": 0,
"target_id": 2,
"target_slot": 0,
"type": "INTERP_MODEL"
},
{
"id": 3,
"origin_id": 3,
"origin_slot": 0,
"target_id": 2,
"target_slot": 1,
"type": "IMAGE"
},
{
"id": 8,
"origin_id": 9,
"origin_slot": 0,
"target_id": 2,
"target_slot": 2,
"type": "INT"
},
{
"id": 4,
"origin_id": 2,
"origin_slot": 0,
"target_id": 5,
"target_slot": 0,
"type": "IMAGE"
},
{
"id": 5,
"origin_id": 3,
"origin_slot": 1,
"target_id": 5,
"target_slot": 1,
"type": "AUDIO"
},
{
"id": 12,
"origin_id": 10,
"origin_slot": 0,
"target_id": 5,
"target_slot": 2,
"type": "FLOAT"
},
{
"id": 11,
"origin_id": 3,
"origin_slot": 2,
"target_id": 10,
"target_slot": 0,
"type": "FLOAT"
},
{
"id": 13,
"origin_id": 11,
"origin_slot": 0,
"target_id": 10,
"target_slot": 1,
"type": "FLOAT"
},
{
"id": 15,
"origin_id": 13,
"origin_slot": 0,
"target_id": 10,
"target_slot": 2,
"type": "BOOLEAN"
},
{
"id": 18,
"origin_id": 3,
"origin_slot": 2,
"target_id": 11,
"target_slot": 0,
"type": "FLOAT"
},
{
"id": 19,
"origin_id": 9,
"origin_slot": 0,
"target_id": 11,
"target_slot": 1,
"type": "INT"
},
{
"id": 2,
"origin_id": -10,
"origin_slot": 0,
"target_id": 3,
"target_slot": 0,
"type": "VIDEO"
},
{
"id": 22,
"origin_id": -10,
"origin_slot": 1,
"target_id": 9,
"target_slot": 0,
"type": "INT"
},
{
"id": 23,
"origin_id": -10,
"origin_slot": 2,
"target_id": 13,
"target_slot": 0,
"type": "BOOLEAN"
},
{
"id": 24,
"origin_id": -10,
"origin_slot": 3,
"target_id": 1,
"target_slot": 0,
"type": "COMBO"
},
{
"id": 26,
"origin_id": 5,
"origin_slot": 0,
"target_id": -20,
"target_slot": 0,
"type": "VIDEO"
},
{
"id": 28,
"origin_id": 2,
"origin_slot": 0,
"target_id": -20,
"target_slot": 1,
"type": "IMAGE"
}
],
"extra": {},
"category": "Video Tools",
"description": "Increases video frame rate by synthesizing intermediate frames with a frame interpolation model."
}
]
},
"extra": {}
}

View File

@ -1,485 +0,0 @@
{
"revision": 0,
"last_node_id": 98,
"last_link_id": 0,
"nodes": [
{
"id": 98,
"type": "dca6e78d-fb06-421e-97f7-6ce17a665260",
"pos": [
-410,
-2230
],
"size": [
270,
104
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "video",
"type": "VIDEO",
"link": null
},
{
"label": "frame_index",
"name": "value",
"type": "INT",
"widget": {
"name": "value"
},
"link": null
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": []
}
],
"title": "Get Any Video Frame",
"properties": {
"proxyWidgets": [
[
"100",
"value"
]
]
},
"widgets_values": []
}
],
"links": [],
"version": 0.4,
"definitions": {
"subgraphs": [
{
"id": "dca6e78d-fb06-421e-97f7-6ce17a665260",
"version": 1,
"state": {
"lastGroupId": 1,
"lastNodeId": 136,
"lastLinkId": 302,
"lastRerouteId": 0
},
"revision": 0,
"config": {},
"name": "Get Any Video Frame",
"inputNode": {
"id": -10,
"bounding": [
380,
-57,
120,
80
]
},
"outputNode": {
"id": -20,
"bounding": [
1460,
-57,
120,
60
]
},
"inputs": [
{
"id": "2ceec378-8dcf-4340-8570-155967f59a93",
"name": "video",
"type": "VIDEO",
"linkIds": [
4
],
"pos": [
480,
-37
]
},
{
"id": "819955f6-c686-4896-8032-ff2d0059109a",
"name": "value",
"type": "INT",
"linkIds": [
283
],
"label": "frame_index",
"pos": [
480,
-17
]
}
],
"outputs": [
{
"id": "1ab0684d-6a44-45b6-8aa4-a0b971a1d41e",
"name": "IMAGE",
"type": "IMAGE",
"linkIds": [
5
],
"pos": [
1480,
-37
]
}
],
"widgets": [],
"nodes": [
{
"id": 1,
"type": "GetVideoComponents",
"pos": [
560,
-150
],
"size": [
230,
120
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [
{
"localized_name": "video",
"name": "video",
"type": "VIDEO",
"link": 4
}
],
"outputs": [
{
"localized_name": "images",
"name": "images",
"type": "IMAGE",
"links": [
1,
2
]
},
{
"localized_name": "audio",
"name": "audio",
"type": "AUDIO",
"links": null
},
{
"localized_name": "fps",
"name": "fps",
"type": "FLOAT",
"links": null
}
],
"properties": {
"Node name for S&R": "GetVideoComponents"
}
},
{
"id": 2,
"type": "GetImageSize",
"pos": [
560,
50
],
"size": [
230,
120
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [
{
"localized_name": "image",
"name": "image",
"type": "IMAGE",
"link": 1
}
],
"outputs": [
{
"localized_name": "width",
"name": "width",
"type": "INT",
"links": null
},
{
"localized_name": "height",
"name": "height",
"type": "INT",
"links": null
},
{
"localized_name": "batch_size",
"name": "batch_size",
"type": "INT",
"links": [
285
]
}
],
"properties": {
"Node name for S&R": "GetImageSize"
}
},
{
"id": 3,
"type": "ImageFromBatch",
"pos": [
1130,
-150
],
"size": [
270,
140
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"localized_name": "image",
"name": "image",
"type": "IMAGE",
"link": 2
},
{
"localized_name": "batch_index",
"name": "batch_index",
"type": "INT",
"widget": {
"name": "batch_index"
},
"link": 286
},
{
"localized_name": "length",
"name": "length",
"type": "INT",
"widget": {
"name": "length"
},
"link": null
}
],
"outputs": [
{
"localized_name": "IMAGE",
"name": "IMAGE",
"type": "IMAGE",
"links": [
5
]
}
],
"properties": {
"Node name for S&R": "ImageFromBatch"
},
"widgets_values": [
0,
1
]
},
{
"id": 99,
"type": "ComfyMathExpression",
"pos": [
910,
100
],
"size": [
400,
200
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"label": "a",
"localized_name": "values.a",
"name": "values.a",
"type": "FLOAT,INT",
"link": 284
},
{
"label": "b",
"localized_name": "values.b",
"name": "values.b",
"shape": 7,
"type": "FLOAT,INT",
"link": 285
},
{
"label": "c",
"localized_name": "values.c",
"name": "values.c",
"shape": 7,
"type": "FLOAT,INT",
"link": null
},
{
"localized_name": "expression",
"name": "expression",
"type": "STRING",
"widget": {
"name": "expression"
},
"link": null
}
],
"outputs": [
{
"localized_name": "FLOAT",
"name": "FLOAT",
"type": "FLOAT",
"links": null
},
{
"localized_name": "INT",
"name": "INT",
"type": "INT",
"links": [
286
]
}
],
"properties": {
"Node name for S&R": "ComfyMathExpression"
},
"widgets_values": [
"min(max(int(a if a >= 0 else b + a), 0), b - 1)"
]
},
{
"id": 100,
"type": "PrimitiveInt",
"pos": [
560,
250
],
"size": [
270,
110
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"localized_name": "value",
"name": "value",
"type": "INT",
"widget": {
"name": "value"
},
"link": 283
}
],
"outputs": [
{
"localized_name": "INT",
"name": "INT",
"type": "INT",
"links": [
284
]
}
],
"properties": {
"Node name for S&R": "PrimitiveInt"
},
"widgets_values": [
0,
"fixed"
]
}
],
"groups": [],
"links": [
{
"id": 1,
"origin_id": 1,
"origin_slot": 0,
"target_id": 2,
"target_slot": 0,
"type": "IMAGE"
},
{
"id": 2,
"origin_id": 1,
"origin_slot": 0,
"target_id": 3,
"target_slot": 0,
"type": "IMAGE"
},
{
"id": 4,
"origin_id": -10,
"origin_slot": 0,
"target_id": 1,
"target_slot": 0,
"type": "VIDEO"
},
{
"id": 5,
"origin_id": 3,
"origin_slot": 0,
"target_id": -20,
"target_slot": 0,
"type": "IMAGE"
},
{
"id": 283,
"origin_id": -10,
"origin_slot": 1,
"target_id": 100,
"target_slot": 0,
"type": "INT"
},
{
"id": 284,
"origin_id": 100,
"origin_slot": 0,
"target_id": 99,
"target_slot": 0,
"type": "INT"
},
{
"id": 285,
"origin_id": 2,
"origin_slot": 2,
"target_id": 99,
"target_slot": 1,
"type": "INT"
},
{
"id": 286,
"origin_id": 99,
"origin_slot": 1,
"target_id": 3,
"target_slot": 1,
"type": "INT"
}
],
"extra": {},
"category": "Video Tools",
"description": "Extracts one image frame from a video at a chosen index, with optional trim and FPS control."
}
]
},
"extra": {
"ds": {
"scale": 1.197015527856339,
"offset": [
-168.76833554248222,
540.6638955283997
]
},
"frontendVersion": "1.42.8"
}
}

View File

@ -268,7 +268,7 @@
"Node name for S&R": "GLSLShader"
},
"widgets_values": [
"#version 300 es\nprecision mediump float;\n\nuniform sampler2D u_image0;\nuniform int u_int0; // Blend mode\nuniform int u_int1; // Color tint\nuniform float u_float0; // Intensity\nuniform float u_float1; // Radius\nuniform float u_float2; // Threshold\n\nin vec2 v_texCoord;\nout vec4 fragColor;\n\nconst int BLEND_ADD = 0;\nconst int BLEND_SCREEN = 1;\nconst int BLEND_SOFT = 2;\nconst int BLEND_OVERLAY = 3;\nconst int BLEND_LIGHTEN = 4;\n\nconst float GOLDEN_ANGLE = 2.39996323;\nconst int MAX_SAMPLES = 48;\nconst vec3 LUMA = vec3(0.299, 0.587, 0.114);\n\nfloat hash(vec2 p) {\n p = fract(p * vec2(123.34, 456.21));\n p += dot(p, p + 45.32);\n return fract(p.x * p.y);\n}\n\nvec3 hexToRgb(int h) {\n return vec3(\n float((h >> 16) & 255),\n float((h >> 8) & 255),\n float(h & 255)\n ) * (1.0 / 255.0);\n}\n\nvec3 blend(vec3 base, vec3 glow, int mode) {\n if (mode == BLEND_SCREEN) {\n return 1.0 - (1.0 - base) * (1.0 - glow);\n }\n if (mode == BLEND_SOFT) {\n return mix(\n base - (1.0 - 2.0 * glow) * base * (1.0 - base),\n base + (2.0 * glow - 1.0) * (sqrt(base) - base),\n step(0.5, glow)\n );\n }\n if (mode == BLEND_OVERLAY) {\n return mix(\n 2.0 * base * glow,\n 1.0 - 2.0 * (1.0 - base) * (1.0 - glow),\n step(0.5, base)\n );\n }\n if (mode == BLEND_LIGHTEN) {\n return max(base, glow);\n }\n return base + glow;\n}\n\nvoid main() {\n vec4 original = texture(u_image0, v_texCoord);\n \n float intensity = u_float0 * 0.05;\n float radius = u_float1 * u_float1 * 0.012;\n \n if (intensity < 0.001 || radius < 0.1) {\n fragColor = original;\n return;\n }\n \n float threshold = 1.0 - u_float2 * 0.01;\n float t0 = threshold - 0.15;\n float t1 = threshold + 0.15;\n \n vec2 texelSize = 1.0 / vec2(textureSize(u_image0, 0));\n float radius2 = radius * radius;\n \n float sampleScale = clamp(radius * 0.75, 0.35, 1.0);\n int samples = int(float(MAX_SAMPLES) * sampleScale);\n \n float noise = hash(gl_FragCoord.xy);\n float angleOffset = noise * GOLDEN_ANGLE;\n float radiusJitter = 0.85 + noise * 0.3;\n \n float ca = cos(GOLDEN_ANGLE);\n float sa = sin(GOLDEN_ANGLE);\n vec2 dir = vec2(cos(angleOffset), sin(angleOffset));\n \n vec3 glow = vec3(0.0);\n float totalWeight = 0.0;\n \n // Center tap\n float centerMask = smoothstep(t0, t1, dot(original.rgb, LUMA));\n glow += original.rgb * centerMask * 2.0;\n totalWeight += 2.0;\n \n for (int i = 1; i < MAX_SAMPLES; i++) {\n if (i >= samples) break;\n \n float fi = float(i);\n float dist = sqrt(fi / float(samples)) * radius * radiusJitter;\n \n vec2 offset = dir * dist * texelSize;\n vec3 c = texture(u_image0, v_texCoord + offset).rgb;\n float mask = smoothstep(t0, t1, dot(c, LUMA));\n \n float w = 1.0 - (dist * dist) / (radius2 * 1.5);\n w = max(w, 0.0);\n w *= w;\n \n glow += c * mask * w;\n totalWeight += w;\n \n dir = vec2(\n dir.x * ca - dir.y * sa,\n dir.x * sa + dir.y * ca\n );\n }\n \n glow *= intensity / max(totalWeight, 0.001);\n \n if (u_int1 > 0) {\n glow *= hexToRgb(u_int1);\n }\n \n vec3 result = blend(original.rgb, glow, u_int0);\n result += (noise - 0.5) * (1.0 / 255.0);\n \n fragColor = vec4(clamp(result, 0.0, 1.0), original.a);\n}",
"#version 300 es\nprecision mediump float;\n\nuniform sampler2D u_image0;\nuniform vec2 u_resolution;\nuniform int u_int0; // Blend mode\nuniform int u_int1; // Color tint\nuniform float u_float0; // Intensity\nuniform float u_float1; // Radius\nuniform float u_float2; // Threshold\n\nin vec2 v_texCoord;\nout vec4 fragColor;\n\nconst int BLEND_ADD = 0;\nconst int BLEND_SCREEN = 1;\nconst int BLEND_SOFT = 2;\nconst int BLEND_OVERLAY = 3;\nconst int BLEND_LIGHTEN = 4;\n\nconst float GOLDEN_ANGLE = 2.39996323;\nconst int MAX_SAMPLES = 48;\nconst vec3 LUMA = vec3(0.299, 0.587, 0.114);\n\nfloat hash(vec2 p) {\n p = fract(p * vec2(123.34, 456.21));\n p += dot(p, p + 45.32);\n return fract(p.x * p.y);\n}\n\nvec3 hexToRgb(int h) {\n return vec3(\n float((h >> 16) & 255),\n float((h >> 8) & 255),\n float(h & 255)\n ) * (1.0 / 255.0);\n}\n\nvec3 blend(vec3 base, vec3 glow, int mode) {\n if (mode == BLEND_SCREEN) {\n return 1.0 - (1.0 - base) * (1.0 - glow);\n }\n if (mode == BLEND_SOFT) {\n return mix(\n base - (1.0 - 2.0 * glow) * base * (1.0 - base),\n base + (2.0 * glow - 1.0) * (sqrt(base) - base),\n step(0.5, glow)\n );\n }\n if (mode == BLEND_OVERLAY) {\n return mix(\n 2.0 * base * glow,\n 1.0 - 2.0 * (1.0 - base) * (1.0 - glow),\n step(0.5, base)\n );\n }\n if (mode == BLEND_LIGHTEN) {\n return max(base, glow);\n }\n return base + glow;\n}\n\nvoid main() {\n vec4 original = texture(u_image0, v_texCoord);\n \n float intensity = u_float0 * 0.05;\n float radius = u_float1 * u_float1 * 0.012;\n \n if (intensity < 0.001 || radius < 0.1) {\n fragColor = original;\n return;\n }\n \n float threshold = 1.0 - u_float2 * 0.01;\n float t0 = threshold - 0.15;\n float t1 = threshold + 0.15;\n \n vec2 texelSize = 1.0 / u_resolution;\n float radius2 = radius * radius;\n \n float sampleScale = clamp(radius * 0.75, 0.35, 1.0);\n int samples = int(float(MAX_SAMPLES) * sampleScale);\n \n float noise = hash(gl_FragCoord.xy);\n float angleOffset = noise * GOLDEN_ANGLE;\n float radiusJitter = 0.85 + noise * 0.3;\n \n float ca = cos(GOLDEN_ANGLE);\n float sa = sin(GOLDEN_ANGLE);\n vec2 dir = vec2(cos(angleOffset), sin(angleOffset));\n \n vec3 glow = vec3(0.0);\n float totalWeight = 0.0;\n \n // Center tap\n float centerMask = smoothstep(t0, t1, dot(original.rgb, LUMA));\n glow += original.rgb * centerMask * 2.0;\n totalWeight += 2.0;\n \n for (int i = 1; i < MAX_SAMPLES; i++) {\n if (i >= samples) break;\n \n float fi = float(i);\n float dist = sqrt(fi / float(samples)) * radius * radiusJitter;\n \n vec2 offset = dir * dist * texelSize;\n vec3 c = texture(u_image0, v_texCoord + offset).rgb;\n float mask = smoothstep(t0, t1, dot(c, LUMA));\n \n float w = 1.0 - (dist * dist) / (radius2 * 1.5);\n w = max(w, 0.0);\n w *= w;\n \n glow += c * mask * w;\n totalWeight += w;\n \n dir = vec2(\n dir.x * ca - dir.y * sa,\n dir.x * sa + dir.y * ca\n );\n }\n \n glow *= intensity / max(totalWeight, 0.001);\n \n if (u_int1 > 0) {\n glow *= hexToRgb(u_int1);\n }\n \n vec3 result = blend(original.rgb, glow, u_int0);\n result += (noise - 0.5) * (1.0 / 255.0);\n \n fragColor = vec4(clamp(result, 0.0, 1.0), original.a);\n}",
"from_input"
]
},
@ -575,9 +575,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust",
"description": "Adds a glow/bloom effect around bright image areas via GPU fragment shader."
"category": "Image Tools/Color adjust"
}
]
}
}
}

View File

@ -752,9 +752,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust",
"description": "Adjusts hue, saturation, and lightness of an image using a real-time GPU fragment shader."
"category": "Image Tools/Color adjust"
}
]
}
}
}

View File

@ -331,7 +331,7 @@
"Node name for S&R": "GLSLShader"
},
"widgets_values": [
"#version 300 es\n#pragma passes 2\nprecision highp float;\n\n// Blur type constants\nconst int BLUR_GAUSSIAN = 0;\nconst int BLUR_BOX = 1;\nconst int BLUR_RADIAL = 2;\n\n// Radial blur config\nconst int RADIAL_SAMPLES = 12;\nconst float RADIAL_STRENGTH = 0.0003;\n\nuniform sampler2D u_image0;\nuniform int u_int0; // Blur type (BLUR_GAUSSIAN, BLUR_BOX, BLUR_RADIAL)\nuniform float u_float0; // Blur radius/amount\nuniform int u_pass; // Pass index (0 = horizontal, 1 = vertical)\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\n\nfloat gaussian(float x, float sigma) {\n return exp(-(x * x) / (2.0 * sigma * sigma));\n}\n\nvoid main() {\n vec2 texelSize = 1.0 / vec2(textureSize(u_image0, 0));\n float radius = max(u_float0, 0.0);\n\n // Radial (angular) blur - single pass, doesn't use separable\n if (u_int0 == BLUR_RADIAL) {\n // Only execute on first pass\n if (u_pass > 0) {\n fragColor0 = texture(u_image0, v_texCoord);\n return;\n }\n\n vec2 center = vec2(0.5);\n vec2 dir = v_texCoord - center;\n float dist = length(dir);\n\n if (dist < 1e-4) {\n fragColor0 = texture(u_image0, v_texCoord);\n return;\n }\n\n vec4 sum = vec4(0.0);\n float totalWeight = 0.0;\n float angleStep = radius * RADIAL_STRENGTH;\n\n dir /= dist;\n\n float cosStep = cos(angleStep);\n float sinStep = sin(angleStep);\n\n float negAngle = -float(RADIAL_SAMPLES) * angleStep;\n vec2 rotDir = vec2(\n dir.x * cos(negAngle) - dir.y * sin(negAngle),\n dir.x * sin(negAngle) + dir.y * cos(negAngle)\n );\n\n for (int i = -RADIAL_SAMPLES; i <= RADIAL_SAMPLES; i++) {\n vec2 uv = center + rotDir * dist;\n float w = 1.0 - abs(float(i)) / float(RADIAL_SAMPLES);\n sum += texture(u_image0, uv) * w;\n totalWeight += w;\n\n rotDir = vec2(\n rotDir.x * cosStep - rotDir.y * sinStep,\n rotDir.x * sinStep + rotDir.y * cosStep\n );\n }\n\n fragColor0 = sum / max(totalWeight, 0.001);\n return;\n }\n\n // Separable Gaussian / Box blur\n int samples = int(ceil(radius));\n\n if (samples == 0) {\n fragColor0 = texture(u_image0, v_texCoord);\n return;\n }\n\n // Direction: pass 0 = horizontal, pass 1 = vertical\n vec2 dir = (u_pass == 0) ? vec2(1.0, 0.0) : vec2(0.0, 1.0);\n\n vec4 color = vec4(0.0);\n float totalWeight = 0.0;\n float sigma = radius / 2.0;\n\n for (int i = -samples; i <= samples; i++) {\n vec2 offset = dir * float(i) * texelSize;\n vec4 sample_color = texture(u_image0, v_texCoord + offset);\n\n float weight;\n if (u_int0 == BLUR_GAUSSIAN) {\n weight = gaussian(float(i), sigma);\n } else {\n // BLUR_BOX\n weight = 1.0;\n }\n\n color += sample_color * weight;\n totalWeight += weight;\n }\n\n fragColor0 = color / totalWeight;\n}\n",
"#version 300 es\n#pragma passes 2\nprecision highp float;\n\n// Blur type constants\nconst int BLUR_GAUSSIAN = 0;\nconst int BLUR_BOX = 1;\nconst int BLUR_RADIAL = 2;\n\n// Radial blur config\nconst int RADIAL_SAMPLES = 12;\nconst float RADIAL_STRENGTH = 0.0003;\n\nuniform sampler2D u_image0;\nuniform vec2 u_resolution;\nuniform int u_int0; // Blur type (BLUR_GAUSSIAN, BLUR_BOX, BLUR_RADIAL)\nuniform float u_float0; // Blur radius/amount\nuniform int u_pass; // Pass index (0 = horizontal, 1 = vertical)\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\n\nfloat gaussian(float x, float sigma) {\n return exp(-(x * x) / (2.0 * sigma * sigma));\n}\n\nvoid main() {\n vec2 texelSize = 1.0 / u_resolution;\n float radius = max(u_float0, 0.0);\n\n // Radial (angular) blur - single pass, doesn't use separable\n if (u_int0 == BLUR_RADIAL) {\n // Only execute on first pass\n if (u_pass > 0) {\n fragColor0 = texture(u_image0, v_texCoord);\n return;\n }\n\n vec2 center = vec2(0.5);\n vec2 dir = v_texCoord - center;\n float dist = length(dir);\n\n if (dist < 1e-4) {\n fragColor0 = texture(u_image0, v_texCoord);\n return;\n }\n\n vec4 sum = vec4(0.0);\n float totalWeight = 0.0;\n float angleStep = radius * RADIAL_STRENGTH;\n\n dir /= dist;\n\n float cosStep = cos(angleStep);\n float sinStep = sin(angleStep);\n\n float negAngle = -float(RADIAL_SAMPLES) * angleStep;\n vec2 rotDir = vec2(\n dir.x * cos(negAngle) - dir.y * sin(negAngle),\n dir.x * sin(negAngle) + dir.y * cos(negAngle)\n );\n\n for (int i = -RADIAL_SAMPLES; i <= RADIAL_SAMPLES; i++) {\n vec2 uv = center + rotDir * dist;\n float w = 1.0 - abs(float(i)) / float(RADIAL_SAMPLES);\n sum += texture(u_image0, uv) * w;\n totalWeight += w;\n\n rotDir = vec2(\n rotDir.x * cosStep - rotDir.y * sinStep,\n rotDir.x * sinStep + rotDir.y * cosStep\n );\n }\n\n fragColor0 = sum / max(totalWeight, 0.001);\n return;\n }\n\n // Separable Gaussian / Box blur\n int samples = int(ceil(radius));\n\n if (samples == 0) {\n fragColor0 = texture(u_image0, v_texCoord);\n return;\n }\n\n // Direction: pass 0 = horizontal, pass 1 = vertical\n vec2 dir = (u_pass == 0) ? vec2(1.0, 0.0) : vec2(0.0, 1.0);\n\n vec4 color = vec4(0.0);\n float totalWeight = 0.0;\n float sigma = radius / 2.0;\n\n for (int i = -samples; i <= samples; i++) {\n vec2 offset = dir * float(i) * texelSize;\n vec4 sample_color = texture(u_image0, v_texCoord + offset);\n\n float weight;\n if (u_int0 == BLUR_GAUSSIAN) {\n weight = gaussian(float(i), sigma);\n } else {\n // BLUR_BOX\n weight = 1.0;\n }\n\n color += sample_color * weight;\n totalWeight += weight;\n }\n\n fragColor0 = color / totalWeight;\n}\n",
"from_input"
]
}
@ -374,8 +374,7 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Blur",
"description": "Applies Gaussian, Box, or Radial blur to soften images and create stylized depth or motion effects."
"category": "Image Tools/Blur"
}
]
}

View File

@ -310,8 +310,7 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Text generation/Image Captioning",
"description": "Generates descriptive captions for images using Google's Gemini multimodal LLM."
"category": "Text generation/Image Captioning"
}
]
}

View File

@ -315,9 +315,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust",
"description": "Manipulates individual RGBA channels for masking, compositing, and channel effects."
"category": "Image Tools/Color adjust"
}
]
}
}
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@ -128,7 +128,7 @@
},
"revision": 0,
"config": {},
"name": "Image Edit (Flux.2 Klein 4B)",
"name": "local-Image Edit (Flux.2 Klein 4B)",
"inputNode": {
"id": -10,
"bounding": [
@ -1472,8 +1472,7 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image generation and editing/Edit image",
"description": "Edits an input image via text instructions using FLUX.2 [klein] 4B."
"category": "Image generation and editing/Edit image"
},
{
"id": "6007e698-2ebd-4917-84d8-299b35d7b7ab",
@ -1822,8 +1821,7 @@
],
"extra": {
"workflowRendererVersion": "LG"
},
"description": "Applies reference image conditioning for style/identity transfer (Flux.2 Klein 4B)."
}
}
]
},

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@ -132,7 +132,7 @@
},
"revision": 0,
"config": {},
"name": "Image Edit (Qwen 2511)",
"name": "local-Image Edit (Qwen 2511)",
"inputNode": {
"id": -10,
"bounding": [
@ -1468,8 +1468,7 @@
"VHS_MetadataImage": true,
"VHS_KeepIntermediate": true
},
"category": "Image generation and editing/Edit image",
"description": "Edits images via text instructions using Qwen-Image-Edit-2511 with improved character consistency and integrated LoRA."
"category": "Image generation and editing/Edit image"
}
]
},
@ -1490,4 +1489,4 @@
}
},
"version": 0.4
}
}

File diff suppressed because it is too large Load Diff

View File

@ -124,7 +124,7 @@
},
"revision": 0,
"config": {},
"name": "Image Inpainting (Qwen-image)",
"name": "local-Image Inpainting (Qwen-image)",
"inputNode": {
"id": -10,
"bounding": [
@ -1548,8 +1548,7 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image generation and editing/Inpaint image",
"description": "Inpaints masked regions using Qwen-Image, extending its multilingual text rendering to inpainting tasks."
"category": "Image generation and editing/Inpaint image"
},
{
"id": "56a1f603-fbd2-40ed-94ef-c9ecbd96aca8",
@ -1908,8 +1907,7 @@
],
"extra": {
"workflowRendererVersion": "LG"
},
"description": "Expands and softens mask edges to reduce visible seams after image processing."
}
}
]
},
@ -1925,4 +1923,4 @@
"workflowRendererVersion": "LG"
},
"version": 0.4
}
}

View File

@ -742,10 +742,9 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust",
"description": "Adjusts black point, white point, and gamma for tonal range control via GPU shader."
"category": "Image Tools/Color adjust"
}
]
},
"extra": {}
}
}

View File

@ -204,7 +204,7 @@
},
"revision": 0,
"config": {},
"name": "Image Outpainting (Qwen-Image)",
"name": "local-Image Outpainting (Qwen-Image)",
"inputNode": {
"id": -10,
"bounding": [
@ -1919,8 +1919,7 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image generation and editing/Outpaint image",
"description": "Outpaints beyond image boundaries using Qwen-Image's outpainting capabilities."
"category": "Image generation and editing/Outpaint image"
},
{
"id": "f93c215e-c393-460e-9534-ed2c3d8a652e",
@ -2279,8 +2278,7 @@
],
"extra": {
"workflowRendererVersion": "LG"
},
"description": "Expands and softens mask edges to reduce visible seams after image processing."
}
},
{
"id": "2a4b2cc0-db37-4302-a067-da392f38f06b",
@ -2735,8 +2733,7 @@
],
"extra": {
"workflowRendererVersion": "LG"
},
"description": "Scales both image and mask together while preserving alignment for editing workflows."
}
}
]
},
@ -2752,4 +2749,4 @@
}
},
"version": 0.4
}
}

View File

@ -1,714 +0,0 @@
{
"revision": 0,
"last_node_id": 99,
"last_link_id": 0,
"nodes": [
{
"id": 99,
"type": "6e7ab3ea-96aa-470f-9b94-3d9d0e01f481",
"pos": [
-1630,
-3270
],
"size": [
290,
370
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"label": "image",
"localized_name": "image",
"name": "image",
"type": "IMAGE",
"link": null
},
{
"label": "object",
"name": "text",
"type": "STRING",
"widget": {
"name": "text"
},
"link": null
},
{
"name": "bboxes",
"type": "BOUNDING_BOX",
"link": null
},
{
"name": "positive_coords",
"type": "STRING",
"link": null
},
{
"name": "negative_coords",
"type": "STRING",
"link": null
},
{
"name": "threshold",
"type": "FLOAT",
"widget": {
"name": "threshold"
},
"link": null
},
{
"name": "refine_iterations",
"type": "INT",
"widget": {
"name": "refine_iterations"
},
"link": null
},
{
"name": "individual_masks",
"type": "BOOLEAN",
"widget": {
"name": "individual_masks"
},
"link": null
},
{
"name": "ckpt_name",
"type": "COMBO",
"widget": {
"name": "ckpt_name"
},
"link": null
}
],
"outputs": [
{
"localized_name": "masks",
"name": "masks",
"type": "MASK",
"links": []
},
{
"localized_name": "bboxes",
"name": "bboxes",
"type": "BOUNDING_BOX",
"links": []
}
],
"properties": {
"proxyWidgets": [
[
"78",
"text"
],
[
"75",
"threshold"
],
[
"75",
"refine_iterations"
],
[
"75",
"individual_masks"
],
[
"77",
"ckpt_name"
]
],
"ue_properties": {
"widget_ue_connectable": {
"text": true
},
"version": "7.7",
"input_ue_unconnectable": {}
},
"cnr_id": "comfy-core",
"ver": "0.19.3",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
},
"widgets_values": [],
"title": "Image Segmentation (SAM3)"
}
],
"links": [],
"version": 0.4,
"definitions": {
"subgraphs": [
{
"id": "6e7ab3ea-96aa-470f-9b94-3d9d0e01f481",
"version": 1,
"state": {
"lastGroupId": 0,
"lastNodeId": 113,
"lastLinkId": 283,
"lastRerouteId": 0
},
"revision": 0,
"config": {},
"name": "Image Segmentation (SAM3)",
"inputNode": {
"id": -10,
"bounding": [
-2260,
-3450,
136.369140625,
220
]
},
"outputNode": {
"id": -20,
"bounding": [
-1130,
-3305,
120,
80
]
},
"inputs": [
{
"id": "a6e75fa2-162a-4af0-a2fd-1e9c899a5ab6",
"name": "image",
"type": "IMAGE",
"linkIds": [
264
],
"localized_name": "image",
"label": "image",
"pos": [
-2143.630859375,
-3430
]
},
{
"id": "3cefd304-7631-4ff6-a5a0-5a0ffb120745",
"name": "text",
"type": "STRING",
"linkIds": [
265
],
"label": "object",
"pos": [
-2143.630859375,
-3410
]
},
{
"id": "1aec91c5-d8d2-441c-928c-49c14e7e80ed",
"name": "bboxes",
"type": "BOUNDING_BOX",
"linkIds": [
266
],
"pos": [
-2143.630859375,
-3390
]
},
{
"id": "1ec7ce1a-8257-4719-8a81-60ebc8a98899",
"name": "positive_coords",
"type": "STRING",
"linkIds": [
267
],
"pos": [
-2143.630859375,
-3370
]
},
{
"id": "c65f8b87-9bd7-48be-9fc2-823431e95019",
"name": "negative_coords",
"type": "STRING",
"linkIds": [
268
],
"pos": [
-2143.630859375,
-3350
]
},
{
"id": "bb4ba35a-ccfe-4c37-98e5-d9b0d69585fb",
"name": "threshold",
"type": "FLOAT",
"linkIds": [
269
],
"pos": [
-2143.630859375,
-3330
]
},
{
"id": "b1439668-b050-490b-a5dc-fc4052c55666",
"name": "refine_iterations",
"type": "INT",
"linkIds": [
270
],
"pos": [
-2143.630859375,
-3310
]
},
{
"id": "86e239e5-c098-4302-b54d-d42a38bc0f89",
"name": "individual_masks",
"type": "BOOLEAN",
"linkIds": [
271
],
"pos": [
-2143.630859375,
-3290
]
},
{
"id": "f9e0b9d4-b2f1-4907-a4a5-305656576706",
"name": "ckpt_name",
"type": "COMBO",
"linkIds": [
272
],
"pos": [
-2143.630859375,
-3270
]
}
],
"outputs": [
{
"id": "ff50da09-1e59-4a58-9b7f-be1a00aa5913",
"name": "masks",
"type": "MASK",
"linkIds": [
231
],
"localized_name": "masks",
"pos": [
-1110,
-3285
]
},
{
"id": "8f622e40-8528-4078-b7d3-147e9f872194",
"name": "bboxes",
"type": "BOUNDING_BOX",
"linkIds": [
232
],
"localized_name": "bboxes",
"pos": [
-1110,
-3265
]
}
],
"widgets": [],
"nodes": [
{
"id": 75,
"type": "SAM3_Detect",
"pos": [
-1470,
-3460
],
"size": [
270,
260
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [
{
"label": "model",
"localized_name": "model",
"name": "model",
"type": "MODEL",
"link": 237
},
{
"label": "image",
"localized_name": "image",
"name": "image",
"type": "IMAGE",
"link": 264
},
{
"label": "conditioning",
"localized_name": "conditioning",
"name": "conditioning",
"shape": 7,
"type": "CONDITIONING",
"link": 200
},
{
"label": "bboxes",
"localized_name": "bboxes",
"name": "bboxes",
"shape": 7,
"type": "BOUNDING_BOX",
"link": 266
},
{
"label": "positive_coords",
"localized_name": "positive_coords",
"name": "positive_coords",
"shape": 7,
"type": "STRING",
"link": 267
},
{
"label": "negative_coords",
"localized_name": "negative_coords",
"name": "negative_coords",
"shape": 7,
"type": "STRING",
"link": 268
},
{
"localized_name": "threshold",
"name": "threshold",
"type": "FLOAT",
"widget": {
"name": "threshold"
},
"link": 269
},
{
"localized_name": "refine_iterations",
"name": "refine_iterations",
"type": "INT",
"widget": {
"name": "refine_iterations"
},
"link": 270
},
{
"localized_name": "individual_masks",
"name": "individual_masks",
"type": "BOOLEAN",
"widget": {
"name": "individual_masks"
},
"link": 271
}
],
"outputs": [
{
"localized_name": "masks",
"name": "masks",
"type": "MASK",
"links": [
231
]
},
{
"localized_name": "bboxes",
"name": "bboxes",
"type": "BOUNDING_BOX",
"links": [
232
]
}
],
"properties": {
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.7",
"input_ue_unconnectable": {}
},
"cnr_id": "comfy-core",
"ver": "0.19.3",
"Node name for S&R": "SAM3_Detect",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
},
"widgets_values": [
0.5,
2,
false
]
},
{
"id": 77,
"type": "CheckpointLoaderSimple",
"pos": [
-1970,
-3200
],
"size": [
330,
140
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [
{
"localized_name": "ckpt_name",
"name": "ckpt_name",
"type": "COMBO",
"widget": {
"name": "ckpt_name"
},
"link": 272
}
],
"outputs": [
{
"localized_name": "MODEL",
"name": "MODEL",
"type": "MODEL",
"links": [
237
]
},
{
"localized_name": "CLIP",
"name": "CLIP",
"type": "CLIP",
"links": [
240
]
},
{
"localized_name": "VAE",
"name": "VAE",
"type": "VAE",
"links": null
}
],
"properties": {
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.7",
"input_ue_unconnectable": {}
},
"cnr_id": "comfy-core",
"ver": "0.19.3",
"Node name for S&R": "CheckpointLoaderSimple",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65,
"models": [
{
"name": "sam3.1_multiplex_fp16.safetensors",
"url": "https://huggingface.co/Comfy-Org/sam3.1/resolve/main/checkpoints/sam3.1_multiplex_fp16.safetensors",
"directory": "checkpoints"
}
]
},
"widgets_values": [
"sam3.1_multiplex_fp16.safetensors"
]
},
{
"id": 78,
"type": "CLIPTextEncode",
"pos": [
-2000,
-3000
],
"size": [
400,
200
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"localized_name": "clip",
"name": "clip",
"type": "CLIP",
"link": 240
},
{
"localized_name": "text",
"name": "text",
"type": "STRING",
"widget": {
"name": "text"
},
"link": 265
}
],
"outputs": [
{
"localized_name": "CONDITIONING",
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
200
]
}
],
"properties": {
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.7",
"input_ue_unconnectable": {}
},
"cnr_id": "comfy-core",
"ver": "0.19.3",
"Node name for S&R": "CLIPTextEncode",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
},
"widgets_values": [
""
]
}
],
"groups": [],
"links": [
{
"id": 237,
"origin_id": 77,
"origin_slot": 0,
"target_id": 75,
"target_slot": 0,
"type": "MODEL"
},
{
"id": 200,
"origin_id": 78,
"origin_slot": 0,
"target_id": 75,
"target_slot": 2,
"type": "CONDITIONING"
},
{
"id": 240,
"origin_id": 77,
"origin_slot": 1,
"target_id": 78,
"target_slot": 0,
"type": "CLIP"
},
{
"id": 231,
"origin_id": 75,
"origin_slot": 0,
"target_id": -20,
"target_slot": 0,
"type": "MASK"
},
{
"id": 232,
"origin_id": 75,
"origin_slot": 1,
"target_id": -20,
"target_slot": 1,
"type": "BOUNDING_BOX"
},
{
"id": 264,
"origin_id": -10,
"origin_slot": 0,
"target_id": 75,
"target_slot": 1,
"type": "IMAGE"
},
{
"id": 265,
"origin_id": -10,
"origin_slot": 1,
"target_id": 78,
"target_slot": 1,
"type": "STRING"
},
{
"id": 266,
"origin_id": -10,
"origin_slot": 2,
"target_id": 75,
"target_slot": 3,
"type": "BOUNDING_BOX"
},
{
"id": 267,
"origin_id": -10,
"origin_slot": 3,
"target_id": 75,
"target_slot": 4,
"type": "STRING"
},
{
"id": 268,
"origin_id": -10,
"origin_slot": 4,
"target_id": 75,
"target_slot": 5,
"type": "STRING"
},
{
"id": 269,
"origin_id": -10,
"origin_slot": 5,
"target_id": 75,
"target_slot": 6,
"type": "FLOAT"
},
{
"id": 270,
"origin_id": -10,
"origin_slot": 6,
"target_id": 75,
"target_slot": 7,
"type": "INT"
},
{
"id": 271,
"origin_id": -10,
"origin_slot": 7,
"target_id": 75,
"target_slot": 8,
"type": "BOOLEAN"
},
{
"id": 272,
"origin_id": -10,
"origin_slot": 8,
"target_id": 77,
"target_slot": 0,
"type": "COMBO"
}
],
"extra": {},
"category": "Image Tools/Image Segmentation",
"description": "Segments images into masks using Meta SAM3 from text prompts, points, or boxes."
}
]
},
"extra": {
"ue_links": []
}
}

View File

@ -141,7 +141,7 @@
},
"revision": 0,
"config": {},
"name": "Image Upscale (Z-image-Turbo)",
"name": "local-Image Upscale(Z-image-Turbo)",
"inputNode": {
"id": -10,
"bounding": [
@ -1302,8 +1302,7 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image generation and editing/Enhance",
"description": "Upscales images to higher resolution using Z-Image-Turbo."
"category": "Image generation and editing/Enhance"
}
]
},

View File

@ -99,7 +99,7 @@
},
"revision": 0,
"config": {},
"name": "Image to Depth Map (Lotus)",
"name": "local-Image to Depth Map (Lotus)",
"inputNode": {
"id": -10,
"bounding": [
@ -948,8 +948,7 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image generation and editing/Depth to image",
"description": "Estimates a monocular depth map from an input image using the Lotus depth estimation model."
"category": "Image generation and editing/Depth to image"
}
]
},
@ -965,4 +964,4 @@
"workflowRendererVersion": "LG"
},
"version": 0.4
}
}

View File

@ -1,14 +1,15 @@
{
"id": "1a761372-7c82-4016-b9bf-fa285967e1e9",
"revision": 0,
"last_node_id": 176,
"last_node_id": 83,
"last_link_id": 0,
"nodes": [
{
"id": 176,
"type": "2d2e3c8e-53b3-4618-be52-6d1d99382f0e",
"id": 83,
"type": "f754a936-daaf-4b6e-9658-41fdc54d301d",
"pos": [
-1150,
200
61.999827823554256,
153.3332507624185
],
"size": [
400,
@ -55,38 +56,6 @@
"name": "layers"
},
"link": null
},
{
"name": "seed",
"type": "INT",
"widget": {
"name": "seed"
},
"link": null
},
{
"name": "unet_name",
"type": "COMBO",
"widget": {
"name": "unet_name"
},
"link": null
},
{
"name": "clip_name",
"type": "COMBO",
"widget": {
"name": "clip_name"
},
"link": null
},
{
"name": "vae_name",
"type": "COMBO",
"widget": {
"name": "vae_name"
},
"link": null
}
],
"outputs": [
@ -97,41 +66,28 @@
"links": []
}
],
"title": "Image to Layers (Qwen-Image-Layered)",
"properties": {
"proxyWidgets": [
[
"6",
"-1",
"text"
],
[
"3",
"-1",
"steps"
],
[
"3",
"-1",
"cfg"
],
[
"83",
"-1",
"layers"
],
[
"3",
"seed"
],
[
"37",
"unet_name"
],
[
"38",
"clip_name"
],
[
"39",
"vae_name"
],
[
"3",
"control_after_generate"
@ -139,11 +95,6 @@
],
"cnr_id": "comfy-core",
"ver": "0.5.1",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.7"
},
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
@ -152,20 +103,25 @@
"secondTabOffset": 80,
"secondTabWidth": 65
},
"widgets_values": []
"widgets_values": [
"",
20,
2.5,
2
]
}
],
"links": [],
"version": 0.4,
"groups": [],
"definitions": {
"subgraphs": [
{
"id": "2d2e3c8e-53b3-4618-be52-6d1d99382f0e",
"id": "f754a936-daaf-4b6e-9658-41fdc54d301d",
"version": 1,
"state": {
"lastGroupId": 8,
"lastNodeId": 176,
"lastLinkId": 380,
"lastGroupId": 3,
"lastNodeId": 83,
"lastLinkId": 159,
"lastRerouteId": 0
},
"revision": 0,
@ -174,10 +130,10 @@
"inputNode": {
"id": -10,
"bounding": [
-720,
720,
-510,
523,
120,
220
140
]
},
"outputNode": {
@ -200,8 +156,8 @@
],
"localized_name": "image",
"pos": [
-620,
740
-410,
543
]
},
{
@ -212,8 +168,8 @@
150
],
"pos": [
-620,
760
-410,
563
]
},
{
@ -224,8 +180,8 @@
153
],
"pos": [
-620,
780
-410,
583
]
},
{
@ -236,8 +192,8 @@
154
],
"pos": [
-620,
800
-410,
603
]
},
{
@ -248,56 +204,8 @@
159
],
"pos": [
-620,
820
]
},
{
"id": "9f76338b-f4ca-4bb3-b61a-57b3f233061e",
"name": "seed",
"type": "INT",
"linkIds": [
377
],
"pos": [
-620,
840
]
},
{
"id": "8d0422d5-5eee-4f7e-9817-dc613cc62eca",
"name": "unet_name",
"type": "COMBO",
"linkIds": [
378
],
"pos": [
-620,
860
]
},
{
"id": "552eece2-a735-4d00-ae78-ded454622bc1",
"name": "clip_name",
"type": "COMBO",
"linkIds": [
379
],
"pos": [
-620,
880
]
},
{
"id": "1e6d141c-d0f9-4a2b-895c-b6780e57cfa0",
"name": "vae_name",
"type": "COMBO",
"linkIds": [
380
],
"pos": [
-620,
900
-410,
623
]
}
],
@ -323,14 +231,14 @@
"type": "CLIPLoader",
"pos": [
-320,
360
310
],
"size": [
350,
150
346.7470703125,
106
],
"flags": {},
"order": 5,
"order": 0,
"mode": 0,
"inputs": [
{
@ -340,7 +248,7 @@
"widget": {
"name": "clip_name"
},
"link": 379
"link": null
},
{
"localized_name": "type",
@ -375,14 +283,9 @@
}
],
"properties": {
"Node name for S&R": "CLIPLoader",
"cnr_id": "comfy-core",
"ver": "0.5.1",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.7"
},
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "qwen_2.5_vl_7b_fp8_scaled.safetensors",
@ -409,14 +312,14 @@
"type": "VAELoader",
"pos": [
-320,
580
460
],
"size": [
350,
110
346.7470703125,
58
],
"flags": {},
"order": 6,
"order": 1,
"mode": 0,
"inputs": [
{
@ -426,7 +329,7 @@
"widget": {
"name": "vae_name"
},
"link": 380
"link": null
}
],
"outputs": [
@ -442,14 +345,9 @@
}
],
"properties": {
"Node name for S&R": "VAELoader",
"cnr_id": "comfy-core",
"ver": "0.5.1",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.7"
},
"Node name for S&R": "VAELoader",
"models": [
{
"name": "qwen_image_layered_vae.safetensors",
@ -477,11 +375,11 @@
420
],
"size": [
430,
190
425.27801513671875,
180.6060791015625
],
"flags": {},
"order": 2,
"order": 3,
"mode": 0,
"inputs": [
{
@ -513,14 +411,9 @@
],
"title": "CLIP Text Encode (Negative Prompt)",
"properties": {
"Node name for S&R": "CLIPTextEncode",
"cnr_id": "comfy-core",
"ver": "0.5.1",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.7"
},
"Node name for S&R": "CLIPTextEncode",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
@ -539,12 +432,12 @@
"id": 70,
"type": "ReferenceLatent",
"pos": [
140,
700
330,
670
],
"size": [
210,
50
204.1666717529297,
46
],
"flags": {
"collapsed": true
@ -577,14 +470,9 @@
}
],
"properties": {
"Node name for S&R": "ReferenceLatent",
"cnr_id": "comfy-core",
"ver": "0.5.1",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.7"
},
"Node name for S&R": "ReferenceLatent",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
@ -592,18 +480,19 @@
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
}
},
"widgets_values": []
},
{
"id": 69,
"type": "ReferenceLatent",
"pos": [
160,
820
330,
710
],
"size": [
210,
50
204.1666717529297,
46
],
"flags": {
"collapsed": true
@ -636,14 +525,9 @@
}
],
"properties": {
"Node name for S&R": "ReferenceLatent",
"cnr_id": "comfy-core",
"ver": "0.5.1",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.7"
},
"Node name for S&R": "ReferenceLatent",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
@ -651,7 +535,8 @@
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
}
},
"widgets_values": []
},
{
"id": 66,
@ -662,10 +547,10 @@
],
"size": [
270,
110
58
],
"flags": {},
"order": 7,
"order": 4,
"mode": 0,
"inputs": [
{
@ -695,14 +580,9 @@
}
],
"properties": {
"Node name for S&R": "ModelSamplingAuraFlow",
"cnr_id": "comfy-core",
"ver": "0.5.1",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.7"
},
"Node name for S&R": "ModelSamplingAuraFlow",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
@ -720,11 +600,11 @@
"type": "LatentCutToBatch",
"pos": [
830,
140
160
],
"size": [
270,
140
82
],
"flags": {},
"order": 11,
@ -766,14 +646,9 @@
}
],
"properties": {
"Node name for S&R": "LatentCutToBatch",
"cnr_id": "comfy-core",
"ver": "0.5.1",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.7"
},
"Node name for S&R": "LatentCutToBatch",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
@ -791,12 +666,12 @@
"id": 71,
"type": "VAEEncode",
"pos": [
-280,
780
100,
690
],
"size": [
230,
100
140,
46
],
"flags": {
"collapsed": false
@ -829,14 +704,9 @@
}
],
"properties": {
"Node name for S&R": "VAEEncode",
"cnr_id": "comfy-core",
"ver": "0.5.1",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.7"
},
"Node name for S&R": "VAEEncode",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
@ -844,23 +714,24 @@
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
}
},
"widgets_values": []
},
{
"id": 8,
"type": "VAEDecode",
"pos": [
850,
370
310
],
"size": [
210,
50
46
],
"flags": {
"collapsed": true
},
"order": 3,
"order": 7,
"mode": 0,
"inputs": [
{
@ -888,14 +759,9 @@
}
],
"properties": {
"Node name for S&R": "VAEDecode",
"cnr_id": "comfy-core",
"ver": "0.5.1",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.7"
},
"Node name for S&R": "VAEDecode",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
@ -903,7 +769,8 @@
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
}
},
"widgets_values": []
},
{
"id": 6,
@ -913,11 +780,11 @@
180
],
"size": [
430,
170
422.84503173828125,
164.31304931640625
],
"flags": {},
"order": 1,
"order": 6,
"mode": 0,
"inputs": [
{
@ -949,14 +816,9 @@
],
"title": "CLIP Text Encode (Positive Prompt)",
"properties": {
"Node name for S&R": "CLIPTextEncode",
"cnr_id": "comfy-core",
"ver": "0.5.1",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.7"
},
"Node name for S&R": "CLIPTextEncode",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
@ -976,14 +838,14 @@
"type": "KSampler",
"pos": [
530,
340
280
],
"size": [
270,
400
],
"flags": {},
"order": 0,
"order": 5,
"mode": 0,
"inputs": [
{
@ -1017,7 +879,7 @@
"widget": {
"name": "seed"
},
"link": 377
"link": null
},
{
"localized_name": "steps",
@ -1077,14 +939,9 @@
}
],
"properties": {
"Node name for S&R": "KSampler",
"cnr_id": "comfy-core",
"ver": "0.5.1",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.7"
},
"Node name for S&R": "KSampler",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
@ -1107,12 +964,12 @@
"id": 78,
"type": "GetImageSize",
"pos": [
-280,
930
80,
790
],
"size": [
230,
140
210,
136
],
"flags": {},
"order": 12,
@ -1150,14 +1007,9 @@
}
],
"properties": {
"Node name for S&R": "GetImageSize",
"cnr_id": "comfy-core",
"ver": "0.5.1",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.7"
},
"Node name for S&R": "GetImageSize",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
@ -1165,23 +1017,23 @@
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
}
},
"widgets_values": []
},
{
"id": 83,
"type": "EmptyQwenImageLayeredLatentImage",
"pos": [
-280,
1120
320,
790
],
"size": [
340,
200
330.9341796875,
130
],
"flags": {},
"order": 13,
"mode": 0,
"showAdvanced": true,
"inputs": [
{
"localized_name": "width",
@ -1231,14 +1083,9 @@
}
],
"properties": {
"Node name for S&R": "EmptyQwenImageLayeredLatentImage",
"cnr_id": "comfy-core",
"ver": "0.5.1",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.7"
},
"Node name for S&R": "EmptyQwenImageLayeredLatentImage",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
@ -1262,11 +1109,11 @@
180
],
"size": [
350,
110
346.7470703125,
82
],
"flags": {},
"order": 4,
"order": 2,
"mode": 0,
"inputs": [
{
@ -1276,7 +1123,7 @@
"widget": {
"name": "unet_name"
},
"link": 378
"link": null
},
{
"localized_name": "weight_dtype",
@ -1300,14 +1147,9 @@
}
],
"properties": {
"Node name for S&R": "UNETLoader",
"cnr_id": "comfy-core",
"ver": "0.5.1",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.7"
},
"Node name for S&R": "UNETLoader",
"models": [
{
"name": "qwen_image_layered_bf16.safetensors",
@ -1349,8 +1191,8 @@
"bounding": [
-330,
110,
370,
610
366.7470703125,
421.6
],
"color": "#3f789e",
"font_size": 24,
@ -1549,48 +1391,16 @@
"target_id": 83,
"target_slot": 2,
"type": "INT"
},
{
"id": 377,
"origin_id": -10,
"origin_slot": 5,
"target_id": 3,
"target_slot": 4,
"type": "INT"
},
{
"id": 378,
"origin_id": -10,
"origin_slot": 6,
"target_id": 37,
"target_slot": 0,
"type": "COMBO"
},
{
"id": 379,
"origin_id": -10,
"origin_slot": 7,
"target_id": 38,
"target_slot": 0,
"type": "COMBO"
},
{
"id": 380,
"origin_id": -10,
"origin_slot": 8,
"target_id": 39,
"target_slot": 0,
"type": "COMBO"
}
],
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image generation and editing/Image to layers",
"description": "Decomposes an image into variable-resolution RGBA layers for independent editing using Qwen-Image-Layered."
"category": "Image generation and editing/Image to layers"
}
]
},
"config": {},
"extra": {
"ds": {
"scale": 1.14,
@ -1599,6 +1409,7 @@
6.855893974423647
]
},
"ue_links": []
}
}
"workflowRendererVersion": "LG"
},
"version": 0.4
}

View File

@ -72,7 +72,7 @@
},
"revision": 0,
"config": {},
"name": "Image to 3D Model (Hunyuan3d 2.1)",
"name": "local-Image to Model (Hunyuan3d 2.1)",
"inputNode": {
"id": -10,
"bounding": [
@ -765,8 +765,7 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "3D/Image to 3D Model",
"description": "Generates 3D mesh models from a single input image using Hunyuan3D 2.0/2.1."
"category": "3D/Image to 3D Model"
}
]
},

File diff suppressed because it is too large Load Diff

View File

@ -1,886 +0,0 @@
{
"revision": 0,
"last_node_id": 675,
"last_link_id": 0,
"nodes": [
{
"id": 675,
"type": "01b6a731-fb78-4070-9a38-c87146da9604",
"pos": [
-2480,
3400
],
"size": [
360,
433.3125
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"localized_name": "input",
"name": "input",
"type": "IMAGE,MASK",
"link": null
},
{
"label": "resize_target_longer_size",
"name": "resize_type.longer_size",
"type": "INT",
"widget": {
"name": "resize_type.longer_size"
},
"link": null
},
{
"name": "scale_method",
"type": "COMBO",
"widget": {
"name": "scale_method"
},
"link": null
},
{
"name": "draw_body",
"type": "BOOLEAN",
"widget": {
"name": "draw_body"
},
"link": null
},
{
"name": "draw_hands",
"type": "BOOLEAN",
"widget": {
"name": "draw_hands"
},
"link": null
},
{
"name": "draw_face",
"type": "BOOLEAN",
"widget": {
"name": "draw_face"
},
"link": null
},
{
"name": "draw_feet",
"type": "BOOLEAN",
"widget": {
"name": "draw_feet"
},
"link": null
},
{
"name": "stick_width",
"type": "INT",
"widget": {
"name": "stick_width"
},
"link": null
},
{
"name": "face_point_size",
"type": "INT",
"widget": {
"name": "face_point_size"
},
"link": null
},
{
"name": "score_threshold",
"type": "FLOAT",
"widget": {
"name": "score_threshold"
},
"link": null
},
{
"name": "ckpt_name",
"type": "COMBO",
"widget": {
"name": "ckpt_name"
},
"link": null
},
{
"name": "bboxes",
"shape": 7,
"type": "BOUNDING_BOX",
"link": null
}
],
"outputs": [
{
"localized_name": "IMAGE",
"name": "IMAGE",
"type": "IMAGE",
"links": []
},
{
"name": "keypoints",
"type": "POSE_KEYPOINT",
"links": null
}
],
"properties": {
"proxyWidgets": [
[
"674",
"resize_type.longer_size"
],
[
"674",
"scale_method"
],
[
"672",
"draw_body"
],
[
"672",
"draw_hands"
],
[
"672",
"draw_face"
],
[
"672",
"draw_feet"
],
[
"672",
"stick_width"
],
[
"672",
"face_point_size"
],
[
"672",
"score_threshold"
],
[
"673",
"ckpt_name"
]
],
"cnr_id": "comfy-core",
"ver": "0.15.1",
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.7",
"input_ue_unconnectable": {}
}
},
"widgets_values": [],
"title": "Image to Pose Map (SDPose-OOD)"
}
],
"links": [],
"version": 0.4,
"definitions": {
"subgraphs": [
{
"id": "01b6a731-fb78-4070-9a38-c87146da9604",
"version": 1,
"state": {
"lastGroupId": 0,
"lastNodeId": 676,
"lastLinkId": 1715,
"lastRerouteId": 0
},
"revision": 0,
"config": {},
"name": "Image to Pose Map (SDPose-OOD)",
"inputNode": {
"id": -10,
"bounding": [
-3290,
3590,
190.8984375,
288
]
},
"outputNode": {
"id": -20,
"bounding": [
-1756.2451602089645,
3366,
128,
88
]
},
"inputs": [
{
"id": "e24699c3-1356-4634-9eb4-19bb58e5c0b0",
"name": "input",
"type": "IMAGE,MASK",
"linkIds": [
1700
],
"localized_name": "input",
"pos": [
-3123.1015625,
3614
]
},
{
"id": "088eefc1-cd8a-4573-993f-9e4da008a12d",
"name": "resize_type.longer_size",
"type": "INT",
"linkIds": [
1704
],
"label": "resize_target_longer_size",
"pos": [
-3123.1015625,
3634
]
},
{
"id": "b6449bd3-73d4-41c8-b81f-cf8d33f76a2e",
"name": "scale_method",
"type": "COMBO",
"linkIds": [
1705
],
"pos": [
-3123.1015625,
3654
]
},
{
"id": "4cff52ad-ed07-4c97-8803-fcbd89554fd0",
"name": "draw_body",
"type": "BOOLEAN",
"linkIds": [
1706
],
"pos": [
-3123.1015625,
3674
]
},
{
"id": "7af63dce-f7df-4d7e-8215-d7c7f60bf81c",
"name": "draw_hands",
"type": "BOOLEAN",
"linkIds": [
1707
],
"pos": [
-3123.1015625,
3694
]
},
{
"id": "af3a9bce-61f9-4aca-b530-9f65e028b35e",
"name": "draw_face",
"type": "BOOLEAN",
"linkIds": [
1708
],
"pos": [
-3123.1015625,
3714
]
},
{
"id": "4620f6a3-2c85-4b79-ad8f-35d0326b568f",
"name": "draw_feet",
"type": "BOOLEAN",
"linkIds": [
1709
],
"pos": [
-3123.1015625,
3734
]
},
{
"id": "fee5d0c9-8d4b-4934-81d8-ba2206dc56cb",
"name": "stick_width",
"type": "INT",
"linkIds": [
1710
],
"pos": [
-3123.1015625,
3754
]
},
{
"id": "aafdd060-ba81-4324-a9cc-b656e1ebc133",
"name": "face_point_size",
"type": "INT",
"linkIds": [
1711
],
"pos": [
-3123.1015625,
3774
]
},
{
"id": "514c5503-f9e6-4d23-b1ae-1d3291acb2a3",
"name": "score_threshold",
"type": "FLOAT",
"linkIds": [
1712
],
"pos": [
-3123.1015625,
3794
]
},
{
"id": "ae46de61-2cc6-483e-8ee9-87e4144a2ffa",
"name": "ckpt_name",
"type": "COMBO",
"linkIds": [
1713
],
"pos": [
-3123.1015625,
3814
]
},
{
"id": "41bec0c6-dffa-4c78-9289-ee678715ae54",
"name": "bboxes",
"type": "BOUNDING_BOX",
"linkIds": [
1714
],
"pos": [
-3123.1015625,
3834
]
}
],
"outputs": [
{
"id": "f05ed8cc-9403-4f14-8085-4364b06f8a48",
"name": "IMAGE",
"type": "IMAGE",
"linkIds": [
1701
],
"localized_name": "IMAGE",
"pos": [
-1732.2451602089645,
3390
]
},
{
"id": "29a6584e-4685-4986-8ffd-e6d8539953fd",
"name": "keypoints",
"type": "POSE_KEYPOINT",
"linkIds": [
1715
],
"pos": [
-1732.2451602089645,
3410
]
}
],
"widgets": [],
"nodes": [
{
"id": 671,
"type": "SDPoseKeypointExtractor",
"pos": [
-2470,
3250
],
"size": [
270,
180
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [
{
"localized_name": "model",
"name": "model",
"type": "MODEL",
"link": 1696
},
{
"localized_name": "vae",
"name": "vae",
"type": "VAE",
"link": 1697
},
{
"localized_name": "image",
"name": "image",
"type": "IMAGE",
"link": 1698
},
{
"localized_name": "bboxes",
"name": "bboxes",
"shape": 7,
"type": "BOUNDING_BOX",
"link": 1714
},
{
"localized_name": "batch_size",
"name": "batch_size",
"type": "INT",
"widget": {
"name": "batch_size"
},
"link": null
}
],
"outputs": [
{
"localized_name": "keypoints",
"name": "keypoints",
"type": "POSE_KEYPOINT",
"links": [
1699,
1715
]
}
],
"properties": {
"Node name for S&R": "SDPoseKeypointExtractor",
"cnr_id": "comfy-core",
"ver": "0.15.0",
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.7",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
16
]
},
{
"id": 674,
"type": "ResizeImageMaskNode",
"pos": [
-2960,
3490
],
"size": [
270,
110
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"localized_name": "input",
"name": "input",
"type": "IMAGE,MASK",
"link": 1700
},
{
"localized_name": "resize_type",
"name": "resize_type",
"type": "COMFY_DYNAMICCOMBO_V3",
"widget": {
"name": "resize_type"
},
"link": null
},
{
"localized_name": "resize_type.longer_size",
"name": "resize_type.longer_size",
"type": "INT",
"widget": {
"name": "resize_type.longer_size"
},
"link": 1704
},
{
"localized_name": "scale_method",
"name": "scale_method",
"type": "COMBO",
"widget": {
"name": "scale_method"
},
"link": 1705
}
],
"outputs": [
{
"localized_name": "resized",
"name": "resized",
"type": "*",
"links": [
1698
]
}
],
"properties": {
"Node name for S&R": "ResizeImageMaskNode",
"cnr_id": "comfy-core",
"ver": "0.15.0",
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.7",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
"scale longer dimension",
1024,
"area"
]
},
{
"id": 672,
"type": "SDPoseDrawKeypoints",
"pos": [
-2120,
3260
],
"size": [
270,
280
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [
{
"localized_name": "keypoints",
"name": "keypoints",
"type": "POSE_KEYPOINT",
"link": 1699
},
{
"localized_name": "draw_body",
"name": "draw_body",
"type": "BOOLEAN",
"widget": {
"name": "draw_body"
},
"link": 1706
},
{
"localized_name": "draw_hands",
"name": "draw_hands",
"type": "BOOLEAN",
"widget": {
"name": "draw_hands"
},
"link": 1707
},
{
"localized_name": "draw_face",
"name": "draw_face",
"type": "BOOLEAN",
"widget": {
"name": "draw_face"
},
"link": 1708
},
{
"localized_name": "draw_feet",
"name": "draw_feet",
"type": "BOOLEAN",
"widget": {
"name": "draw_feet"
},
"link": 1709
},
{
"localized_name": "stick_width",
"name": "stick_width",
"type": "INT",
"widget": {
"name": "stick_width"
},
"link": 1710
},
{
"localized_name": "face_point_size",
"name": "face_point_size",
"type": "INT",
"widget": {
"name": "face_point_size"
},
"link": 1711
},
{
"localized_name": "score_threshold",
"name": "score_threshold",
"type": "FLOAT",
"widget": {
"name": "score_threshold"
},
"link": 1712
}
],
"outputs": [
{
"localized_name": "IMAGE",
"name": "IMAGE",
"type": "IMAGE",
"links": [
1701
]
}
],
"properties": {
"Node name for S&R": "SDPoseDrawKeypoints",
"cnr_id": "comfy-core",
"ver": "0.15.0",
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.7",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
true,
true,
true,
true,
4,
2,
0.5
]
},
{
"id": 673,
"type": "CheckpointLoaderSimple",
"pos": [
-2960,
3250
],
"size": [
390,
190
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"localized_name": "ckpt_name",
"name": "ckpt_name",
"type": "COMBO",
"widget": {
"name": "ckpt_name"
},
"link": 1713
}
],
"outputs": [
{
"localized_name": "MODEL",
"name": "MODEL",
"type": "MODEL",
"links": [
1696
]
},
{
"localized_name": "CLIP",
"name": "CLIP",
"type": "CLIP",
"links": []
},
{
"localized_name": "VAE",
"name": "VAE",
"type": "VAE",
"links": [
1697
]
}
],
"properties": {
"Node name for S&R": "CheckpointLoaderSimple",
"cnr_id": "comfy-core",
"ver": "0.15.0",
"models": [
{
"name": "sdpose_wholebody_fp16.safetensors",
"url": "https://huggingface.co/Comfy-Org/SDPose/resolve/main/checkpoints/sdpose_wholebody_fp16.safetensors",
"directory": "checkpoints"
}
],
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.7",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
"sdpose_wholebody_fp16.safetensors"
]
}
],
"groups": [],
"links": [
{
"id": 1696,
"origin_id": 673,
"origin_slot": 0,
"target_id": 671,
"target_slot": 0,
"type": "MODEL"
},
{
"id": 1697,
"origin_id": 673,
"origin_slot": 2,
"target_id": 671,
"target_slot": 1,
"type": "VAE"
},
{
"id": 1698,
"origin_id": 674,
"origin_slot": 0,
"target_id": 671,
"target_slot": 2,
"type": "IMAGE"
},
{
"id": 1699,
"origin_id": 671,
"origin_slot": 0,
"target_id": 672,
"target_slot": 0,
"type": "POSE_KEYPOINT"
},
{
"id": 1700,
"origin_id": -10,
"origin_slot": 0,
"target_id": 674,
"target_slot": 0,
"type": "IMAGE,MASK"
},
{
"id": 1701,
"origin_id": 672,
"origin_slot": 0,
"target_id": -20,
"target_slot": 0,
"type": "IMAGE"
},
{
"id": 1704,
"origin_id": -10,
"origin_slot": 1,
"target_id": 674,
"target_slot": 2,
"type": "INT"
},
{
"id": 1705,
"origin_id": -10,
"origin_slot": 2,
"target_id": 674,
"target_slot": 3,
"type": "COMBO"
},
{
"id": 1706,
"origin_id": -10,
"origin_slot": 3,
"target_id": 672,
"target_slot": 1,
"type": "BOOLEAN"
},
{
"id": 1707,
"origin_id": -10,
"origin_slot": 4,
"target_id": 672,
"target_slot": 2,
"type": "BOOLEAN"
},
{
"id": 1708,
"origin_id": -10,
"origin_slot": 5,
"target_id": 672,
"target_slot": 3,
"type": "BOOLEAN"
},
{
"id": 1709,
"origin_id": -10,
"origin_slot": 6,
"target_id": 672,
"target_slot": 4,
"type": "BOOLEAN"
},
{
"id": 1710,
"origin_id": -10,
"origin_slot": 7,
"target_id": 672,
"target_slot": 5,
"type": "INT"
},
{
"id": 1711,
"origin_id": -10,
"origin_slot": 8,
"target_id": 672,
"target_slot": 6,
"type": "INT"
},
{
"id": 1712,
"origin_id": -10,
"origin_slot": 9,
"target_id": 672,
"target_slot": 7,
"type": "FLOAT"
},
{
"id": 1713,
"origin_id": -10,
"origin_slot": 10,
"target_id": 673,
"target_slot": 0,
"type": "COMBO"
},
{
"id": 1714,
"origin_id": -10,
"origin_slot": 11,
"target_id": 671,
"target_slot": 3,
"type": "BOUNDING_BOX"
},
{
"id": 1715,
"origin_id": 671,
"origin_slot": 0,
"target_id": -20,
"target_slot": 1,
"type": "POSE_KEYPOINT"
}
],
"extra": {
"workflowRendererVersion": "LG"
}
}
]
},
"extra": {
"ue_links": []
}
}

File diff suppressed because it is too large Load Diff

View File

@ -206,7 +206,7 @@
},
"revision": 0,
"config": {},
"name": "Image to Video (Wan 2.2)",
"name": "local-Image to Video (Wan 2.2)",
"inputNode": {
"id": -10,
"bounding": [
@ -2027,8 +2027,7 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Video generation and editing/Image to video",
"description": "Image-to-video with Wan 2.2 using a start image plus text prompt to extend motion from the still frame."
"category": "Video generation and editing/Image to video"
}
]
},

File diff suppressed because it is too large Load Diff

View File

@ -134,7 +134,7 @@
},
"revision": 0,
"config": {},
"name": "Pose to Image (Z-Image-Turbo)",
"name": "local-Pose to Image (Z-Image-Turbo)",
"inputNode": {
"id": -10,
"bounding": [
@ -1298,8 +1298,7 @@
"VHS_MetadataImage": true,
"VHS_KeepIntermediate": true
},
"category": "Image generation and editing/Pose to image",
"description": "Generates an image from pose keypoints using Z-Image-Turbo with text conditioning."
"category": "Image generation and editing/Pose to image"
}
]
},
@ -1320,4 +1319,4 @@
}
},
"version": 0.4
}
}

File diff suppressed because it is too large Load Diff

View File

@ -270,10 +270,9 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Text generation/Prompt enhance",
"description": "Expands short text prompts into detailed descriptions using a text generation model for better generation quality."
"category": "Text generation/Prompt enhance"
}
]
},
"extra": {}
}
}

View File

@ -1,397 +0,0 @@
{
"revision": 0,
"last_node_id": 19,
"last_link_id": 0,
"nodes": [
{
"id": 19,
"type": "5b40ca21-ba1a-41d5-b403-4d2d7acdc195",
"pos": [
-6411.330578108367,
1940.2638932730042
],
"size": [
349.609375,
145.9375
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"localized_name": "image",
"name": "image",
"type": "IMAGE",
"link": null
},
{
"name": "bg_removal_name",
"type": "COMBO",
"widget": {
"name": "bg_removal_name"
},
"link": null
}
],
"outputs": [
{
"localized_name": "IMAGE",
"name": "IMAGE",
"type": "IMAGE",
"links": []
},
{
"name": "mask",
"type": "MASK",
"links": []
}
],
"properties": {
"proxyWidgets": [
[
"14",
"bg_removal_name"
]
]
},
"widgets_values": [],
"title": "Remove Background (BiRefNet)"
}
],
"links": [],
"version": 0.4,
"definitions": {
"subgraphs": [
{
"id": "5b40ca21-ba1a-41d5-b403-4d2d7acdc195",
"version": 1,
"state": {
"lastGroupId": 0,
"lastNodeId": 21,
"lastLinkId": 16,
"lastRerouteId": 0
},
"revision": 0,
"config": {},
"name": "Remove Background (BiRefNet)",
"description": "Removes or replaces image backgrounds using BiRefNet segmentation and alpha compositing.",
"inputNode": {
"id": -10,
"bounding": [
-6728.534070722246,
1475.2619799128663,
150.9140625,
88
]
},
"outputNode": {
"id": -20,
"bounding": [
-6169.049695722246,
1475.2619799128663,
128,
88
]
},
"inputs": [
{
"id": "7bc321cd-df31-4c39-aaf7-7f0d01326189",
"name": "image",
"type": "IMAGE",
"linkIds": [
5,
7
],
"localized_name": "image",
"pos": [
-6601.620008222246,
1499.2619799128663
]
},
{
"id": "e89d2cd8-daa3-4e29-8a69-851db85072cb",
"name": "bg_removal_name",
"type": "COMBO",
"linkIds": [
12
],
"pos": [
-6601.620008222246,
1519.2619799128663
]
}
],
"outputs": [
{
"id": "16e7863c-4c38-46c2-aa74-e82991fbfe8d",
"name": "IMAGE",
"type": "IMAGE",
"linkIds": [
8
],
"localized_name": "IMAGE",
"pos": [
-6145.049695722246,
1499.2619799128663
]
},
{
"id": "f7240c19-5b80-406e-a8e2-9b12440ee2d6",
"name": "mask",
"type": "MASK",
"linkIds": [
11
],
"pos": [
-6145.049695722246,
1519.2619799128663
]
}
],
"widgets": [],
"nodes": [
{
"id": 13,
"type": "RemoveBackground",
"pos": [
-6536.764823982709,
1444.9963409012412
],
"size": [
302.25,
72
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [
{
"localized_name": "image",
"name": "image",
"type": "IMAGE",
"link": 5
},
{
"localized_name": "bg_removal_model",
"name": "bg_removal_model",
"type": "BACKGROUND_REMOVAL",
"link": 3
}
],
"outputs": [
{
"localized_name": "mask",
"name": "mask",
"type": "MASK",
"links": [
4,
11
]
}
],
"properties": {
"Node name for S&R": "RemoveBackground"
}
},
{
"id": 14,
"type": "LoadBackgroundRemovalModel",
"pos": [
-6540.534070722246,
1302.223464635445
],
"size": [
311.484375,
85.515625
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [
{
"localized_name": "bg_removal_name",
"name": "bg_removal_name",
"type": "COMBO",
"widget": {
"name": "bg_removal_name"
},
"link": 12
}
],
"outputs": [
{
"localized_name": "bg_model",
"name": "bg_model",
"type": "BACKGROUND_REMOVAL",
"links": [
3
]
}
],
"properties": {
"Node name for S&R": "LoadBackgroundRemovalModel",
"models": [
{
"name": "birefnet.safetensors",
"url": "https://huggingface.co/Comfy-Org/BiRefNet/resolve/main/background_removal/birefnet.safetensors",
"directory": "background_removal"
}
]
},
"widgets_values": [
"birefnet.safetensors"
]
},
{
"id": 15,
"type": "InvertMask",
"pos": [
-6532.446160529669,
1571.1111286839914
],
"size": [
285.984375,
48
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"localized_name": "mask",
"name": "mask",
"type": "MASK",
"link": 4
}
],
"outputs": [
{
"localized_name": "MASK",
"name": "MASK",
"type": "MASK",
"links": [
6
]
}
],
"properties": {
"Node name for S&R": "InvertMask"
}
},
{
"id": 16,
"type": "JoinImageWithAlpha",
"pos": [
-6527.4370171636665,
1674.3004951902876
],
"size": [
284.96875,
72
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"localized_name": "image",
"name": "image",
"type": "IMAGE",
"link": 7
},
{
"localized_name": "alpha",
"name": "alpha",
"type": "MASK",
"link": 6
}
],
"outputs": [
{
"localized_name": "IMAGE",
"name": "IMAGE",
"type": "IMAGE",
"links": [
8
]
}
],
"properties": {
"Node name for S&R": "JoinImageWithAlpha"
}
}
],
"groups": [],
"links": [
{
"id": 3,
"origin_id": 14,
"origin_slot": 0,
"target_id": 13,
"target_slot": 1,
"type": "BACKGROUND_REMOVAL"
},
{
"id": 4,
"origin_id": 13,
"origin_slot": 0,
"target_id": 15,
"target_slot": 0,
"type": "MASK"
},
{
"id": 6,
"origin_id": 15,
"origin_slot": 0,
"target_id": 16,
"target_slot": 1,
"type": "MASK"
},
{
"id": 5,
"origin_id": -10,
"origin_slot": 0,
"target_id": 13,
"target_slot": 0,
"type": "IMAGE"
},
{
"id": 7,
"origin_id": -10,
"origin_slot": 0,
"target_id": 16,
"target_slot": 0,
"type": "IMAGE"
},
{
"id": 8,
"origin_id": 16,
"origin_slot": 0,
"target_id": -20,
"target_slot": 0,
"type": "IMAGE"
},
{
"id": 11,
"origin_id": 13,
"origin_slot": 0,
"target_id": -20,
"target_slot": 1,
"type": "MASK"
},
{
"id": 12,
"origin_id": -10,
"origin_slot": 1,
"target_id": 14,
"target_slot": 0,
"type": "COMBO"
}
],
"extra": {},
"category": "Image generation and editing/Background Removal"
}
]
},
"extra": {}
}

View File

@ -1,484 +0,0 @@
{
"revision": 0,
"last_node_id": 10,
"last_link_id": 0,
"nodes": [
{
"id": 10,
"type": "3fb7557a-470d-4983-9d8c-6d5caa9788f0",
"pos": [
-250,
8590
],
"size": [
280,
360
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [
{
"localized_name": "text_per_line",
"name": "text_per_line",
"type": "STRING",
"widget": {
"name": "text_per_line"
},
"link": null
},
{
"localized_name": "index",
"name": "index",
"type": "INT",
"widget": {
"name": "index"
},
"link": null
}
],
"outputs": [
{
"localized_name": "selected_line",
"name": "selected_line",
"type": "STRING",
"links": []
}
],
"properties": {
"proxyWidgets": [
[
"2",
"string"
],
[
"3",
"value"
]
],
"cnr_id": "comfy-core",
"ver": "0.19.0",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {}
}
},
"widgets_values": [],
"title": "Select Per-Line Text by Index"
}
],
"links": [],
"version": 0.4,
"definitions": {
"subgraphs": [
{
"id": "3fb7557a-470d-4983-9d8c-6d5caa9788f0",
"version": 1,
"state": {
"lastGroupId": 0,
"lastNodeId": 10,
"lastLinkId": 14,
"lastRerouteId": 0
},
"revision": 0,
"config": {},
"name": "Select Per-Line Text by Index",
"inputNode": {
"id": -10,
"bounding": [
-990,
8595,
128,
88
]
},
"outputNode": {
"id": -20,
"bounding": [
710,
8585,
128,
68
]
},
"inputs": [
{
"id": "75417d82-a934-4ac9-b667-d8dcd5a3bfb3",
"name": "text_per_line",
"type": "STRING",
"linkIds": [
13
],
"localized_name": "text_per_line",
"pos": [
-886,
8619
]
},
{
"id": "46e69a73-1804-4ca6-9175-31445bf0be96",
"name": "index",
"type": "INT",
"linkIds": [
14
],
"localized_name": "index",
"pos": [
-886,
8639
]
}
],
"outputs": [
{
"id": "e34e8ad1-84d2-4bd2-a460-eb7de6067c10",
"name": "selected_line",
"type": "STRING",
"linkIds": [
10
],
"localized_name": "selected_line",
"pos": [
734,
8609
]
}
],
"widgets": [],
"nodes": [
{
"id": 1,
"type": "PreviewAny",
"pos": [
-500,
8400
],
"size": [
230,
180
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [
{
"localized_name": "source",
"name": "source",
"type": "*",
"link": 1
}
],
"outputs": [
{
"localized_name": "STRING",
"name": "STRING",
"type": "STRING",
"links": [
6
]
}
],
"properties": {
"Node name for S&R": "PreviewAny",
"cnr_id": "comfy-core",
"ver": "0.19.0",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {}
}
},
"widgets_values": [
null,
null,
null
]
},
{
"id": 2,
"type": "RegexExtract",
"pos": [
-240,
8740
],
"size": [
470,
460
],
"flags": {},
"order": 1,
"mode": 0,
"showAdvanced": false,
"inputs": [
{
"localized_name": "string",
"name": "string",
"type": "STRING",
"widget": {
"name": "string"
},
"link": 13
},
{
"localized_name": "regex_pattern",
"name": "regex_pattern",
"type": "STRING",
"widget": {
"name": "regex_pattern"
},
"link": 9
},
{
"localized_name": "mode",
"name": "mode",
"type": "COMBO",
"widget": {
"name": "mode"
},
"link": null
},
{
"localized_name": "case_insensitive",
"name": "case_insensitive",
"type": "BOOLEAN",
"widget": {
"name": "case_insensitive"
},
"link": null
},
{
"localized_name": "multiline",
"name": "multiline",
"type": "BOOLEAN",
"widget": {
"name": "multiline"
},
"link": null
},
{
"localized_name": "dotall",
"name": "dotall",
"type": "BOOLEAN",
"widget": {
"name": "dotall"
},
"link": null
},
{
"localized_name": "group_index",
"name": "group_index",
"type": "INT",
"widget": {
"name": "group_index"
},
"link": null
}
],
"outputs": [
{
"localized_name": "STRING",
"name": "STRING",
"type": "STRING",
"links": [
10
]
}
],
"properties": {
"Node name for S&R": "RegexExtract",
"cnr_id": "comfy-core",
"ver": "0.19.0",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {}
}
},
"widgets_values": [
"",
"",
"First Group",
false,
false,
false,
1
]
},
{
"id": 3,
"type": "PrimitiveInt",
"pos": [
-810,
8400
],
"size": [
270,
110
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"localized_name": "value",
"name": "value",
"type": "INT",
"widget": {
"name": "value"
},
"link": 14
}
],
"outputs": [
{
"localized_name": "INT",
"name": "INT",
"type": "INT",
"links": [
1
]
}
],
"title": "Int (line index)",
"properties": {
"Node name for S&R": "Int (line index)",
"cnr_id": "comfy-core",
"ver": "0.19.0",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {}
}
},
"widgets_values": [
0,
"fixed"
]
},
{
"id": 8,
"type": "StringReplace",
"pos": [
-240,
8400
],
"size": [
400,
280
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"localized_name": "string",
"name": "string",
"type": "STRING",
"widget": {
"name": "string"
},
"link": null
},
{
"localized_name": "find",
"name": "find",
"type": "STRING",
"widget": {
"name": "find"
},
"link": null
},
{
"localized_name": "replace",
"name": "replace",
"type": "STRING",
"widget": {
"name": "replace"
},
"link": 6
}
],
"outputs": [
{
"localized_name": "STRING",
"name": "STRING",
"type": "STRING",
"links": [
9
]
}
],
"properties": {
"Node name for S&R": "StringReplace",
"cnr_id": "comfy-core",
"ver": "0.19.0",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {}
}
},
"widgets_values": [
"(?:[^\\n]*\\n){index}([^\\n]+)",
"index",
""
]
}
],
"groups": [],
"links": [
{
"id": 1,
"origin_id": 3,
"origin_slot": 0,
"target_id": 1,
"target_slot": 0,
"type": "INT"
},
{
"id": 9,
"origin_id": 8,
"origin_slot": 0,
"target_id": 2,
"target_slot": 1,
"type": "STRING"
},
{
"id": 6,
"origin_id": 1,
"origin_slot": 0,
"target_id": 8,
"target_slot": 2,
"type": "STRING"
},
{
"id": 10,
"origin_id": 2,
"origin_slot": 0,
"target_id": -20,
"target_slot": 0,
"type": "STRING"
},
{
"id": 13,
"origin_id": -10,
"origin_slot": 0,
"target_id": 2,
"target_slot": 0,
"type": "STRING"
},
{
"id": 14,
"origin_id": -10,
"origin_slot": 1,
"target_id": 3,
"target_slot": 0,
"type": "INT"
}
],
"extra": {},
"category": "Text Tools"
}
]
},
"extra": {
"ue_links": [],
"links_added_by_ue": []
}
}

View File

@ -267,7 +267,7 @@
"Node name for S&R": "GLSLShader"
},
"widgets_values": [
"#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform float u_float0; // strength [0.0 2.0] typical: 0.31.0\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\n\nvoid main() {\n vec2 texel = 1.0 / vec2(textureSize(u_image0, 0));\n \n // Sample center and neighbors\n vec4 center = texture(u_image0, v_texCoord);\n vec4 top = texture(u_image0, v_texCoord + vec2( 0.0, -texel.y));\n vec4 bottom = texture(u_image0, v_texCoord + vec2( 0.0, texel.y));\n vec4 left = texture(u_image0, v_texCoord + vec2(-texel.x, 0.0));\n vec4 right = texture(u_image0, v_texCoord + vec2( texel.x, 0.0));\n \n // Edge enhancement (Laplacian)\n vec4 edges = center * 4.0 - top - bottom - left - right;\n \n // Add edges back scaled by strength\n vec4 sharpened = center + edges * u_float0;\n \n fragColor0 = vec4(clamp(sharpened.rgb, 0.0, 1.0), center.a);\n}",
"#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform vec2 u_resolution;\nuniform float u_float0; // strength [0.0 2.0] typical: 0.31.0\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\n\nvoid main() {\n vec2 texel = 1.0 / u_resolution;\n \n // Sample center and neighbors\n vec4 center = texture(u_image0, v_texCoord);\n vec4 top = texture(u_image0, v_texCoord + vec2( 0.0, -texel.y));\n vec4 bottom = texture(u_image0, v_texCoord + vec2( 0.0, texel.y));\n vec4 left = texture(u_image0, v_texCoord + vec2(-texel.x, 0.0));\n vec4 right = texture(u_image0, v_texCoord + vec2( texel.x, 0.0));\n \n // Edge enhancement (Laplacian)\n vec4 edges = center * 4.0 - top - bottom - left - right;\n \n // Add edges back scaled by strength\n vec4 sharpened = center + edges * u_float0;\n \n fragColor0 = vec4(clamp(sharpened.rgb, 0.0, 1.0), center.a);\n}",
"from_input"
]
}
@ -302,9 +302,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Sharpen",
"description": "Sharpens image details using a GPU fragment shader for enhanced clarity."
"category": "Image Tools/Sharpen"
}
]
}
}
}

View File

@ -1,713 +0,0 @@
{
"revision": 0,
"last_node_id": 251,
"last_link_id": 0,
"nodes": [
{
"id": 251,
"type": "609e1fd1-b731-4b78-89ac-d19b1156b025",
"pos": [
-1490,
130
],
"size": [
230,
164
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [
{
"localized_name": "source_image",
"name": "source_image",
"type": "IMAGE",
"link": null
},
{
"localized_name": "columns",
"name": "columns",
"type": "INT",
"widget": {
"name": "columns"
},
"link": null
},
{
"localized_name": "rows",
"name": "rows",
"type": "INT",
"widget": {
"name": "rows"
},
"link": null
}
],
"outputs": [
{
"localized_name": "tiles",
"name": "tiles",
"type": "IMAGE",
"links": []
}
],
"properties": {
"proxyWidgets": [
[
"228",
"value"
],
[
"252",
"value"
]
],
"cnr_id": "comfy-core",
"ver": "0.20.1",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
},
"widgets_values": [],
"title": "Split Image Grid to Tiles"
}
],
"links": [],
"version": 0.4,
"definitions": {
"subgraphs": [
{
"id": "609e1fd1-b731-4b78-89ac-d19b1156b025",
"version": 1,
"state": {
"lastGroupId": 9,
"lastNodeId": 252,
"lastLinkId": 429,
"lastRerouteId": 0
},
"revision": 0,
"config": {},
"name": "Split Image Grid to Tiles",
"inputNode": {
"id": -10,
"bounding": [
-1690,
260,
128,
108
]
},
"outputNode": {
"id": -20,
"bounding": [
-510,
590,
128,
68
]
},
"inputs": [
{
"id": "866ac798-cfbc-450a-b755-e704f86404d9",
"name": "source_image",
"type": "IMAGE",
"linkIds": [
386,
389
],
"localized_name": "source_image",
"pos": [
-1586,
284
]
},
{
"id": "bc37b1f8-8ab2-4f19-bd00-75d4fbc4feb3",
"name": "columns",
"type": "INT",
"linkIds": [
427
],
"localized_name": "columns",
"pos": [
-1586,
304
]
},
{
"id": "d45915da-e848-43dd-9ccc-e3161e9c99d9",
"name": "rows",
"type": "INT",
"linkIds": [
428
],
"localized_name": "rows",
"pos": [
-1586,
324
]
}
],
"outputs": [
{
"id": "18bc780f-064b-4038-87c6-67dba71deb08",
"name": "tiles",
"type": "IMAGE",
"linkIds": [
394
],
"localized_name": "tiles",
"shape": 6,
"pos": [
-486,
614
]
}
],
"widgets": [],
"nodes": [
{
"id": 225,
"type": "SplitImageToTileList",
"pos": [
-1010,
620
],
"size": [
290,
170
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [
{
"localized_name": "image",
"name": "image",
"type": "IMAGE",
"link": 386
},
{
"localized_name": "tile_width",
"name": "tile_width",
"type": "INT",
"widget": {
"name": "tile_width"
},
"link": 403
},
{
"localized_name": "tile_height",
"name": "tile_height",
"type": "INT",
"widget": {
"name": "tile_height"
},
"link": 404
},
{
"localized_name": "overlap",
"name": "overlap",
"type": "INT",
"widget": {
"name": "overlap"
},
"link": null
}
],
"outputs": [
{
"localized_name": "IMAGE",
"name": "IMAGE",
"shape": 6,
"type": "IMAGE",
"links": [
394
]
}
],
"properties": {
"Node name for S&R": "SplitImageToTileList",
"cnr_id": "comfy-core",
"ver": "0.20.1",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
},
"widgets_values": [
1024,
1024,
0
]
},
{
"id": 231,
"type": "ComfyMathExpression",
"pos": [
-1080,
330
],
"size": [
370,
190
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"label": "a",
"localized_name": "values.a",
"name": "values.a",
"type": "FLOAT,INT,BOOLEAN",
"link": 390
},
{
"label": "b",
"localized_name": "values.b",
"name": "values.b",
"shape": 7,
"type": "FLOAT,INT,BOOLEAN",
"link": 429
},
{
"label": "c",
"localized_name": "values.c",
"name": "values.c",
"shape": 7,
"type": "FLOAT,INT,BOOLEAN",
"link": null
},
{
"localized_name": "expression",
"name": "expression",
"type": "STRING",
"widget": {
"name": "expression"
},
"link": null
}
],
"outputs": [
{
"localized_name": "FLOAT",
"name": "FLOAT",
"type": "FLOAT",
"links": null
},
{
"localized_name": "INT",
"name": "INT",
"type": "INT",
"links": [
404
]
},
{
"localized_name": "BOOL",
"name": "BOOL",
"type": "BOOLEAN",
"links": null
}
],
"title": "Math Expression Height",
"properties": {
"Node name for S&R": "ComfyMathExpression",
"cnr_id": "comfy-core",
"ver": "0.18.1",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65,
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.7",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
"max(1, (int(a) + int(b) - 1) // int(b))"
]
},
{
"id": 229,
"type": "ComfyMathExpression",
"pos": [
-1090,
-30
],
"size": [
370,
190
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"label": "a",
"localized_name": "values.a",
"name": "values.a",
"type": "FLOAT,INT,BOOLEAN",
"link": 387
},
{
"label": "b",
"localized_name": "values.b",
"name": "values.b",
"shape": 7,
"type": "FLOAT,INT,BOOLEAN",
"link": 388
},
{
"label": "c",
"localized_name": "values.c",
"name": "values.c",
"shape": 7,
"type": "FLOAT,INT,BOOLEAN",
"link": null
},
{
"localized_name": "expression",
"name": "expression",
"type": "STRING",
"widget": {
"name": "expression"
},
"link": null
}
],
"outputs": [
{
"localized_name": "FLOAT",
"name": "FLOAT",
"type": "FLOAT",
"links": null
},
{
"localized_name": "INT",
"name": "INT",
"type": "INT",
"links": [
403
]
},
{
"localized_name": "BOOL",
"name": "BOOL",
"type": "BOOLEAN",
"links": null
}
],
"title": "Math Expression Width",
"properties": {
"Node name for S&R": "ComfyMathExpression",
"cnr_id": "comfy-core",
"ver": "0.18.1",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65,
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.7",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
"max(1, (int(a) + int(b) - 1) // int(b))"
]
},
{
"id": 228,
"type": "PrimitiveInt",
"pos": [
-1380,
90
],
"size": [
230,
110
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [
{
"localized_name": "value",
"name": "value",
"type": "INT",
"widget": {
"name": "value"
},
"link": 427
}
],
"outputs": [
{
"localized_name": "INT",
"name": "INT",
"type": "INT",
"links": [
388
]
}
],
"title": "Int (grid columns)",
"properties": {
"Node name for S&R": "Int (grid columns)",
"cnr_id": "comfy-core",
"ver": "0.18.1",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65,
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.7",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
2,
"fixed"
]
},
{
"id": 230,
"type": "GetImageSize",
"pos": [
-1380,
290
],
"size": [
230,
100
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"localized_name": "image",
"name": "image",
"type": "IMAGE",
"link": 389
}
],
"outputs": [
{
"localized_name": "width",
"name": "width",
"type": "INT",
"links": [
387
]
},
{
"localized_name": "height",
"name": "height",
"type": "INT",
"links": [
390
]
},
{
"localized_name": "batch_size",
"name": "batch_size",
"type": "INT",
"links": null
}
],
"properties": {
"Node name for S&R": "GetImageSize",
"cnr_id": "comfy-core",
"ver": "0.18.1",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65,
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.7",
"input_ue_unconnectable": {}
}
}
},
{
"id": 252,
"type": "PrimitiveInt",
"pos": [
-1380,
470
],
"size": [
230,
110
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"localized_name": "value",
"name": "value",
"type": "INT",
"widget": {
"name": "value"
},
"link": 428
}
],
"outputs": [
{
"localized_name": "INT",
"name": "INT",
"type": "INT",
"links": [
429
]
}
],
"title": "Int (grid rows)",
"properties": {
"Node name for S&R": "Int (grid rows)",
"cnr_id": "comfy-core",
"ver": "0.18.1",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65,
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.7",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
3,
"fixed"
]
}
],
"groups": [],
"links": [
{
"id": 403,
"origin_id": 229,
"origin_slot": 1,
"target_id": 225,
"target_slot": 1,
"type": "INT"
},
{
"id": 404,
"origin_id": 231,
"origin_slot": 1,
"target_id": 225,
"target_slot": 2,
"type": "INT"
},
{
"id": 390,
"origin_id": 230,
"origin_slot": 1,
"target_id": 231,
"target_slot": 0,
"type": "INT"
},
{
"id": 387,
"origin_id": 230,
"origin_slot": 0,
"target_id": 229,
"target_slot": 0,
"type": "INT"
},
{
"id": 388,
"origin_id": 228,
"origin_slot": 0,
"target_id": 229,
"target_slot": 1,
"type": "INT"
},
{
"id": 386,
"origin_id": -10,
"origin_slot": 0,
"target_id": 225,
"target_slot": 0,
"type": "IMAGE"
},
{
"id": 389,
"origin_id": -10,
"origin_slot": 0,
"target_id": 230,
"target_slot": 0,
"type": "IMAGE"
},
{
"id": 394,
"origin_id": 225,
"origin_slot": 0,
"target_id": -20,
"target_slot": 0,
"type": "IMAGE"
},
{
"id": 427,
"origin_id": -10,
"origin_slot": 1,
"target_id": 228,
"target_slot": 0,
"type": "INT"
},
{
"id": 428,
"origin_id": -10,
"origin_slot": 2,
"target_id": 252,
"target_slot": 0,
"type": "INT"
},
{
"id": 429,
"origin_id": 252,
"origin_slot": 0,
"target_id": 231,
"target_slot": 1,
"type": "INT"
}
],
"extra": {},
"category": "Image Tools/Crop"
}
]
},
"extra": {}
}

View File

@ -222,7 +222,7 @@
},
"revision": 0,
"config": {},
"name": "Text to Audio (ACE-Step 1.5)",
"name": "local-Text to Audio (ACE-Step 1.5)",
"inputNode": {
"id": -10,
"bounding": [
@ -1502,8 +1502,7 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Audio/Music generation",
"description": "Generates audio/music from text prompts using ACE-Step 1.5, a diffusion-based audio generation model."
"category": "Audio/Music generation"
}
]
},
@ -1519,4 +1518,4 @@
}
},
"version": 0.4
}
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@ -1,21 +1,22 @@
{
"id": "1c3eaa76-5cfa-4dc7-8571-97a570324e01",
"revision": 0,
"last_node_id": 57,
"last_link_id": 0,
"last_node_id": 34,
"last_link_id": 40,
"nodes": [
{
"id": 57,
"type": "f2fdebf6-dfaf-43b6-9eb2-7f70613cfdc1",
"id": 5,
"type": "dfe9eb32-97c0-43a5-90d5-4fd37768d91b",
"pos": [
130,
200
-2.5766491043910378e-05,
1229.999928629805
],
"size": [
400,
470
],
"flags": {},
"order": 1,
"order": 0,
"mode": 0,
"inputs": [
{
@ -43,22 +44,6 @@
},
"link": null
},
{
"name": "seed",
"type": "INT",
"widget": {
"name": "seed"
},
"link": null
},
{
"name": "steps",
"type": "INT",
"widget": {
"name": "steps"
},
"link": null
},
{
"name": "unet_name",
"type": "COMBO",
@ -95,15 +80,15 @@
"properties": {
"proxyWidgets": [
[
"27",
"-1",
"text"
],
[
"13",
"-1",
"width"
],
[
"13",
"-1",
"height"
],
[
@ -112,23 +97,19 @@
],
[
"3",
"steps"
"control_after_generate"
],
[
"28",
"-1",
"unet_name"
],
[
"30",
"-1",
"clip_name"
],
[
"29",
"-1",
"vae_name"
],
[
"3",
"control_after_generate"
]
],
"cnr_id": "comfy-core",
@ -141,40 +122,48 @@
"secondTabOffset": 80,
"secondTabWidth": 65
},
"widgets_values": [],
"title": "Text to Image (Z-Image-Turbo)"
"widgets_values": [
"",
1024,
1024,
null,
null,
"z_image_turbo_bf16.safetensors",
"qwen_3_4b.safetensors",
"ae.safetensors"
]
}
],
"links": [],
"version": 0.4,
"groups": [],
"definitions": {
"subgraphs": [
{
"id": "f2fdebf6-dfaf-43b6-9eb2-7f70613cfdc1",
"id": "dfe9eb32-97c0-43a5-90d5-4fd37768d91b",
"version": 1,
"state": {
"lastGroupId": 4,
"lastNodeId": 61,
"lastLinkId": 75,
"lastNodeId": 34,
"lastLinkId": 40,
"lastRerouteId": 0
},
"revision": 0,
"config": {},
"name": "Text to Image (Z-Image-Turbo)",
"name": "local-Text to Image (Z-Image-Turbo)",
"inputNode": {
"id": -10,
"bounding": [
-560,
480,
-80,
425,
120,
200
160
]
},
"outputNode": {
"id": -20,
"bounding": [
1670,
320,
1490,
415,
120,
60
]
@ -189,8 +178,8 @@
],
"label": "prompt",
"pos": [
-460,
500
20,
445
]
},
{
@ -201,8 +190,8 @@
35
],
"pos": [
-460,
520
20,
465
]
},
{
@ -213,68 +202,44 @@
36
],
"pos": [
-460,
540
20,
485
]
},
{
"id": "f77677f7-6bf6-4c19-a71f-c4a553d5981e",
"name": "seed",
"type": "INT",
"linkIds": [
71
],
"pos": [
-460,
560
]
},
{
"id": "ef9a9fb1-5983-4bc9-a60b-cf5aec48bff1",
"name": "steps",
"type": "INT",
"linkIds": [
72
],
"pos": [
-460,
580
]
},
{
"id": "a20a1b30-785f-4a04-bb6d-3d61adab9764",
"id": "23087d15-8412-4fbd-b71e-9b6d7ef76de1",
"name": "unet_name",
"type": "COMBO",
"linkIds": [
73
38
],
"pos": [
-460,
600
20,
505
]
},
{
"id": "4af8fc2b-4655-4086-8240-45f8cb38c6f6",
"id": "0677f5c3-2a3f-43d4-98ac-a4c56d5efdc0",
"name": "clip_name",
"type": "COMBO",
"linkIds": [
74
39
],
"pos": [
-460,
620
20,
525
]
},
{
"id": "4d518693-2807-439c-9cb6-cffd23ccba2c",
"id": "c85c0445-2641-48b1-bbca-95057edf2fcf",
"name": "vae_name",
"type": "COMBO",
"linkIds": [
75
40
],
"pos": [
-460,
640
20,
545
]
}
],
@ -288,8 +253,8 @@
],
"localized_name": "IMAGE",
"pos": [
1690,
340
1510,
435
]
}
],
@ -299,15 +264,15 @@
"id": 30,
"type": "CLIPLoader",
"pos": [
30,
420
109.99997264844609,
329.99999029608756
],
"size": [
270,
150
269.9869791666667,
106
],
"flags": {},
"order": 7,
"order": 0,
"mode": 0,
"inputs": [
{
@ -317,7 +282,7 @@
"widget": {
"name": "clip_name"
},
"link": 74
"link": 39
},
{
"localized_name": "type",
@ -350,9 +315,9 @@
}
],
"properties": {
"Node name for S&R": "CLIPLoader",
"cnr_id": "comfy-core",
"ver": "0.3.73",
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "qwen_3_4b.safetensors",
@ -378,15 +343,15 @@
"id": 29,
"type": "VAELoader",
"pos": [
30,
650
109.99997264844609,
479.9999847172637
],
"size": [
270,
110
269.9869791666667,
58
],
"flags": {},
"order": 6,
"order": 1,
"mode": 0,
"inputs": [
{
@ -396,7 +361,7 @@
"widget": {
"name": "vae_name"
},
"link": 75
"link": 40
}
],
"outputs": [
@ -410,9 +375,9 @@
}
],
"properties": {
"Node name for S&R": "VAELoader",
"cnr_id": "comfy-core",
"ver": "0.3.73",
"Node name for S&R": "VAELoader",
"models": [
{
"name": "ae.safetensors",
@ -436,12 +401,12 @@
"id": 33,
"type": "ConditioningZeroOut",
"pos": [
630,
960
639.9999103333332,
620.0000271257795
],
"size": [
230,
80
204.134765625,
26
],
"flags": {},
"order": 8,
@ -465,9 +430,9 @@
}
],
"properties": {
"Node name for S&R": "ConditioningZeroOut",
"cnr_id": "comfy-core",
"ver": "0.3.73",
"Node name for S&R": "ConditioningZeroOut",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
@ -475,21 +440,22 @@
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
}
},
"widgets_values": []
},
{
"id": 8,
"type": "VAEDecode",
"pos": [
1320,
230
1219.9999088104782,
160.00009184959066
],
"size": [
230,
100
209.98697916666669,
46
],
"flags": {},
"order": 1,
"order": 5,
"mode": 0,
"inputs": [
{
@ -517,9 +483,9 @@
}
],
"properties": {
"Node name for S&R": "VAEDecode",
"cnr_id": "comfy-core",
"ver": "0.3.64",
"Node name for S&R": "VAEDecode",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
@ -527,21 +493,22 @@
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
}
},
"widgets_values": []
},
{
"id": 28,
"type": "UNETLoader",
"pos": [
30,
230
109.99997264844609,
200.0000502647102
],
"size": [
270,
110
269.9869791666667,
82
],
"flags": {},
"order": 5,
"order": 2,
"mode": 0,
"inputs": [
{
@ -551,7 +518,7 @@
"widget": {
"name": "unet_name"
},
"link": 73
"link": 38
},
{
"localized_name": "weight_dtype",
@ -574,9 +541,9 @@
}
],
"properties": {
"Node name for S&R": "UNETLoader",
"cnr_id": "comfy-core",
"ver": "0.3.73",
"Node name for S&R": "UNETLoader",
"models": [
{
"name": "z_image_turbo_bf16.safetensors",
@ -601,15 +568,15 @@
"id": 27,
"type": "CLIPTextEncode",
"pos": [
400,
230
429.99997828947767,
200.0000502647102
],
"size": [
450,
650
409.9869791666667,
319.9869791666667
],
"flags": {},
"order": 4,
"order": 7,
"mode": 0,
"inputs": [
{
@ -640,9 +607,9 @@
}
],
"properties": {
"Node name for S&R": "CLIPTextEncode",
"cnr_id": "comfy-core",
"ver": "0.3.73",
"Node name for S&R": "CLIPTextEncode",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
@ -659,15 +626,15 @@
"id": 13,
"type": "EmptySD3LatentImage",
"pos": [
40,
890
109.99997264844609,
629.9999791384399
],
"size": [
260,
170
259.9869791666667,
106
],
"flags": {},
"order": 3,
"order": 6,
"mode": 0,
"inputs": [
{
@ -710,9 +677,9 @@
}
],
"properties": {
"Node name for S&R": "EmptySD3LatentImage",
"cnr_id": "comfy-core",
"ver": "0.3.64",
"Node name for S&R": "EmptySD3LatentImage",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
@ -727,77 +694,19 @@
1
]
},
{
"id": 11,
"type": "ModelSamplingAuraFlow",
"pos": [
950,
230
],
"size": [
310,
110
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"localized_name": "model",
"name": "model",
"type": "MODEL",
"link": 26
},
{
"localized_name": "shift",
"name": "shift",
"type": "FLOAT",
"widget": {
"name": "shift"
},
"link": null
}
],
"outputs": [
{
"localized_name": "MODEL",
"name": "MODEL",
"type": "MODEL",
"slot_index": 0,
"links": [
13
]
}
],
"properties": {
"Node name for S&R": "ModelSamplingAuraFlow",
"cnr_id": "comfy-core",
"ver": "0.3.64",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
},
"widgets_values": [
3
]
},
{
"id": 3,
"type": "KSampler",
"pos": [
950,
400
879.9999615530063,
269.9999774911694
],
"size": [
320,
350
314.9869791666667,
262
],
"flags": {},
"order": 0,
"order": 4,
"mode": 0,
"inputs": [
{
@ -831,7 +740,7 @@
"widget": {
"name": "seed"
},
"link": 71
"link": null
},
{
"localized_name": "steps",
@ -840,7 +749,7 @@
"widget": {
"name": "steps"
},
"link": 72
"link": null
},
{
"localized_name": "cfg",
@ -891,9 +800,9 @@
}
],
"properties": {
"Node name for S&R": "KSampler",
"cnr_id": "comfy-core",
"ver": "0.3.64",
"Node name for S&R": "KSampler",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
@ -905,23 +814,81 @@
"widgets_values": [
0,
"randomize",
8,
4,
1,
"res_multistep",
"simple",
1
]
},
{
"id": 11,
"type": "ModelSamplingAuraFlow",
"pos": [
879.9999615530063,
160.00009184959066
],
"size": [
309.9869791666667,
58
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"localized_name": "model",
"name": "model",
"type": "MODEL",
"link": 26
},
{
"localized_name": "shift",
"name": "shift",
"type": "FLOAT",
"widget": {
"name": "shift"
},
"link": null
}
],
"outputs": [
{
"localized_name": "MODEL",
"name": "MODEL",
"type": "MODEL",
"slot_index": 0,
"links": [
13
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.64",
"Node name for S&R": "ModelSamplingAuraFlow",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
},
"widgets_values": [
3
]
}
],
"groups": [
{
"id": 2,
"title": "Step2 - Image size",
"title": "Image size",
"bounding": [
10,
820,
320,
280
100,
560,
290,
200
],
"color": "#3f789e",
"font_size": 24,
@ -929,12 +896,12 @@
},
{
"id": 3,
"title": "Step3 - Prompt",
"title": "Prompt",
"bounding": [
360,
410,
130,
530,
970
450,
540
],
"color": "#3f789e",
"font_size": 24,
@ -942,12 +909,12 @@
},
{
"id": 4,
"title": "Step1 - Load models",
"title": "Models",
"bounding": [
0,
100,
130,
330,
660
290,
413.6
],
"color": "#3f789e",
"font_size": 24,
@ -1060,41 +1027,25 @@
"type": "INT"
},
{
"id": 71,
"id": 38,
"origin_id": -10,
"origin_slot": 3,
"target_id": 3,
"target_slot": 4,
"type": "INT"
},
{
"id": 72,
"origin_id": -10,
"origin_slot": 4,
"target_id": 3,
"target_slot": 5,
"type": "INT"
},
{
"id": 73,
"origin_id": -10,
"origin_slot": 5,
"target_id": 28,
"target_slot": 0,
"type": "COMBO"
},
{
"id": 74,
"id": 39,
"origin_id": -10,
"origin_slot": 6,
"origin_slot": 4,
"target_id": 30,
"target_slot": 0,
"type": "COMBO"
},
{
"id": 75,
"id": 40,
"origin_id": -10,
"origin_slot": 7,
"origin_slot": 5,
"target_id": 29,
"target_slot": 0,
"type": "COMBO"
@ -1103,10 +1054,25 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image generation and editing/Text to image",
"description": "Generates images from text prompts using Z-Image-Turbo, Alibaba's distilled 6B DiT model."
"category": "Image generation and editing/Text to image"
}
]
},
"extra": {}
}
"config": {},
"extra": {
"frontendVersion": "1.37.10",
"workflowRendererVersion": "LG",
"VHS_latentpreview": false,
"VHS_latentpreviewrate": 0,
"VHS_MetadataImage": true,
"VHS_KeepIntermediate": true,
"ds": {
"scale": 0.8401370345180755,
"offset": [
940.0587067393087,
-830.7121087564725
]
}
},
"version": 0.4
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@ -1572,8 +1572,7 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Video generation and editing/Text to video",
"description": "Generates video from text prompts using Wan2.2, Alibaba's diffusion video model."
"category": "Video generation and editing/Text to video"
}
]
},
@ -1587,4 +1586,4 @@
"VHS_KeepIntermediate": true
},
"version": 0.4
}
}

View File

@ -383,7 +383,7 @@
"Node name for S&R": "GLSLShader"
},
"widgets_values": [
"#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform float u_float0; // amount [0.0 - 3.0] typical: 0.5-1.5\nuniform float u_float1; // radius [0.5 - 10.0] blur radius in pixels\nuniform float u_float2; // threshold [0.0 - 0.1] min difference to sharpen\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\n\nfloat gaussian(float x, float sigma) {\n return exp(-(x * x) / (2.0 * sigma * sigma));\n}\n\nfloat getLuminance(vec3 color) {\n return dot(color, vec3(0.2126, 0.7152, 0.0722));\n}\n\nvoid main() {\n vec2 texel = 1.0 / vec2(textureSize(u_image0, 0));\n float radius = max(u_float1, 0.5);\n float amount = u_float0;\n float threshold = u_float2;\n\n vec4 original = texture(u_image0, v_texCoord);\n\n // Gaussian blur for the \"unsharp\" mask\n int samples = int(ceil(radius));\n float sigma = radius / 2.0;\n\n vec4 blurred = vec4(0.0);\n float totalWeight = 0.0;\n\n for (int x = -samples; x <= samples; x++) {\n for (int y = -samples; y <= samples; y++) {\n vec2 offset = vec2(float(x), float(y)) * texel;\n vec4 sample_color = texture(u_image0, v_texCoord + offset);\n\n float dist = length(vec2(float(x), float(y)));\n float weight = gaussian(dist, sigma);\n blurred += sample_color * weight;\n totalWeight += weight;\n }\n }\n blurred /= totalWeight;\n\n // Unsharp mask = original - blurred\n vec3 mask = original.rgb - blurred.rgb;\n\n // Luminance-based threshold with smooth falloff\n float lumaDelta = abs(getLuminance(original.rgb) - getLuminance(blurred.rgb));\n float thresholdScale = smoothstep(0.0, threshold, lumaDelta);\n mask *= thresholdScale;\n\n // Sharpen: original + mask * amount\n vec3 sharpened = original.rgb + mask * amount;\n\n fragColor0 = vec4(clamp(sharpened, 0.0, 1.0), original.a);\n}\n",
"#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform vec2 u_resolution;\nuniform float u_float0; // amount [0.0 - 3.0] typical: 0.5-1.5\nuniform float u_float1; // radius [0.5 - 10.0] blur radius in pixels\nuniform float u_float2; // threshold [0.0 - 0.1] min difference to sharpen\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\n\nfloat gaussian(float x, float sigma) {\n return exp(-(x * x) / (2.0 * sigma * sigma));\n}\n\nfloat getLuminance(vec3 color) {\n return dot(color, vec3(0.2126, 0.7152, 0.0722));\n}\n\nvoid main() {\n vec2 texel = 1.0 / u_resolution;\n float radius = max(u_float1, 0.5);\n float amount = u_float0;\n float threshold = u_float2;\n\n vec4 original = texture(u_image0, v_texCoord);\n\n // Gaussian blur for the \"unsharp\" mask\n int samples = int(ceil(radius));\n float sigma = radius / 2.0;\n\n vec4 blurred = vec4(0.0);\n float totalWeight = 0.0;\n\n for (int x = -samples; x <= samples; x++) {\n for (int y = -samples; y <= samples; y++) {\n vec2 offset = vec2(float(x), float(y)) * texel;\n vec4 sample_color = texture(u_image0, v_texCoord + offset);\n\n float dist = length(vec2(float(x), float(y)));\n float weight = gaussian(dist, sigma);\n blurred += sample_color * weight;\n totalWeight += weight;\n }\n }\n blurred /= totalWeight;\n\n // Unsharp mask = original - blurred\n vec3 mask = original.rgb - blurred.rgb;\n\n // Luminance-based threshold with smooth falloff\n float lumaDelta = abs(getLuminance(original.rgb) - getLuminance(blurred.rgb));\n float thresholdScale = smoothstep(0.0, threshold, lumaDelta);\n mask *= thresholdScale;\n\n // Sharpen: original + mask * amount\n vec3 sharpened = original.rgb + mask * amount;\n\n fragColor0 = vec4(clamp(sharpened, 0.0, 1.0), original.a);\n}\n",
"from_input"
]
}
@ -434,9 +434,8 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Sharpen",
"description": "Enhances edge contrast via unsharp masking for a sharper image appearance."
"category": "Image Tools/Sharpen"
}
]
}
}
}

View File

@ -307,8 +307,7 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Text generation/Video Captioning",
"description": "Generates descriptive captions for video input using Google's Gemini multimodal LLM."
"category": "Text generation/Video Captioning"
}
]
}

File diff suppressed because it is too large Load Diff

View File

@ -165,7 +165,7 @@
},
"revision": 0,
"config": {},
"name": "Video Inpaint (Wan 2.1 VACE)",
"name": "local-Video Inpaint(Wan2.1 VACE)",
"inputNode": {
"id": -10,
"bounding": [
@ -2368,8 +2368,7 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Video generation and editing/Inpaint video",
"description": "Inpaints masked regions in video frames using Wan 2.1 VACE."
"category": "Video generation and editing/Inpaint video"
}
]
},

View File

@ -1,827 +0,0 @@
{
"revision": 0,
"last_node_id": 130,
"last_link_id": 0,
"nodes": [
{
"id": 130,
"type": "7937cf78-b52b-40a3-93b2-b4e2e5f98df1",
"pos": [
-1210,
-2780
],
"size": [
300,
370
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"name": "video",
"type": "VIDEO",
"link": null
},
{
"name": "text",
"type": "STRING",
"widget": {
"name": "text"
},
"link": null
},
{
"name": "bboxes",
"type": "BOUNDING_BOX",
"link": null
},
{
"name": "positive_coords",
"type": "STRING",
"link": null
},
{
"name": "negative_coords",
"type": "STRING",
"link": null
},
{
"name": "threshold",
"type": "FLOAT",
"widget": {
"name": "threshold"
},
"link": null
},
{
"name": "refine_iterations",
"type": "INT",
"widget": {
"name": "refine_iterations"
},
"link": null
},
{
"name": "individual_masks",
"type": "BOOLEAN",
"widget": {
"name": "individual_masks"
},
"link": null
},
{
"name": "ckpt_name",
"type": "COMBO",
"widget": {
"name": "ckpt_name"
},
"link": null
}
],
"outputs": [
{
"localized_name": "masks",
"name": "masks",
"type": "MASK",
"links": []
},
{
"localized_name": "bboxes",
"name": "bboxes",
"type": "BOUNDING_BOX",
"links": []
},
{
"name": "audio",
"type": "AUDIO",
"links": null
},
{
"name": "fps",
"type": "FLOAT",
"links": null
}
],
"properties": {
"proxyWidgets": [
[
"125",
"text"
],
[
"126",
"threshold"
],
[
"126",
"refine_iterations"
],
[
"126",
"individual_masks"
],
[
"127",
"ckpt_name"
]
],
"cnr_id": "comfy-core",
"ver": "0.19.3",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
},
"widgets_values": [],
"title": "Video Segmentation (SAM3)"
}
],
"links": [],
"version": 0.4,
"definitions": {
"subgraphs": [
{
"id": "7937cf78-b52b-40a3-93b2-b4e2e5f98df1",
"version": 1,
"state": {
"lastGroupId": 0,
"lastNodeId": 130,
"lastLinkId": 299,
"lastRerouteId": 0
},
"revision": 0,
"config": {},
"name": "Video Segmentation (SAM3)",
"inputNode": {
"id": -10,
"bounding": [
-2260,
-3450,
136.369140625,
220
]
},
"outputNode": {
"id": -20,
"bounding": [
-1050,
-3510,
120,
120
]
},
"inputs": [
{
"id": "680ffd88-32fe-48be-88d6-91ea44d5eaee",
"name": "video",
"type": "VIDEO",
"linkIds": [
252
],
"pos": [
-2143.630859375,
-3430
]
},
{
"id": "ceaf249c-32d7-4624-8bf6-e590e347ed90",
"name": "text",
"type": "STRING",
"linkIds": [
254
],
"pos": [
-2143.630859375,
-3410
]
},
{
"id": "1ffbff36-da0c-4854-8cb4-88ad31e64f99",
"name": "bboxes",
"type": "BOUNDING_BOX",
"linkIds": [
255
],
"pos": [
-2143.630859375,
-3390
]
},
{
"id": "67b7f4c7-cec0-4e00-b154-23cc1abf880e",
"name": "positive_coords",
"type": "STRING",
"linkIds": [
256
],
"pos": [
-2143.630859375,
-3370
]
},
{
"id": "b090a498-2bde-46b9-9554-18501401d687",
"name": "negative_coords",
"type": "STRING",
"linkIds": [
257
],
"pos": [
-2143.630859375,
-3350
]
},
{
"id": "1a76dfcf-ce95-46af-bba5-c42160c683dd",
"name": "threshold",
"type": "FLOAT",
"linkIds": [
261
],
"pos": [
-2143.630859375,
-3330
]
},
{
"id": "999523fa-c476-4c53-80c3-0a2f554d18ab",
"name": "refine_iterations",
"type": "INT",
"linkIds": [
262
],
"pos": [
-2143.630859375,
-3310
]
},
{
"id": "d2371011-7fe5-4a39-b0c1-df2e0bbd6ece",
"name": "individual_masks",
"type": "BOOLEAN",
"linkIds": [
263
],
"pos": [
-2143.630859375,
-3290
]
},
{
"id": "675a8b37-17db-48d1-853c-2fe5d6a74582",
"name": "ckpt_name",
"type": "COMBO",
"linkIds": [
273
],
"pos": [
-2143.630859375,
-3270
]
}
],
"outputs": [
{
"id": "ff50da09-1e59-4a58-9b7f-be1a00aa5913",
"name": "masks",
"type": "MASK",
"linkIds": [
231
],
"localized_name": "masks",
"pos": [
-1030,
-3490
]
},
{
"id": "8f622e40-8528-4078-b7d3-147e9f872194",
"name": "bboxes",
"type": "BOUNDING_BOX",
"linkIds": [
232
],
"localized_name": "bboxes",
"pos": [
-1030,
-3470
]
},
{
"id": "6c9924ec-f0fa-4509-83ea-8f97f5889bcc",
"name": "audio",
"type": "AUDIO",
"linkIds": [
259
],
"pos": [
-1030,
-3450
]
},
{
"id": "82c1cddc-ab11-44eb-9e2f-1a5c7ea5645b",
"name": "fps",
"type": "FLOAT",
"linkIds": [
260
],
"pos": [
-1030,
-3430
]
}
],
"widgets": [],
"nodes": [
{
"id": 125,
"type": "CLIPTextEncode",
"pos": [
-2010,
-3040
],
"size": [
400,
200
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [
{
"localized_name": "clip",
"name": "clip",
"type": "CLIP",
"link": 240
},
{
"localized_name": "text",
"name": "text",
"type": "STRING",
"widget": {
"name": "text"
},
"link": 254
}
],
"outputs": [
{
"localized_name": "CONDITIONING",
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
200
]
}
],
"properties": {
"Node name for S&R": "CLIPTextEncode",
"cnr_id": "comfy-core",
"ver": "0.19.3",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
},
"widgets_values": [
""
]
},
{
"id": 126,
"type": "SAM3_Detect",
"pos": [
-1520,
-3520
],
"size": [
270,
290
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"label": "model",
"localized_name": "model",
"name": "model",
"type": "MODEL",
"link": 237
},
{
"label": "image",
"localized_name": "image",
"name": "image",
"type": "IMAGE",
"link": 253
},
{
"label": "conditioning",
"localized_name": "conditioning",
"name": "conditioning",
"shape": 7,
"type": "CONDITIONING",
"link": 200
},
{
"label": "bboxes",
"localized_name": "bboxes",
"name": "bboxes",
"shape": 7,
"type": "BOUNDING_BOX",
"link": 255
},
{
"label": "positive_coords",
"localized_name": "positive_coords",
"name": "positive_coords",
"shape": 7,
"type": "STRING",
"link": 256
},
{
"label": "negative_coords",
"localized_name": "negative_coords",
"name": "negative_coords",
"shape": 7,
"type": "STRING",
"link": 257
},
{
"localized_name": "threshold",
"name": "threshold",
"type": "FLOAT",
"widget": {
"name": "threshold"
},
"link": 261
},
{
"localized_name": "refine_iterations",
"name": "refine_iterations",
"type": "INT",
"widget": {
"name": "refine_iterations"
},
"link": 262
},
{
"localized_name": "individual_masks",
"name": "individual_masks",
"type": "BOOLEAN",
"widget": {
"name": "individual_masks"
},
"link": 263
}
],
"outputs": [
{
"localized_name": "masks",
"name": "masks",
"type": "MASK",
"links": [
231
]
},
{
"localized_name": "bboxes",
"name": "bboxes",
"type": "BOUNDING_BOX",
"links": [
232
]
}
],
"properties": {
"Node name for S&R": "SAM3_Detect",
"cnr_id": "comfy-core",
"ver": "0.19.3",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
},
"widgets_values": [
0.5,
2,
false
]
},
{
"id": 127,
"type": "CheckpointLoaderSimple",
"pos": [
-1970,
-3310
],
"size": [
330,
160
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"localized_name": "ckpt_name",
"name": "ckpt_name",
"type": "COMBO",
"widget": {
"name": "ckpt_name"
},
"link": 273
}
],
"outputs": [
{
"localized_name": "MODEL",
"name": "MODEL",
"type": "MODEL",
"links": [
237
]
},
{
"localized_name": "CLIP",
"name": "CLIP",
"type": "CLIP",
"links": [
240
]
},
{
"localized_name": "VAE",
"name": "VAE",
"type": "VAE",
"links": null
}
],
"properties": {
"Node name for S&R": "CheckpointLoaderSimple",
"cnr_id": "comfy-core",
"ver": "0.19.3",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65,
"models": [
{
"name": "sam3.1_multiplex_fp16.safetensors",
"url": "https://huggingface.co/Comfy-Org/sam3.1/resolve/main/checkpoints/sam3.1_multiplex_fp16.safetensors",
"directory": "checkpoints"
}
]
},
"widgets_values": [
"sam3.1_multiplex_fp16.safetensors"
]
},
{
"id": 128,
"type": "GetVideoComponents",
"pos": [
-1910,
-3540
],
"size": [
230,
120
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"localized_name": "video",
"name": "video",
"type": "VIDEO",
"link": 252
}
],
"outputs": [
{
"localized_name": "images",
"name": "images",
"type": "IMAGE",
"links": [
253
]
},
{
"localized_name": "audio",
"name": "audio",
"type": "AUDIO",
"links": [
259
]
},
{
"localized_name": "fps",
"name": "fps",
"type": "FLOAT",
"links": [
260
]
}
],
"properties": {
"Node name for S&R": "GetVideoComponents",
"cnr_id": "comfy-core",
"ver": "0.19.3",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
}
},
{
"id": 129,
"type": "Note",
"pos": [
-1980,
-2790
],
"size": [
370,
250
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [],
"title": "Note: Prompt format",
"properties": {},
"widgets_values": [
"Max tokens for this model is only 32, to separately prompt multiple subjects you can separate prompts with comma, and set the max amount of objects detected for each prompt with :N\n\nFor example above test prompt finds 2 cakes, one apron, 4 window panels"
],
"color": "#432",
"bgcolor": "#653"
}
],
"groups": [],
"links": [
{
"id": 237,
"origin_id": 127,
"origin_slot": 0,
"target_id": 126,
"target_slot": 0,
"type": "MODEL"
},
{
"id": 200,
"origin_id": 125,
"origin_slot": 0,
"target_id": 126,
"target_slot": 2,
"type": "CONDITIONING"
},
{
"id": 240,
"origin_id": 127,
"origin_slot": 1,
"target_id": 125,
"target_slot": 0,
"type": "CLIP"
},
{
"id": 231,
"origin_id": 126,
"origin_slot": 0,
"target_id": -20,
"target_slot": 0,
"type": "MASK"
},
{
"id": 232,
"origin_id": 126,
"origin_slot": 1,
"target_id": -20,
"target_slot": 1,
"type": "BOUNDING_BOX"
},
{
"id": 252,
"origin_id": -10,
"origin_slot": 0,
"target_id": 128,
"target_slot": 0,
"type": "VIDEO"
},
{
"id": 253,
"origin_id": 128,
"origin_slot": 0,
"target_id": 126,
"target_slot": 1,
"type": "IMAGE"
},
{
"id": 254,
"origin_id": -10,
"origin_slot": 1,
"target_id": 125,
"target_slot": 1,
"type": "STRING"
},
{
"id": 255,
"origin_id": -10,
"origin_slot": 2,
"target_id": 126,
"target_slot": 3,
"type": "BOUNDING_BOX"
},
{
"id": 256,
"origin_id": -10,
"origin_slot": 3,
"target_id": 126,
"target_slot": 4,
"type": "STRING"
},
{
"id": 257,
"origin_id": -10,
"origin_slot": 4,
"target_id": 126,
"target_slot": 5,
"type": "STRING"
},
{
"id": 259,
"origin_id": 128,
"origin_slot": 1,
"target_id": -20,
"target_slot": 2,
"type": "AUDIO"
},
{
"id": 260,
"origin_id": 128,
"origin_slot": 2,
"target_id": -20,
"target_slot": 3,
"type": "FLOAT"
},
{
"id": 261,
"origin_id": -10,
"origin_slot": 5,
"target_id": 126,
"target_slot": 6,
"type": "FLOAT"
},
{
"id": 262,
"origin_id": -10,
"origin_slot": 6,
"target_id": 126,
"target_slot": 7,
"type": "INT"
},
{
"id": 263,
"origin_id": -10,
"origin_slot": 7,
"target_id": 126,
"target_slot": 8,
"type": "BOOLEAN"
},
{
"id": 273,
"origin_id": -10,
"origin_slot": 8,
"target_id": 127,
"target_slot": 0,
"type": "COMBO"
}
],
"extra": {},
"category": "Video Tools",
"description": "Segments video into temporally consistent masks using Meta SAM3 from text or interactive prompts."
}
]
},
"extra": {}
}

View File

@ -1,21 +1,21 @@
{
"revision": 0,
"last_node_id": 85,
"last_node_id": 84,
"last_link_id": 0,
"nodes": [
{
"id": 85,
"type": "637913e7-0206-46ba-8ded-70ae3a7c2e19",
"id": 84,
"type": "8e8aa94a-647e-436d-8440-8ee4691864de",
"pos": [
-880,
-2260
-6100,
2620
],
"size": [
290,
160
],
"flags": {},
"order": 2,
"order": 0,
"mode": 0,
"inputs": [
{
@ -76,26 +76,31 @@
"properties": {
"proxyWidgets": [
[
"79",
"-1",
"direction"
],
[
"79",
"-1",
"match_image_size"
],
[
"79",
"-1",
"spacing_width"
],
[
"79",
"-1",
"spacing_color"
]
],
"cnr_id": "comfy-core",
"ver": "0.13.0"
},
"widgets_values": [],
"widgets_values": [
"right",
true,
0,
"white"
],
"title": "Video Stitch"
}
],
@ -104,12 +109,12 @@
"definitions": {
"subgraphs": [
{
"id": "637913e7-0206-46ba-8ded-70ae3a7c2e19",
"id": "8e8aa94a-647e-436d-8440-8ee4691864de",
"version": 1,
"state": {
"lastGroupId": 1,
"lastNodeId": 97,
"lastLinkId": 282,
"lastNodeId": 84,
"lastLinkId": 262,
"lastRerouteId": 0
},
"revision": 0,
@ -118,8 +123,8 @@
"inputNode": {
"id": -10,
"bounding": [
-6810,
2580,
-6580,
2649,
143.55859375,
160
]
@ -127,8 +132,8 @@
"outputNode": {
"id": -20,
"bounding": [
-4770,
2600,
-5720,
2659,
120,
60
]
@ -144,8 +149,8 @@
"localized_name": "video",
"label": "Before Video",
"pos": [
-6686.44140625,
2600
-6456.44140625,
2669
]
},
{
@ -158,8 +163,8 @@
"localized_name": "video_1",
"label": "After Video",
"pos": [
-6686.44140625,
2620
-6456.44140625,
2689
]
},
{
@ -170,8 +175,8 @@
259
],
"pos": [
-6686.44140625,
2640
-6456.44140625,
2709
]
},
{
@ -182,8 +187,8 @@
260
],
"pos": [
-6686.44140625,
2660
-6456.44140625,
2729
]
},
{
@ -194,8 +199,8 @@
261
],
"pos": [
-6686.44140625,
2680
-6456.44140625,
2749
]
},
{
@ -206,8 +211,8 @@
262
],
"pos": [
-6686.44140625,
2700
-6456.44140625,
2769
]
}
],
@ -221,8 +226,8 @@
],
"localized_name": "VIDEO",
"pos": [
-4750,
2620
-5700,
2679
]
}
],
@ -233,11 +238,11 @@
"type": "GetVideoComponents",
"pos": [
-6390,
2600
2560
],
"size": [
230,
120
193.530859375,
66
],
"flags": {},
"order": 1,
@ -273,9 +278,9 @@
}
],
"properties": {
"Node name for S&R": "GetVideoComponents",
"cnr_id": "comfy-core",
"ver": "0.13.0"
"ver": "0.13.0",
"Node name for S&R": "GetVideoComponents"
}
},
{
@ -286,8 +291,8 @@
2420
],
"size": [
230,
120
193.530859375,
66
],
"flags": {},
"order": 0,
@ -327,254 +332,21 @@
}
],
"properties": {
"Node name for S&R": "GetVideoComponents",
"cnr_id": "comfy-core",
"ver": "0.13.0"
"ver": "0.13.0",
"Node name for S&R": "GetVideoComponents"
}
},
{
"id": 90,
"type": "GetImageSize",
"pos": [
-6390,
3030
],
"size": [
230,
120
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"localized_name": "image",
"name": "image",
"type": "IMAGE",
"link": 266
}
],
"outputs": [
{
"localized_name": "width",
"name": "width",
"type": "INT",
"links": [
274
]
},
{
"localized_name": "height",
"name": "height",
"type": "INT",
"links": [
276
]
},
{
"localized_name": "batch_size",
"name": "batch_size",
"type": "INT",
"links": null
}
],
"properties": {
"Node name for S&R": "GetImageSize"
}
},
{
"id": 80,
"type": "CreateVideo",
"pos": [
-5190,
2420
],
"size": [
270,
130
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"localized_name": "images",
"name": "images",
"type": "IMAGE",
"link": 282
},
{
"localized_name": "audio",
"name": "audio",
"shape": 7,
"type": "AUDIO",
"link": 251
},
{
"localized_name": "fps",
"name": "fps",
"type": "FLOAT",
"widget": {
"name": "fps"
},
"link": 252
}
],
"outputs": [
{
"localized_name": "VIDEO",
"name": "VIDEO",
"type": "VIDEO",
"links": [
255
]
}
],
"properties": {
"Node name for S&R": "CreateVideo",
"cnr_id": "comfy-core",
"ver": "0.13.0"
},
"widgets_values": [
30
]
},
{
"id": 95,
"type": "ComfyMathExpression",
"pos": [
-6040,
3020
],
"size": [
400,
200
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"label": "a",
"localized_name": "values.a",
"name": "values.a",
"type": "FLOAT,INT",
"link": 274
},
{
"label": "b",
"localized_name": "values.b",
"name": "values.b",
"shape": 7,
"type": "FLOAT,INT",
"link": null
},
{
"localized_name": "expression",
"name": "expression",
"type": "STRING",
"widget": {
"name": "expression"
},
"link": null
}
],
"outputs": [
{
"localized_name": "FLOAT",
"name": "FLOAT",
"type": "FLOAT",
"links": null
},
{
"localized_name": "INT",
"name": "INT",
"type": "INT",
"links": [
279
]
}
],
"properties": {
"Node name for S&R": "ComfyMathExpression"
},
"widgets_values": [
"a & ~1"
]
},
{
"id": 96,
"type": "ComfyMathExpression",
"pos": [
-6040,
3290
],
"size": [
400,
200
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"label": "a",
"localized_name": "values.a",
"name": "values.a",
"type": "FLOAT,INT",
"link": 276
},
{
"label": "b",
"localized_name": "values.b",
"name": "values.b",
"shape": 7,
"type": "FLOAT,INT",
"link": null
},
{
"localized_name": "expression",
"name": "expression",
"type": "STRING",
"widget": {
"name": "expression"
},
"link": null
}
],
"outputs": [
{
"localized_name": "FLOAT",
"name": "FLOAT",
"type": "FLOAT",
"links": null
},
{
"localized_name": "INT",
"name": "INT",
"type": "INT",
"links": [
280
]
}
],
"properties": {
"Node name for S&R": "ComfyMathExpression"
},
"widgets_values": [
"a & ~1"
]
},
{
"id": 79,
"type": "ImageStitch",
"pos": [
-6390,
2780
2700
],
"size": [
270,
160
150
],
"flags": {},
"order": 2,
@ -636,15 +408,14 @@
"name": "IMAGE",
"type": "IMAGE",
"links": [
266,
281
250
]
}
],
"properties": {
"Node name for S&R": "ImageStitch",
"cnr_id": "comfy-core",
"ver": "0.13.0"
"ver": "0.13.0",
"Node name for S&R": "ImageStitch"
},
"widgets_values": [
"right",
@ -654,91 +425,60 @@
]
},
{
"id": 97,
"type": "ResizeImageMaskNode",
"id": 80,
"type": "CreateVideo",
"pos": [
-5560,
2790
-6040,
2610
],
"size": [
270,
160
78
],
"flags": {},
"order": 7,
"order": 3,
"mode": 0,
"inputs": [
{
"localized_name": "input",
"name": "input",
"type": "IMAGE,MASK",
"link": 281
"localized_name": "images",
"name": "images",
"type": "IMAGE",
"link": 250
},
{
"localized_name": "resize_type",
"name": "resize_type",
"type": "COMFY_DYNAMICCOMBO_V3",
"widget": {
"name": "resize_type"
},
"link": null
"localized_name": "audio",
"name": "audio",
"shape": 7,
"type": "AUDIO",
"link": 251
},
{
"localized_name": "width",
"name": "resize_type.width",
"type": "INT",
"localized_name": "fps",
"name": "fps",
"type": "FLOAT",
"widget": {
"name": "resize_type.width"
"name": "fps"
},
"link": 279
},
{
"localized_name": "height",
"name": "resize_type.height",
"type": "INT",
"widget": {
"name": "resize_type.height"
},
"link": 280
},
{
"localized_name": "crop",
"name": "resize_type.crop",
"type": "COMBO",
"widget": {
"name": "resize_type.crop"
},
"link": null
},
{
"localized_name": "scale_method",
"name": "scale_method",
"type": "COMBO",
"widget": {
"name": "scale_method"
},
"link": null
"link": 252
}
],
"outputs": [
{
"localized_name": "resized",
"name": "resized",
"type": "*",
"localized_name": "VIDEO",
"name": "VIDEO",
"type": "VIDEO",
"links": [
282
255
]
}
],
"properties": {
"Node name for S&R": "ResizeImageMaskNode"
"cnr_id": "comfy-core",
"ver": "0.13.0",
"Node name for S&R": "CreateVideo"
},
"widgets_values": [
"scale dimensions",
512,
512,
"center",
"area"
30
]
}
],
@ -760,6 +500,14 @@
"target_slot": 1,
"type": "IMAGE"
},
{
"id": 250,
"origin_id": 79,
"origin_slot": 0,
"target_id": 80,
"target_slot": 0,
"type": "IMAGE"
},
{
"id": 251,
"origin_id": 77,
@ -831,71 +579,13 @@
"target_id": 79,
"target_slot": 5,
"type": "COMBO"
},
{
"id": 266,
"origin_id": 79,
"origin_slot": 0,
"target_id": 90,
"target_slot": 0,
"type": "IMAGE"
},
{
"id": 274,
"origin_id": 90,
"origin_slot": 0,
"target_id": 95,
"target_slot": 0,
"type": "INT"
},
{
"id": 276,
"origin_id": 90,
"origin_slot": 1,
"target_id": 96,
"target_slot": 0,
"type": "INT"
},
{
"id": 279,
"origin_id": 95,
"origin_slot": 1,
"target_id": 97,
"target_slot": 2,
"type": "INT"
},
{
"id": 280,
"origin_id": 96,
"origin_slot": 1,
"target_id": 97,
"target_slot": 3,
"type": "INT"
},
{
"id": 281,
"origin_id": 79,
"origin_slot": 0,
"target_id": 97,
"target_slot": 0,
"type": "IMAGE"
},
{
"id": 282,
"origin_id": 97,
"origin_slot": 0,
"target_id": 80,
"target_slot": 0,
"type": "IMAGE"
}
],
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Video Tools/Stitch videos",
"description": "Stitches multiple video clips into a single sequential video file."
"category": "Video Tools/Stitch videos"
}
]
},
"extra": {}
}
}
}

View File

@ -412,10 +412,9 @@
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Video generation and editing/Enhance video",
"description": "Upscales video to 4× resolution using a GAN-based upscaling model."
"category": "Video generation and editing/Enhance video"
}
]
},
"extra": {}
}
}

File diff suppressed because it is too large Load Diff

View File

@ -1,7 +0,0 @@
{
"model_type": "birefnet",
"image_std": [1.0, 1.0, 1.0],
"image_mean": [0.0, 0.0, 0.0],
"image_size": 1024,
"resize_to_original": true
}

View File

@ -1,689 +0,0 @@
import torch
import comfy.ops
import numpy as np
import torch.nn as nn
from functools import partial
import torch.nn.functional as F
from torchvision.ops import deform_conv2d
from comfy.ldm.modules.attention import optimized_attention_for_device
CXT = [3072, 1536, 768, 384][1:][::-1][-3:]
class Attention(nn.Module):
def __init__(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, device=None, dtype=None, operations=None):
super().__init__()
self.dim = dim
self.num_heads = num_heads
head_dim = dim // num_heads
self.scale = qk_scale or head_dim ** -0.5
self.q = operations.Linear(dim, dim, bias=qkv_bias, device=device, dtype=dtype)
self.kv = operations.Linear(dim, dim * 2, bias=qkv_bias, device=device, dtype=dtype)
self.proj = operations.Linear(dim, dim, device=device, dtype=dtype)
def forward(self, x):
B, N, C = x.shape
optimized_attention = optimized_attention_for_device(x.device, mask=False, small_input=True)
q = self.q(x).reshape(B, N, self.num_heads, C // self.num_heads).permute(0, 2, 1, 3)
kv = self.kv(x).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
k, v = kv[0], kv[1]
x = optimized_attention(
q, k, v, heads=self.num_heads, skip_output_reshape=True, skip_reshape=True
).transpose(1, 2).reshape(B, N, C)
x = self.proj(x)
return x
class Mlp(nn.Module):
def __init__(self, in_features, hidden_features=None, out_features=None, device=None, dtype=None, operations=None):
super().__init__()
out_features = out_features or in_features
hidden_features = hidden_features or in_features
self.fc1 = operations.Linear(in_features, hidden_features, device=device, dtype=dtype)
self.act = nn.GELU()
self.fc2 = operations.Linear(hidden_features, out_features, device=device, dtype=dtype)
def forward(self, x):
x = self.fc1(x)
x = self.act(x)
x = self.fc2(x)
return x
def window_partition(x, window_size):
B, H, W, C = x.shape
x = x.view(B, H // window_size, window_size, W // window_size, window_size, C)
windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C)
return windows
def window_reverse(windows, window_size, H, W):
B = int(windows.shape[0] / (H * W / window_size / window_size))
x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1)
x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1)
return x
class WindowAttention(nn.Module):
def __init__(self, dim, window_size, num_heads, qkv_bias=True, qk_scale=None, device=None, dtype=None, operations=None):
super().__init__()
self.dim = dim
self.window_size = window_size # Wh, Ww
self.num_heads = num_heads
head_dim = dim // num_heads
self.scale = qk_scale or head_dim ** -0.5
self.relative_position_bias_table = nn.Parameter(
torch.zeros((2 * window_size[0] - 1) * (2 * window_size[1] - 1), num_heads, device=device, dtype=dtype))
coords_h = torch.arange(self.window_size[0])
coords_w = torch.arange(self.window_size[1])
coords = torch.stack(torch.meshgrid([coords_h, coords_w], indexing='ij')) # 2, Wh, Ww
coords_flatten = torch.flatten(coords, 1) # 2, Wh*Ww
relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :] # 2, Wh*Ww, Wh*Ww
relative_coords = relative_coords.permute(1, 2, 0).contiguous() # Wh*Ww, Wh*Ww, 2
relative_coords[:, :, 0] += self.window_size[0] - 1
relative_coords[:, :, 1] += self.window_size[1] - 1
relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1
relative_position_index = relative_coords.sum(-1) # Wh*Ww, Wh*Ww
self.register_buffer("relative_position_index", relative_position_index)
self.qkv = operations.Linear(dim, dim * 3, bias=qkv_bias, device=device, dtype=dtype)
self.proj = operations.Linear(dim, dim, device=device, dtype=dtype)
self.softmax = nn.Softmax(dim=-1)
def forward(self, x, mask=None):
B_, N, C = x.shape
qkv = self.qkv(x).reshape(B_, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
q, k, v = qkv[0], qkv[1], qkv[2]
q = q * self.scale
attn = (q @ k.transpose(-2, -1))
relative_position_bias = self.relative_position_bias_table[self.relative_position_index.long().view(-1)].view(
self.window_size[0] * self.window_size[1], self.window_size[0] * self.window_size[1], -1) # Wh*Ww,Wh*Ww,nH
relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous() # nH, Wh*Ww, Wh*Ww
attn = attn + relative_position_bias.unsqueeze(0)
if mask is not None:
nW = mask.shape[0]
attn = attn.view(B_ // nW, nW, self.num_heads, N, N) + mask.unsqueeze(1).unsqueeze(0)
attn = attn.view(-1, self.num_heads, N, N)
attn = self.softmax(attn)
else:
attn = self.softmax(attn)
x = (attn @ v).transpose(1, 2).reshape(B_, N, C)
x = self.proj(x)
return x
class SwinTransformerBlock(nn.Module):
def __init__(self, dim, num_heads, window_size=7, shift_size=0,
mlp_ratio=4., qkv_bias=True, qk_scale=None,
norm_layer=nn.LayerNorm, device=None, dtype=None, operations=None):
super().__init__()
self.dim = dim
self.num_heads = num_heads
self.window_size = window_size
self.shift_size = shift_size
self.mlp_ratio = mlp_ratio
self.norm1 = norm_layer(dim, device=device, dtype=dtype)
self.attn = WindowAttention(
dim, window_size=(self.window_size, self.window_size), num_heads=num_heads,
qkv_bias=qkv_bias, qk_scale=qk_scale, device=device, dtype=dtype, operations=operations)
self.norm2 = norm_layer(dim, device=device, dtype=dtype)
mlp_hidden_dim = int(dim * mlp_ratio)
self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, device=device, dtype=dtype, operations=operations)
self.H = None
self.W = None
def forward(self, x, mask_matrix):
B, L, C = x.shape
H, W = self.H, self.W
shortcut = x
x = self.norm1(x)
x = x.view(B, H, W, C)
pad_l = pad_t = 0
pad_r = (self.window_size - W % self.window_size) % self.window_size
pad_b = (self.window_size - H % self.window_size) % self.window_size
x = F.pad(x, (0, 0, pad_l, pad_r, pad_t, pad_b))
_, Hp, Wp, _ = x.shape
if self.shift_size > 0:
shifted_x = torch.roll(x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2))
attn_mask = mask_matrix
else:
shifted_x = x
attn_mask = None
x_windows = window_partition(shifted_x, self.window_size)
x_windows = x_windows.view(-1, self.window_size * self.window_size, C)
attn_windows = self.attn(x_windows, mask=attn_mask)
attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C)
shifted_x = window_reverse(attn_windows, self.window_size, Hp, Wp) # B H' W' C
if self.shift_size > 0:
x = torch.roll(shifted_x, shifts=(self.shift_size, self.shift_size), dims=(1, 2))
else:
x = shifted_x
if pad_r > 0 or pad_b > 0:
x = x[:, :H, :W, :].contiguous()
x = x.view(B, H * W, C)
x = shortcut + x
x = x + self.mlp(self.norm2(x))
return x
class PatchMerging(nn.Module):
def __init__(self, dim, device=None, dtype=None, operations=None):
super().__init__()
self.dim = dim
self.reduction = operations.Linear(4 * dim, 2 * dim, bias=False, device=device, dtype=dtype)
self.norm = operations.LayerNorm(4 * dim, device=device, dtype=dtype)
def forward(self, x, H, W):
B, L, C = x.shape
x = x.view(B, H, W, C)
# padding
pad_input = (H % 2 == 1) or (W % 2 == 1)
if pad_input:
x = F.pad(x, (0, 0, 0, W % 2, 0, H % 2))
x0 = x[:, 0::2, 0::2, :] # B H/2 W/2 C
x1 = x[:, 1::2, 0::2, :] # B H/2 W/2 C
x2 = x[:, 0::2, 1::2, :] # B H/2 W/2 C
x3 = x[:, 1::2, 1::2, :] # B H/2 W/2 C
x = torch.cat([x0, x1, x2, x3], -1) # B H/2 W/2 4*C
x = x.view(B, -1, 4 * C) # B H/2*W/2 4*C
x = self.norm(x)
x = self.reduction(x)
return x
class BasicLayer(nn.Module):
def __init__(self,
dim,
depth,
num_heads,
window_size=7,
mlp_ratio=4.,
qkv_bias=True,
qk_scale=None,
norm_layer=nn.LayerNorm,
downsample=None,
device=None, dtype=None, operations=None):
super().__init__()
self.window_size = window_size
self.shift_size = window_size // 2
self.depth = depth
# build blocks
self.blocks = nn.ModuleList([
SwinTransformerBlock(
dim=dim,
num_heads=num_heads,
window_size=window_size,
shift_size=0 if (i % 2 == 0) else window_size // 2,
mlp_ratio=mlp_ratio,
qkv_bias=qkv_bias,
qk_scale=qk_scale,
norm_layer=norm_layer,
device=device, dtype=dtype, operations=operations)
for i in range(depth)])
# patch merging layer
if downsample is not None:
self.downsample = downsample(dim=dim, device=device, dtype=dtype, operations=operations)
else:
self.downsample = None
def forward(self, x, H, W):
Hp = int(np.ceil(H / self.window_size)) * self.window_size
Wp = int(np.ceil(W / self.window_size)) * self.window_size
img_mask = torch.zeros((1, Hp, Wp, 1), device=x.device) # 1 Hp Wp 1
h_slices = (slice(0, -self.window_size),
slice(-self.window_size, -self.shift_size),
slice(-self.shift_size, None))
w_slices = (slice(0, -self.window_size),
slice(-self.window_size, -self.shift_size),
slice(-self.shift_size, None))
cnt = 0
for h in h_slices:
for w in w_slices:
img_mask[:, h, w, :] = cnt
cnt += 1
mask_windows = window_partition(img_mask, self.window_size)
mask_windows = mask_windows.view(-1, self.window_size * self.window_size)
attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)
attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0))
for blk in self.blocks:
blk.H, blk.W = H, W
x = blk(x, attn_mask)
if self.downsample is not None:
x_down = self.downsample(x, H, W)
Wh, Ww = (H + 1) // 2, (W + 1) // 2
return x, H, W, x_down, Wh, Ww
else:
return x, H, W, x, H, W
class PatchEmbed(nn.Module):
def __init__(self, patch_size=4, in_channels=3, embed_dim=96, norm_layer=None, device=None, dtype=None, operations=None):
super().__init__()
patch_size = (patch_size, patch_size)
self.patch_size = patch_size
self.in_channels = in_channels
self.embed_dim = embed_dim
self.proj = operations.Conv2d(in_channels, embed_dim, kernel_size=patch_size, stride=patch_size, device=device, dtype=dtype)
if norm_layer is not None:
self.norm = norm_layer(embed_dim, device=device, dtype=dtype)
else:
self.norm = None
def forward(self, x):
_, _, H, W = x.size()
if W % self.patch_size[1] != 0:
x = F.pad(x, (0, self.patch_size[1] - W % self.patch_size[1]))
if H % self.patch_size[0] != 0:
x = F.pad(x, (0, 0, 0, self.patch_size[0] - H % self.patch_size[0]))
x = self.proj(x) # B C Wh Ww
if self.norm is not None:
Wh, Ww = x.size(2), x.size(3)
x = x.flatten(2).transpose(1, 2)
x = self.norm(x)
x = x.transpose(1, 2).view(-1, self.embed_dim, Wh, Ww)
return x
class SwinTransformer(nn.Module):
def __init__(self,
pretrain_img_size=224,
patch_size=4,
in_channels=3,
embed_dim=96,
depths=[2, 2, 6, 2],
num_heads=[3, 6, 12, 24],
window_size=7,
mlp_ratio=4.,
qkv_bias=True,
qk_scale=None,
patch_norm=True,
out_indices=(0, 1, 2, 3),
frozen_stages=-1,
device=None, dtype=None, operations=None):
super().__init__()
norm_layer = partial(operations.LayerNorm, device=device, dtype=dtype)
self.pretrain_img_size = pretrain_img_size
self.num_layers = len(depths)
self.embed_dim = embed_dim
self.patch_norm = patch_norm
self.out_indices = out_indices
self.frozen_stages = frozen_stages
self.patch_embed = PatchEmbed(
patch_size=patch_size, in_channels=in_channels, embed_dim=embed_dim,
device=device, dtype=dtype, operations=operations,
norm_layer=norm_layer if self.patch_norm else None)
self.layers = nn.ModuleList()
for i_layer in range(self.num_layers):
layer = BasicLayer(
dim=int(embed_dim * 2 ** i_layer),
depth=depths[i_layer],
num_heads=num_heads[i_layer],
window_size=window_size,
mlp_ratio=mlp_ratio,
qkv_bias=qkv_bias,
qk_scale=qk_scale,
norm_layer=norm_layer,
downsample=PatchMerging if (i_layer < self.num_layers - 1) else None,
device=device, dtype=dtype, operations=operations)
self.layers.append(layer)
num_features = [int(embed_dim * 2 ** i) for i in range(self.num_layers)]
self.num_features = num_features
for i_layer in out_indices:
layer = norm_layer(num_features[i_layer])
layer_name = f'norm{i_layer}'
self.add_module(layer_name, layer)
def forward(self, x):
x = self.patch_embed(x)
Wh, Ww = x.size(2), x.size(3)
outs = []
x = x.flatten(2).transpose(1, 2)
for i in range(self.num_layers):
layer = self.layers[i]
x_out, H, W, x, Wh, Ww = layer(x, Wh, Ww)
if i in self.out_indices:
norm_layer = getattr(self, f'norm{i}')
x_out = norm_layer(x_out)
out = x_out.view(-1, H, W, self.num_features[i]).permute(0, 3, 1, 2).contiguous()
outs.append(out)
return tuple(outs)
class DeformableConv2d(nn.Module):
def __init__(self,
in_channels,
out_channels,
kernel_size=3,
stride=1,
padding=1,
bias=False, device=None, dtype=None, operations=None):
super(DeformableConv2d, self).__init__()
kernel_size = kernel_size if type(kernel_size) is tuple else (kernel_size, kernel_size)
self.stride = stride if type(stride) is tuple else (stride, stride)
self.padding = padding
self.offset_conv = operations.Conv2d(in_channels,
2 * kernel_size[0] * kernel_size[1],
kernel_size=kernel_size,
stride=stride,
padding=self.padding,
bias=True, device=device, dtype=dtype)
self.modulator_conv = operations.Conv2d(in_channels,
1 * kernel_size[0] * kernel_size[1],
kernel_size=kernel_size,
stride=stride,
padding=self.padding,
bias=True, device=device, dtype=dtype)
self.regular_conv = operations.Conv2d(in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
stride=stride,
padding=self.padding,
bias=bias, device=device, dtype=dtype)
def forward(self, x):
offset = self.offset_conv(x)
modulator = 2. * torch.sigmoid(self.modulator_conv(x))
weight, bias, offload_info = comfy.ops.cast_bias_weight(self.regular_conv, x, offloadable=True)
x = deform_conv2d(
input=x,
offset=offset,
weight=weight,
bias=None,
padding=self.padding,
mask=modulator,
stride=self.stride,
)
comfy.ops.uncast_bias_weight(self.regular_conv, weight, bias, offload_info)
return x
class BasicDecBlk(nn.Module):
def __init__(self, in_channels=64, out_channels=64, inter_channels=64, device=None, dtype=None, operations=None):
super(BasicDecBlk, self).__init__()
inter_channels = 64
self.conv_in = operations.Conv2d(in_channels, inter_channels, 3, 1, padding=1, device=device, dtype=dtype)
self.relu_in = nn.ReLU(inplace=True)
self.dec_att = ASPPDeformable(in_channels=inter_channels, device=device, dtype=dtype, operations=operations)
self.conv_out = operations.Conv2d(inter_channels, out_channels, 3, 1, padding=1, device=device, dtype=dtype)
self.bn_in = operations.BatchNorm2d(inter_channels, device=device, dtype=dtype)
self.bn_out = operations.BatchNorm2d(out_channels, device=device, dtype=dtype)
def forward(self, x):
x = self.conv_in(x)
x = self.bn_in(x)
x = self.relu_in(x)
x = self.dec_att(x)
x = self.conv_out(x)
x = self.bn_out(x)
return x
class BasicLatBlk(nn.Module):
def __init__(self, in_channels=64, out_channels=64, device=None, dtype=None, operations=None):
super(BasicLatBlk, self).__init__()
self.conv = operations.Conv2d(in_channels, out_channels, 1, 1, 0, device=device, dtype=dtype)
def forward(self, x):
x = self.conv(x)
return x
class _ASPPModuleDeformable(nn.Module):
def __init__(self, in_channels, planes, kernel_size, padding, device, dtype, operations):
super(_ASPPModuleDeformable, self).__init__()
self.atrous_conv = DeformableConv2d(in_channels, planes, kernel_size=kernel_size,
stride=1, padding=padding, bias=False, device=device, dtype=dtype, operations=operations)
self.bn = operations.BatchNorm2d(planes, device=device, dtype=dtype)
self.relu = nn.ReLU(inplace=True)
def forward(self, x):
x = self.atrous_conv(x)
x = self.bn(x)
return self.relu(x)
class ASPPDeformable(nn.Module):
def __init__(self, in_channels, out_channels=None, parallel_block_sizes=[1, 3, 7], device=None, dtype=None, operations=None):
super(ASPPDeformable, self).__init__()
self.down_scale = 1
if out_channels is None:
out_channels = in_channels
self.in_channelster = 256 // self.down_scale
self.aspp1 = _ASPPModuleDeformable(in_channels, self.in_channelster, 1, padding=0, device=device, dtype=dtype, operations=operations)
self.aspp_deforms = nn.ModuleList([
_ASPPModuleDeformable(in_channels, self.in_channelster, conv_size, padding=int(conv_size//2), device=device, dtype=dtype, operations=operations)
for conv_size in parallel_block_sizes
])
self.global_avg_pool = nn.Sequential(nn.AdaptiveAvgPool2d((1, 1)),
operations.Conv2d(in_channels, self.in_channelster, 1, stride=1, bias=False, device=device, dtype=dtype),
operations.BatchNorm2d(self.in_channelster, device=device, dtype=dtype),
nn.ReLU(inplace=True))
self.conv1 = operations.Conv2d(self.in_channelster * (2 + len(self.aspp_deforms)), out_channels, 1, bias=False, device=device, dtype=dtype)
self.bn1 = operations.BatchNorm2d(out_channels, device=device, dtype=dtype)
self.relu = nn.ReLU(inplace=True)
def forward(self, x):
x1 = self.aspp1(x)
x_aspp_deforms = [aspp_deform(x) for aspp_deform in self.aspp_deforms]
x5 = self.global_avg_pool(x)
x5 = F.interpolate(x5, size=x1.size()[2:], mode='bilinear', align_corners=True)
x = torch.cat((x1, *x_aspp_deforms, x5), dim=1)
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
return x
class BiRefNet(nn.Module):
def __init__(self, config=None, dtype=None, device=None, operations=None):
super(BiRefNet, self).__init__()
self.bb = SwinTransformer(embed_dim=192, depths=[2, 2, 18, 2], num_heads=[6, 12, 24, 48], window_size=12, device=device, dtype=dtype, operations=operations)
channels = [1536, 768, 384, 192]
channels = [c * 2 for c in channels]
self.cxt = channels[1:][::-1][-3:]
self.squeeze_module = nn.Sequential(*[
BasicDecBlk(channels[0]+sum(self.cxt), channels[0], device=device, dtype=dtype, operations=operations)
for _ in range(1)
])
self.decoder = Decoder(channels, device=device, dtype=dtype, operations=operations)
def forward_enc(self, x):
x1, x2, x3, x4 = self.bb(x)
B, C, H, W = x.shape
x1_, x2_, x3_, x4_ = self.bb(F.interpolate(x, size=(H//2, W//2), mode='bilinear', align_corners=True))
x1 = torch.cat([x1, F.interpolate(x1_, size=x1.shape[2:], mode='bilinear', align_corners=True)], dim=1)
x2 = torch.cat([x2, F.interpolate(x2_, size=x2.shape[2:], mode='bilinear', align_corners=True)], dim=1)
x3 = torch.cat([x3, F.interpolate(x3_, size=x3.shape[2:], mode='bilinear', align_corners=True)], dim=1)
x4 = torch.cat([x4, F.interpolate(x4_, size=x4.shape[2:], mode='bilinear', align_corners=True)], dim=1)
x4 = torch.cat(
(
*[
F.interpolate(x1, size=x4.shape[2:], mode='bilinear', align_corners=True),
F.interpolate(x2, size=x4.shape[2:], mode='bilinear', align_corners=True),
F.interpolate(x3, size=x4.shape[2:], mode='bilinear', align_corners=True),
][-len(CXT):],
x4
),
dim=1
)
return (x1, x2, x3, x4)
def forward_ori(self, x):
(x1, x2, x3, x4) = self.forward_enc(x)
x4 = self.squeeze_module(x4)
features = [x, x1, x2, x3, x4]
scaled_preds = self.decoder(features)
return scaled_preds
def forward(self, pixel_values, intermediate_output=None):
scaled_preds = self.forward_ori(pixel_values)
return scaled_preds
class Decoder(nn.Module):
def __init__(self, channels, device, dtype, operations):
super(Decoder, self).__init__()
# factory kwargs
fk = {"device":device, "dtype":dtype, "operations":operations}
DecoderBlock = partial(BasicDecBlk, **fk)
LateralBlock = partial(BasicLatBlk, **fk)
DBlock = partial(SimpleConvs, **fk)
self.split = True
N_dec_ipt = 64
ic = 64
ipt_cha_opt = 1
self.ipt_blk5 = DBlock(2**10*3 if self.split else 3, [N_dec_ipt, channels[0]//8][ipt_cha_opt], inter_channels=ic)
self.ipt_blk4 = DBlock(2**8*3 if self.split else 3, [N_dec_ipt, channels[0]//8][ipt_cha_opt], inter_channels=ic)
self.ipt_blk3 = DBlock(2**6*3 if self.split else 3, [N_dec_ipt, channels[1]//8][ipt_cha_opt], inter_channels=ic)
self.ipt_blk2 = DBlock(2**4*3 if self.split else 3, [N_dec_ipt, channels[2]//8][ipt_cha_opt], inter_channels=ic)
self.ipt_blk1 = DBlock(2**0*3 if self.split else 3, [N_dec_ipt, channels[3]//8][ipt_cha_opt], inter_channels=ic)
self.decoder_block4 = DecoderBlock(channels[0]+([N_dec_ipt, channels[0]//8][ipt_cha_opt]), channels[1])
self.decoder_block3 = DecoderBlock(channels[1]+([N_dec_ipt, channels[0]//8][ipt_cha_opt]), channels[2])
self.decoder_block2 = DecoderBlock(channels[2]+([N_dec_ipt, channels[1]//8][ipt_cha_opt]), channels[3])
self.decoder_block1 = DecoderBlock(channels[3]+([N_dec_ipt, channels[2]//8][ipt_cha_opt]), channels[3]//2)
fk = {"device":device, "dtype":dtype}
self.conv_out1 = nn.Sequential(operations.Conv2d(channels[3]//2+([N_dec_ipt, channels[3]//8][ipt_cha_opt]), 1, 1, 1, 0, **fk))
self.lateral_block4 = LateralBlock(channels[1], channels[1])
self.lateral_block3 = LateralBlock(channels[2], channels[2])
self.lateral_block2 = LateralBlock(channels[3], channels[3])
self.conv_ms_spvn_4 = operations.Conv2d(channels[1], 1, 1, 1, 0, **fk)
self.conv_ms_spvn_3 = operations.Conv2d(channels[2], 1, 1, 1, 0, **fk)
self.conv_ms_spvn_2 = operations.Conv2d(channels[3], 1, 1, 1, 0, **fk)
_N = 16
self.gdt_convs_4 = nn.Sequential(operations.Conv2d(channels[0] // 2, _N, 3, 1, 1, **fk), operations.BatchNorm2d(_N, **fk), nn.ReLU(inplace=True))
self.gdt_convs_3 = nn.Sequential(operations.Conv2d(channels[1] // 2, _N, 3, 1, 1, **fk), operations.BatchNorm2d(_N, **fk), nn.ReLU(inplace=True))
self.gdt_convs_2 = nn.Sequential(operations.Conv2d(channels[2] // 2, _N, 3, 1, 1, **fk), operations.BatchNorm2d(_N, **fk), nn.ReLU(inplace=True))
[setattr(self, f"gdt_convs_pred_{i}", nn.Sequential(operations.Conv2d(_N, 1, 1, 1, 0, **fk))) for i in range(2, 5)]
[setattr(self, f"gdt_convs_attn_{i}", nn.Sequential(operations.Conv2d(_N, 1, 1, 1, 0, **fk))) for i in range(2, 5)]
def get_patches_batch(self, x, p):
_size_h, _size_w = p.shape[2:]
patches_batch = []
for idx in range(x.shape[0]):
columns_x = torch.split(x[idx], split_size_or_sections=_size_w, dim=-1)
patches_x = []
for column_x in columns_x:
patches_x += [p.unsqueeze(0) for p in torch.split(column_x, split_size_or_sections=_size_h, dim=-2)]
patch_sample = torch.cat(patches_x, dim=1)
patches_batch.append(patch_sample)
return torch.cat(patches_batch, dim=0)
def forward(self, features):
x, x1, x2, x3, x4 = features
patches_batch = self.get_patches_batch(x, x4) if self.split else x
x4 = torch.cat((x4, self.ipt_blk5(F.interpolate(patches_batch, size=x4.shape[2:], mode='bilinear', align_corners=True))), 1)
p4 = self.decoder_block4(x4)
p4_gdt = self.gdt_convs_4(p4)
gdt_attn_4 = self.gdt_convs_attn_4(p4_gdt).sigmoid()
p4 = p4 * gdt_attn_4
_p4 = F.interpolate(p4, size=x3.shape[2:], mode='bilinear', align_corners=True)
_p3 = _p4 + self.lateral_block4(x3)
patches_batch = self.get_patches_batch(x, _p3) if self.split else x
_p3 = torch.cat((_p3, self.ipt_blk4(F.interpolate(patches_batch, size=x3.shape[2:], mode='bilinear', align_corners=True))), 1)
p3 = self.decoder_block3(_p3)
p3_gdt = self.gdt_convs_3(p3)
gdt_attn_3 = self.gdt_convs_attn_3(p3_gdt).sigmoid()
p3 = p3 * gdt_attn_3
_p3 = F.interpolate(p3, size=x2.shape[2:], mode='bilinear', align_corners=True)
_p2 = _p3 + self.lateral_block3(x2)
patches_batch = self.get_patches_batch(x, _p2) if self.split else x
_p2 = torch.cat((_p2, self.ipt_blk3(F.interpolate(patches_batch, size=x2.shape[2:], mode='bilinear', align_corners=True))), 1)
p2 = self.decoder_block2(_p2)
p2_gdt = self.gdt_convs_2(p2)
gdt_attn_2 = self.gdt_convs_attn_2(p2_gdt).sigmoid()
p2 = p2 * gdt_attn_2
_p2 = F.interpolate(p2, size=x1.shape[2:], mode='bilinear', align_corners=True)
_p1 = _p2 + self.lateral_block2(x1)
patches_batch = self.get_patches_batch(x, _p1) if self.split else x
_p1 = torch.cat((_p1, self.ipt_blk2(F.interpolate(patches_batch, size=x1.shape[2:], mode='bilinear', align_corners=True))), 1)
_p1 = self.decoder_block1(_p1)
_p1 = F.interpolate(_p1, size=x.shape[2:], mode='bilinear', align_corners=True)
patches_batch = self.get_patches_batch(x, _p1) if self.split else x
_p1 = torch.cat((_p1, self.ipt_blk1(F.interpolate(patches_batch, size=x.shape[2:], mode='bilinear', align_corners=True))), 1)
p1_out = self.conv_out1(_p1)
return p1_out
class SimpleConvs(nn.Module):
def __init__(
self, in_channels: int, out_channels: int, inter_channels=64, device=None, dtype=None, operations=None
) -> None:
super().__init__()
self.conv1 = operations.Conv2d(in_channels, inter_channels, 3, 1, 1, device=device, dtype=dtype)
self.conv_out = operations.Conv2d(inter_channels, out_channels, 3, 1, 1, device=device, dtype=dtype)
def forward(self, x):
return self.conv_out(self.conv1(x))

View File

@ -1,85 +0,0 @@
from .utils import load_torch_file
import os
import json
import torch
import logging
import comfy.ops
import comfy.model_patcher
import comfy.model_management
import comfy.clip_model
import comfy.background_removal.birefnet
BG_REMOVAL_MODELS = {
"birefnet": comfy.background_removal.birefnet.BiRefNet
}
class BackgroundRemovalModel():
def __init__(self, json_config):
with open(json_config) as f:
config = json.load(f)
self.image_size = config.get("image_size", 1024)
self.image_mean = config.get("image_mean", [0.0, 0.0, 0.0])
self.image_std = config.get("image_std", [1.0, 1.0, 1.0])
self.model_type = config.get("model_type", "birefnet")
self.config = config.copy()
model_class = BG_REMOVAL_MODELS.get(self.model_type)
self.load_device = comfy.model_management.text_encoder_device()
offload_device = comfy.model_management.text_encoder_offload_device()
self.dtype = comfy.model_management.text_encoder_dtype(self.load_device)
self.model = model_class(config, self.dtype, offload_device, comfy.ops.manual_cast)
self.model.eval()
self.patcher = comfy.model_patcher.CoreModelPatcher(self.model, load_device=self.load_device, offload_device=offload_device)
def load_sd(self, sd):
return self.model.load_state_dict(sd, strict=False, assign=self.patcher.is_dynamic())
def get_sd(self):
return self.model.state_dict()
def encode_image(self, image):
comfy.model_management.load_model_gpu(self.patcher)
H, W = image.shape[1], image.shape[2]
pixel_values = comfy.clip_model.clip_preprocess(image.to(self.load_device), size=self.image_size, mean=self.image_mean, std=self.image_std, crop=False)
if pixel_values.shape[0] > 1:
out = torch.cat([
self.model(pixel_values=pixel_values[i:i+1])
for i in range(pixel_values.shape[0])
], dim=0)
else:
out = self.model(pixel_values=pixel_values)
out = torch.nn.functional.interpolate(out, size=(H, W), mode="bicubic", antialias=False)
mask = out.sigmoid().to(device=comfy.model_management.intermediate_device(), dtype=comfy.model_management.intermediate_dtype())
if mask.ndim == 3:
mask = mask.unsqueeze(0)
if mask.shape[1] != 1:
mask = mask.movedim(-1, 1)
return mask
def load_background_removal_model(sd):
if "bb.layers.1.blocks.0.attn.relative_position_index" in sd:
json_config = os.path.join(os.path.join(os.path.dirname(os.path.realpath(__file__)), "background_removal"), "birefnet.json")
else:
return None
bg_model = BackgroundRemovalModel(json_config)
m, u = bg_model.load_sd(sd)
if len(m) > 0:
logging.warning("missing background removal: {}".format(m))
u = set(u)
keys = list(sd.keys())
for k in keys:
if k not in u:
sd.pop(k)
return bg_model
def load(ckpt_path):
sd = load_torch_file(ckpt_path)
return load_background_removal_model(sd)

View File

@ -90,8 +90,8 @@ parser.add_argument("--force-channels-last", action="store_true", help="Force ch
parser.add_argument("--directml", type=int, nargs="?", metavar="DIRECTML_DEVICE", const=-1, help="Use torch-directml.")
parser.add_argument("--oneapi-device-selector", type=str, default=None, metavar="SELECTOR_STRING", help="Sets the oneAPI device(s) this instance will use.")
parser.add_argument("--disable-ipex-optimize", action="store_true", help="Disables ipex.optimize default when loading models with Intel's Extension for Pytorch.")
parser.add_argument("--supports-fp8-compute", action="store_true", help="ComfyUI will act like if the device supports fp8 compute.")
parser.add_argument("--enable-triton-backend", action="store_true", help="ComfyUI will enable the use of Triton backend in comfy-kitchen. Is disabled at launch by default.")
class LatentPreviewMethod(enum.Enum):
NoPreviews = "none"
@ -141,7 +141,8 @@ manager_group.add_argument("--enable-manager-legacy-ui", action="store_true", he
vram_group = parser.add_mutually_exclusive_group()
vram_group.add_argument("--gpu-only", action="store_true", help="Store and run everything (text encoders/CLIP models, etc... on the GPU).")
vram_group.add_argument("--highvram", action="store_true", help="By default models will be unloaded to CPU memory after being used. This option keeps them in GPU memory.")
vram_group.add_argument("--lowvram", action="store_true", help="Doesn't do anything if dynamic vram is enabled. If dynamic vram isn't being used this option makes the text encoders run on the CPU.")
vram_group.add_argument("--normalvram", action="store_true", help="Used to force normal vram use if lowvram gets automatically enabled.")
vram_group.add_argument("--lowvram", action="store_true", help="Split the unet in parts to use less vram.")
vram_group.add_argument("--novram", action="store_true", help="When lowvram isn't enough.")
vram_group.add_argument("--cpu", action="store_true", help="To use the CPU for everything (slow).")
@ -237,8 +238,6 @@ database_default_path = os.path.abspath(
)
parser.add_argument("--database-url", type=str, default=f"sqlite:///{database_default_path}", help="Specify the database URL, e.g. for an in-memory database you can use 'sqlite:///:memory:'.")
parser.add_argument("--enable-assets", action="store_true", help="Enable the assets system (API routes, database synchronization, and background scanning).")
parser.add_argument("--feature-flag", type=str, action='append', default=[], metavar="KEY[=VALUE]", help="Set a server feature flag. Use KEY=VALUE to set an explicit value, or bare KEY to set it to true. Can be specified multiple times. Boolean values (true/false) and numbers are auto-converted. Examples: --feature-flag show_signin_button=true or --feature-flag show_signin_button")
parser.add_argument("--list-feature-flags", action="store_true", help="Print the registry of known CLI-settable feature flags as JSON and exit.")
if comfy.options.args_parsing:
args = parser.parse_args()

View File

@ -63,11 +63,7 @@ class IndexListContextWindow(ContextWindowABC):
dim = self.dim
if dim == 0 and full.shape[dim] == 1:
return full
indices = self.index_list
anchor_idx = getattr(self, 'causal_anchor_index', None)
if anchor_idx is not None and anchor_idx >= 0:
indices = [anchor_idx] + list(indices)
idx = tuple([slice(None)] * dim + [indices])
idx = tuple([slice(None)] * dim + [self.index_list])
window = full[idx]
if retain_index_list:
idx = tuple([slice(None)] * dim + [retain_index_list])
@ -117,14 +113,7 @@ def slice_cond(cond_value, window: IndexListContextWindow, x_in: torch.Tensor, d
# skip leading latent positions that have no corresponding conditioning (e.g. reference frames)
if temporal_offset > 0:
anchor_idx = getattr(window, 'causal_anchor_index', None)
if anchor_idx is not None and anchor_idx >= 0:
# anchor occupies one of the no-cond positions, so skip one fewer from window.index_list
skip_count = temporal_offset - 1
else:
skip_count = temporal_offset
indices = [i - temporal_offset for i in window.index_list[skip_count:]]
indices = [i - temporal_offset for i in window.index_list[temporal_offset:]]
indices = [i for i in indices if 0 <= i]
else:
indices = list(window.index_list)
@ -161,8 +150,7 @@ class ContextFuseMethod:
ContextResults = collections.namedtuple("ContextResults", ['window_idx', 'sub_conds_out', 'sub_conds', 'window'])
class IndexListContextHandler(ContextHandlerABC):
def __init__(self, context_schedule: ContextSchedule, fuse_method: ContextFuseMethod, context_length: int=1, context_overlap: int=0, context_stride: int=1,
closed_loop: bool=False, dim:int=0, freenoise: bool=False, cond_retain_index_list: list[int]=[], split_conds_to_windows: bool=False,
causal_window_fix: bool=True):
closed_loop: bool=False, dim:int=0, freenoise: bool=False, cond_retain_index_list: list[int]=[], split_conds_to_windows: bool=False):
self.context_schedule = context_schedule
self.fuse_method = fuse_method
self.context_length = context_length
@ -174,7 +162,6 @@ class IndexListContextHandler(ContextHandlerABC):
self.freenoise = freenoise
self.cond_retain_index_list = [int(x.strip()) for x in cond_retain_index_list.split(",")] if cond_retain_index_list else []
self.split_conds_to_windows = split_conds_to_windows
self.causal_window_fix = causal_window_fix
self.callbacks = {}
@ -331,14 +318,6 @@ class IndexListContextHandler(ContextHandlerABC):
# allow processing to end between context window executions for faster Cancel
comfy.model_management.throw_exception_if_processing_interrupted()
# causal_window_fix: prepend a pre-window frame that will be stripped post-forward
anchor_applied = False
if self.causal_window_fix:
anchor_idx = window.index_list[0] - 1
if 0 <= anchor_idx < x_in.size(self.dim):
window.causal_anchor_index = anchor_idx
anchor_applied = True
for callback in comfy.patcher_extension.get_all_callbacks(IndexListCallbacks.EVALUATE_CONTEXT_WINDOWS, self.callbacks):
callback(self, model, x_in, conds, timestep, model_options, window_idx, window, model_options, device, first_device)
@ -353,12 +332,6 @@ class IndexListContextHandler(ContextHandlerABC):
if device is not None:
for i in range(len(sub_conds_out)):
sub_conds_out[i] = sub_conds_out[i].to(x_in.device)
# strip causal_window_fix anchor if applied
if anchor_applied:
for i in range(len(sub_conds_out)):
sub_conds_out[i] = sub_conds_out[i].narrow(self.dim, 1, sub_conds_out[i].shape[self.dim] - 1)
results.append(ContextResults(window_idx, sub_conds_out, sub_conds, window))
return results

View File

@ -1,34 +0,0 @@
import functools
import logging
import os
logger = logging.getLogger(__name__)
_DEFAULT_DEPLOY_ENV = "local-git"
_ENV_FILENAME = ".comfy_environment"
# Resolve the ComfyUI install directory (the parent of this `comfy/` package).
# We deliberately avoid `folder_paths.base_path` here because that is overridden
# by the `--base-directory` CLI arg to a user-supplied path, whereas the
# `.comfy_environment` marker is written by launchers/installers next to the
# ComfyUI install itself.
_COMFY_INSTALL_DIR = os.path.dirname(os.path.dirname(os.path.realpath(__file__)))
@functools.cache
def get_deploy_environment() -> str:
env_file = os.path.join(_COMFY_INSTALL_DIR, _ENV_FILENAME)
try:
with open(env_file, encoding="utf-8") as f:
# Cap the read so a malformed or maliciously crafted file (e.g.
# a single huge line with no newline) can't blow up memory.
first_line = f.readline(128).strip()
value = "".join(c for c in first_line if 32 <= ord(c) < 127)
if value:
return value
except FileNotFoundError:
pass
except Exception as e:
logger.error("Failed to read %s: %s", env_file, e)
return _DEFAULT_DEPLOY_ENV

View File

@ -93,7 +93,7 @@ class Hook:
self.hook_scope = hook_scope
'''Scope of where this hook should apply in terms of the conds used in sampling run.'''
self.custom_should_register = default_should_register
'''Can be overridden with a compatible function to decide if this hook should be registered without the need to override .should_register'''
'''Can be overriden with a compatible function to decide if this hook should be registered without the need to override .should_register'''
@property
def strength(self):

View File

@ -106,7 +106,6 @@ class Dino2Encoder(torch.nn.Module):
class Dino2PatchEmbeddings(torch.nn.Module):
def __init__(self, dim, num_channels=3, patch_size=14, image_size=518, dtype=None, device=None, operations=None):
super().__init__()
self.patch_size = patch_size
self.projection = operations.Conv2d(
in_channels=num_channels,
out_channels=dim,
@ -126,37 +125,17 @@ class Dino2Embeddings(torch.nn.Module):
super().__init__()
patch_size = 14
image_size = 518
self.patch_size = patch_size
self.patch_embeddings = Dino2PatchEmbeddings(dim, patch_size=patch_size, image_size=image_size, dtype=dtype, device=device, operations=operations)
self.position_embeddings = torch.nn.Parameter(torch.empty(1, (image_size // patch_size) ** 2 + 1, dim, dtype=dtype, device=device))
self.cls_token = torch.nn.Parameter(torch.empty(1, 1, dim, dtype=dtype, device=device)) # mask_token is a pre-training param, kept only so strict loading accepts the key.
self.cls_token = torch.nn.Parameter(torch.empty(1, 1, dim, dtype=dtype, device=device))
self.mask_token = torch.nn.Parameter(torch.empty(1, dim, dtype=dtype, device=device))
def interpolate_pos_encoding(self, x, h_pixels, w_pixels):
pos_embed = comfy.model_management.cast_to_device(self.position_embeddings, x.device, torch.float32)
class_pos = pos_embed[:, 0:1]
patch_pos = pos_embed[:, 1:]
N = patch_pos.shape[1]
M = int(N ** 0.5)
h0 = h_pixels // self.patch_size
w0 = w_pixels // self.patch_size
scale_factor = ((h0 + 0.1) / M, (w0 + 0.1) / M) # +0.1 matches upstream DINOv2's FP-rounding workaround so the interpolate output size lands on (h0, w0).
patch_pos = patch_pos.reshape(1, M, M, -1).permute(0, 3, 1, 2)
patch_pos = torch.nn.functional.interpolate(patch_pos, scale_factor=scale_factor, mode="bicubic", antialias=False)
patch_pos = patch_pos.permute(0, 2, 3, 1).flatten(1, 2)
return torch.cat((class_pos, patch_pos), dim=1).to(x.dtype)
def forward(self, pixel_values):
x = self.patch_embeddings(pixel_values)
# TODO: mask_token?
x = torch.cat((self.cls_token.to(device=x.device, dtype=x.dtype).expand(x.shape[0], -1, -1), x), dim=1)
if x.shape[1] - 1 == self.position_embeddings.shape[1] - 1:
x = x + comfy.model_management.cast_to_device(self.position_embeddings, x.device, x.dtype)
else:
h, w = pixel_values.shape[-2:]
x = x + self.interpolate_pos_encoding(x, h, w)
x = x + comfy.model_management.cast_to_device(self.position_embeddings, x.device, x.dtype)
return x
@ -179,21 +158,3 @@ class Dinov2Model(torch.nn.Module):
x = self.layernorm(x)
pooled_output = x[:, 0, :]
return x, i, pooled_output, None
def get_intermediate_layers(self, pixel_values, indices, apply_norm=True):
x = self.embeddings(pixel_values)
optimized_attention = optimized_attention_for_device(x.device, False, small_input=True)
n_layers = len(self.encoder.layer)
resolved = [(i if i >= 0 else n_layers + i) for i in indices]
target = set(resolved)
max_idx = max(resolved)
n_skip = 1 # skip cls token
cache = {}
for i, layer in enumerate(self.encoder.layer):
x = layer(x, optimized_attention)
if i in target:
normed = self.layernorm(x) if apply_norm else x
cache[i] = (normed[:, n_skip:], normed[:, 0])
if i >= max_idx:
break
return [cache[i] for i in resolved]

View File

@ -242,7 +242,6 @@ def sample_euler_ancestral_RF(model, x, sigmas, extra_args=None, callback=None,
extra_args = {} if extra_args is None else extra_args
seed = extra_args.get("seed", None)
noise_sampler = default_noise_sampler(x, seed=seed) if noise_sampler is None else noise_sampler
s_noise = s_noise * getattr(model.inner_model.model_patcher.get_model_object('model_sampling'), "noise_scale", 1.0)
s_in = x.new_ones([x.shape[0]])
for i in trange(len(sigmas) - 1, disable=disable):
denoised = model(x, sigmas[i] * s_in, **extra_args)
@ -374,7 +373,6 @@ def sample_dpm_2_ancestral_RF(model, x, sigmas, extra_args=None, callback=None,
extra_args = {} if extra_args is None else extra_args
seed = extra_args.get("seed", None)
noise_sampler = default_noise_sampler(x, seed=seed) if noise_sampler is None else noise_sampler
s_noise = s_noise * getattr(model.inner_model.model_patcher.get_model_object('model_sampling'), "noise_scale", 1.0)
s_in = x.new_ones([x.shape[0]])
for i in trange(len(sigmas) - 1, disable=disable):
denoised = model(x, sigmas[i] * s_in, **extra_args)
@ -688,7 +686,6 @@ def sample_dpmpp_2s_ancestral_RF(model, x, sigmas, extra_args=None, callback=Non
extra_args = {} if extra_args is None else extra_args
seed = extra_args.get("seed", None)
noise_sampler = default_noise_sampler(x, seed=seed) if noise_sampler is None else noise_sampler
s_noise = s_noise * getattr(model.inner_model.model_patcher.get_model_object('model_sampling'), "noise_scale", 1.0)
s_in = x.new_ones([x.shape[0]])
sigma_fn = lambda lbda: (lbda.exp() + 1) ** -1
lambda_fn = lambda sigma: ((1-sigma)/sigma).log()
@ -750,7 +747,6 @@ def sample_dpmpp_sde(model, x, sigmas, extra_args=None, callback=None, disable=N
sigma_fn = partial(half_log_snr_to_sigma, model_sampling=model_sampling)
lambda_fn = partial(sigma_to_half_log_snr, model_sampling=model_sampling)
sigmas = offset_first_sigma_for_snr(sigmas, model_sampling)
s_noise = s_noise * getattr(model_sampling, "noise_scale", 1.0)
for i in trange(len(sigmas) - 1, disable=disable):
denoised = model(x, sigmas[i] * s_in, **extra_args)
@ -836,7 +832,6 @@ def sample_dpmpp_2m_sde(model, x, sigmas, extra_args=None, callback=None, disabl
model_sampling = model.inner_model.model_patcher.get_model_object('model_sampling')
lambda_fn = partial(sigma_to_half_log_snr, model_sampling=model_sampling)
sigmas = offset_first_sigma_for_snr(sigmas, model_sampling)
s_noise = s_noise * getattr(model_sampling, "noise_scale", 1.0)
old_denoised = None
h, h_last = None, None
@ -894,7 +889,6 @@ def sample_dpmpp_3m_sde(model, x, sigmas, extra_args=None, callback=None, disabl
model_sampling = model.inner_model.model_patcher.get_model_object('model_sampling')
lambda_fn = partial(sigma_to_half_log_snr, model_sampling=model_sampling)
sigmas = offset_first_sigma_for_snr(sigmas, model_sampling)
s_noise = s_noise * getattr(model_sampling, "noise_scale", 1.0)
denoised_1, denoised_2 = None, None
h, h_1, h_2 = None, None, None
@ -1012,39 +1006,23 @@ def sample_ddpm(model, x, sigmas, extra_args=None, callback=None, disable=None,
return generic_step_sampler(model, x, sigmas, extra_args, callback, disable, noise_sampler, DDPMSampler_step)
@torch.no_grad()
def sample_lcm(model, x, sigmas, extra_args=None, callback=None, disable=None, noise_sampler=None, s_noise=1.0, s_noise_end=None, noise_clip_std=0.0):
# s_noise / s_noise_end: per-step noise multiplier, linearly interpolated across steps
# noise_clip_std: clamp injected noise to +/- N stddevs (0 disables).
def sample_lcm(model, x, sigmas, extra_args=None, callback=None, disable=None, noise_sampler=None):
extra_args = {} if extra_args is None else extra_args
seed = extra_args.get("seed", None)
noise_sampler = default_noise_sampler(x, seed=seed) if noise_sampler is None else noise_sampler
s_in = x.new_ones([x.shape[0]])
n_steps = max(1, len(sigmas) - 1)
model_sampling = model.inner_model.model_patcher.get_model_object('model_sampling')
s_start = float(s_noise)
s_end = s_start if s_noise_end is None else float(s_noise_end)
for i in trange(n_steps, disable=disable):
for i in trange(len(sigmas) - 1, disable=disable):
denoised = model(x, sigmas[i] * s_in, **extra_args)
if callback is not None:
callback({'x': x, 'i': i, 'sigma': sigmas[i], 'sigma_hat': sigmas[i], 'denoised': denoised})
x = denoised
if sigmas[i + 1] > 0:
noise = noise_sampler(sigmas[i], sigmas[i + 1])
if noise_clip_std > 0:
clip_val = noise_clip_std * noise.std()
noise = noise.clamp(min=-clip_val, max=clip_val)
t = (i / (n_steps - 1)) if n_steps > 1 else 0.0
s_noise_i = s_start + (s_end - s_start) * t
if s_noise_i != 1.0:
noise = noise * s_noise_i
x = model_sampling.noise_scaling(sigmas[i + 1], noise, x)
x = model.inner_model.inner_model.model_sampling.noise_scaling(sigmas[i + 1], noise_sampler(sigmas[i], sigmas[i + 1]), x)
return x
@torch.no_grad()
def sample_heunpp2(model, x, sigmas, extra_args=None, callback=None, disable=None, s_churn=0., s_tmin=0., s_tmax=float('inf'), s_noise=1.):
# From MIT licensed: https://github.com/Carzit/sd-webui-samplers-scheduler/
@ -1271,7 +1249,6 @@ def sample_euler_ancestral_cfg_pp(model, x, sigmas, extra_args=None, callback=No
model_sampling = model.inner_model.model_patcher.get_model_object("model_sampling")
lambda_fn = partial(sigma_to_half_log_snr, model_sampling=model_sampling)
s_noise = s_noise * getattr(model_sampling, "noise_scale", 1.0)
uncond_denoised = None
@ -1319,7 +1296,6 @@ def sample_dpmpp_2s_ancestral_cfg_pp(model, x, sigmas, extra_args=None, callback
extra_args = {} if extra_args is None else extra_args
seed = extra_args.get("seed", None)
noise_sampler = default_noise_sampler(x, seed=seed) if noise_sampler is None else noise_sampler
s_noise = s_noise * getattr(model.inner_model.model_patcher.get_model_object('model_sampling'), "noise_scale", 1.0)
temp = [0]
def post_cfg_function(args):
@ -1395,7 +1371,6 @@ def res_multistep(model, x, sigmas, extra_args=None, callback=None, disable=None
extra_args = {} if extra_args is None else extra_args
seed = extra_args.get("seed", None)
noise_sampler = default_noise_sampler(x, seed=seed) if noise_sampler is None else noise_sampler
s_noise = s_noise * getattr(model.inner_model.model_patcher.get_model_object('model_sampling'), "noise_scale", 1.0)
s_in = x.new_ones([x.shape[0]])
sigma_fn = lambda t: t.neg().exp()
t_fn = lambda sigma: sigma.log().neg()
@ -1529,7 +1504,6 @@ def sample_er_sde(model, x, sigmas, extra_args=None, callback=None, disable=None
extra_args = {} if extra_args is None else extra_args
seed = extra_args.get("seed", None)
noise_sampler = default_noise_sampler(x, seed=seed) if noise_sampler is None else noise_sampler
s_noise = s_noise * getattr(model.inner_model.model_patcher.get_model_object('model_sampling'), "noise_scale", 1.0)
s_in = x.new_ones([x.shape[0]])
def default_er_sde_noise_scaler(x):
@ -1600,10 +1574,9 @@ def sample_seeds_2(model, x, sigmas, extra_args=None, callback=None, disable=Non
seed = extra_args.get("seed", None)
noise_sampler = default_noise_sampler(x, seed=seed) if noise_sampler is None else noise_sampler
s_in = x.new_ones([x.shape[0]])
inject_noise = eta > 0 and s_noise > 0
model_sampling = model.inner_model.model_patcher.get_model_object('model_sampling')
s_noise = s_noise * getattr(model_sampling, "noise_scale", 1.0)
inject_noise = eta > 0 and s_noise > 0
sigma_fn = partial(half_log_snr_to_sigma, model_sampling=model_sampling)
lambda_fn = partial(sigma_to_half_log_snr, model_sampling=model_sampling)
sigmas = offset_first_sigma_for_snr(sigmas, model_sampling)
@ -1672,10 +1645,9 @@ def sample_seeds_3(model, x, sigmas, extra_args=None, callback=None, disable=Non
seed = extra_args.get("seed", None)
noise_sampler = default_noise_sampler(x, seed=seed) if noise_sampler is None else noise_sampler
s_in = x.new_ones([x.shape[0]])
inject_noise = eta > 0 and s_noise > 0
model_sampling = model.inner_model.model_patcher.get_model_object('model_sampling')
s_noise = s_noise * getattr(model_sampling, "noise_scale", 1.0)
inject_noise = eta > 0 and s_noise > 0
sigma_fn = partial(half_log_snr_to_sigma, model_sampling=model_sampling)
lambda_fn = partial(sigma_to_half_log_snr, model_sampling=model_sampling)
sigmas = offset_first_sigma_for_snr(sigmas, model_sampling)
@ -1741,7 +1713,6 @@ def sample_sa_solver(model, x, sigmas, extra_args=None, callback=None, disable=F
s_in = x.new_ones([x.shape[0]])
model_sampling = model.inner_model.model_patcher.get_model_object("model_sampling")
s_noise = s_noise * getattr(model_sampling, "noise_scale", 1.0)
sigmas = offset_first_sigma_for_snr(sigmas, model_sampling)
lambdas = sigma_to_half_log_snr(sigmas, model_sampling=model_sampling)
@ -1839,119 +1810,3 @@ def sample_sa_solver(model, x, sigmas, extra_args=None, callback=None, disable=F
def sample_sa_solver_pece(model, x, sigmas, extra_args=None, callback=None, disable=False, tau_func=None, s_noise=1.0, noise_sampler=None, predictor_order=3, corrector_order=4, simple_order_2=False):
"""Stochastic Adams Solver with PECE (PredictEvaluateCorrectEvaluate) mode (NeurIPS 2023)."""
return sample_sa_solver(model, x, sigmas, extra_args=extra_args, callback=callback, disable=disable, tau_func=tau_func, s_noise=s_noise, noise_sampler=noise_sampler, predictor_order=predictor_order, corrector_order=corrector_order, use_pece=True, simple_order_2=simple_order_2)
@torch.no_grad()
def sample_ar_video(model, x, sigmas, extra_args=None, callback=None, disable=None,
num_frame_per_block=1):
"""
Autoregressive video sampler: block-by-block denoising with KV cache
and flow-match re-noising for Causal Forcing / Self-Forcing models.
Requires a Causal-WAN compatible model (diffusion_model must expose
init_kv_caches / init_crossattn_caches) and 5-D latents [B,C,T,H,W].
All AR-loop parameters are passed via the SamplerARVideo node, not read
from the checkpoint or transformer_options.
"""
extra_args = {} if extra_args is None else extra_args
model_options = extra_args.get("model_options", {})
transformer_options = model_options.get("transformer_options", {})
if x.ndim != 5:
raise ValueError(
f"ar_video sampler requires 5-D video latents [B,C,T,H,W], got {x.ndim}-D tensor with shape {x.shape}. "
"This sampler is only compatible with autoregressive video models (e.g. Causal-WAN)."
)
inner_model = model.inner_model.inner_model
causal_model = inner_model.diffusion_model
if not (hasattr(causal_model, "init_kv_caches") and hasattr(causal_model, "init_crossattn_caches")):
raise TypeError(
"ar_video sampler requires a Causal-WAN compatible model whose diffusion_model "
"exposes init_kv_caches() and init_crossattn_caches(). The loaded checkpoint "
"does not support this interface — choose a different sampler."
)
seed = extra_args.get("seed", 0)
bs, c, lat_t, lat_h, lat_w = x.shape
frame_seq_len = -(-lat_h // 2) * -(-lat_w // 2) # ceiling division
num_blocks = -(-lat_t // num_frame_per_block) # ceiling division
device = x.device
model_dtype = inner_model.get_dtype()
kv_caches = causal_model.init_kv_caches(bs, lat_t * frame_seq_len, device, model_dtype)
crossattn_caches = causal_model.init_crossattn_caches(bs, device, model_dtype)
output = torch.zeros_like(x)
s_in = x.new_ones([x.shape[0]])
current_start_frame = 0
# I2V: seed KV cache with the initial image latent before the denoising loop
initial_latent = transformer_options.get("ar_config", {}).get("initial_latent", None)
if initial_latent is not None:
initial_latent = inner_model.process_latent_in(initial_latent).to(device=device, dtype=model_dtype)
n_init = initial_latent.shape[2]
output[:, :, :n_init] = initial_latent
ar_state = {"start_frame": 0, "kv_caches": kv_caches, "crossattn_caches": crossattn_caches}
transformer_options["ar_state"] = ar_state
zero_sigma = sigmas.new_zeros([1])
_ = model(initial_latent, zero_sigma * s_in, **extra_args)
current_start_frame = n_init
remaining = lat_t - n_init
num_blocks = -(-remaining // num_frame_per_block)
num_sigma_steps = len(sigmas) - 1
total_real_steps = num_blocks * num_sigma_steps
step_count = 0
try:
for block_idx in trange(num_blocks, disable=disable):
bf = min(num_frame_per_block, lat_t - current_start_frame)
fs, fe = current_start_frame, current_start_frame + bf
noisy_input = x[:, :, fs:fe]
ar_state = {
"start_frame": current_start_frame,
"kv_caches": kv_caches,
"crossattn_caches": crossattn_caches,
}
transformer_options["ar_state"] = ar_state
for i in range(num_sigma_steps):
denoised = model(noisy_input, sigmas[i] * s_in, **extra_args)
if callback is not None:
scaled_i = step_count * num_sigma_steps // total_real_steps
callback({"x": noisy_input, "i": scaled_i, "sigma": sigmas[i],
"sigma_hat": sigmas[i], "denoised": denoised})
if sigmas[i + 1] == 0:
noisy_input = denoised
else:
sigma_next = sigmas[i + 1]
torch.manual_seed(seed + block_idx * 1000 + i)
fresh_noise = torch.randn_like(denoised)
noisy_input = (1.0 - sigma_next) * denoised + sigma_next * fresh_noise
for cache in kv_caches:
cache["end"] -= bf * frame_seq_len
step_count += 1
output[:, :, fs:fe] = noisy_input
for cache in kv_caches:
cache["end"] -= bf * frame_seq_len
zero_sigma = sigmas.new_zeros([1])
_ = model(noisy_input, zero_sigma * s_in, **extra_args)
current_start_frame += bf
finally:
transformer_options.pop("ar_state", None)
return output

View File

@ -9,7 +9,6 @@ class LatentFormat:
latent_rgb_factors_reshape = None
taesd_decoder_name = None
spacial_downscale_ratio = 8
temporal_downscale_ratio = 1
def process_in(self, latent):
return latent * self.scale_factor
@ -150,7 +149,6 @@ class SD3(LatentFormat):
class StableAudio1(LatentFormat):
latent_channels = 64
latent_dimensions = 1
temporal_downscale_ratio = 2048
class Flux(SD3):
latent_channels = 16
@ -226,7 +224,6 @@ class Flux2(LatentFormat):
self.latent_rgb_factors_bias = [-0.0329, -0.0718, -0.0851]
self.latent_rgb_factors_reshape = lambda t: t.reshape(t.shape[0], 32, 2, 2, t.shape[-2], t.shape[-1]).permute(0, 1, 4, 2, 5, 3).reshape(t.shape[0], 32, t.shape[-2] * 2, t.shape[-1] * 2)
self.taesd_decoder_name = "taef2_decoder"
def process_in(self, latent):
return latent
@ -237,7 +234,6 @@ class Flux2(LatentFormat):
class Mochi(LatentFormat):
latent_channels = 12
latent_dimensions = 3
temporal_downscale_ratio = 6
def __init__(self):
self.scale_factor = 1.0
@ -281,7 +277,6 @@ class LTXV(LatentFormat):
latent_channels = 128
latent_dimensions = 3
spacial_downscale_ratio = 32
temporal_downscale_ratio = 8
def __init__(self):
self.latent_rgb_factors = [
@ -425,7 +420,6 @@ class LTXAV(LTXV):
class HunyuanVideo(LatentFormat):
latent_channels = 16
latent_dimensions = 3
temporal_downscale_ratio = 4
scale_factor = 0.476986
latent_rgb_factors = [
[-0.0395, -0.0331, 0.0445],
@ -452,7 +446,6 @@ class HunyuanVideo(LatentFormat):
class Cosmos1CV8x8x8(LatentFormat):
latent_channels = 16
latent_dimensions = 3
temporal_downscale_ratio = 8
latent_rgb_factors = [
[ 0.1817, 0.2284, 0.2423],
@ -478,7 +471,6 @@ class Cosmos1CV8x8x8(LatentFormat):
class Wan21(LatentFormat):
latent_channels = 16
latent_dimensions = 3
temporal_downscale_ratio = 4
latent_rgb_factors = [
[-0.1299, -0.1692, 0.2932],
@ -741,7 +733,6 @@ class HunyuanVideo15(LatentFormat):
latent_channels = 32
latent_dimensions = 3
spacial_downscale_ratio = 16
temporal_downscale_ratio = 4
scale_factor = 1.03682
taesd_decoder_name = "lighttaehy1_5"
@ -767,7 +758,6 @@ class ACEAudio(LatentFormat):
class ACEAudio15(LatentFormat):
latent_channels = 64
latent_dimensions = 1
temporal_downscale_ratio = 1764
class ChromaRadiance(LatentFormat):
latent_channels = 3
@ -793,36 +783,3 @@ class ZImagePixelSpace(ChromaRadiance):
No VAE encoding/decoding — the model operates directly on RGB pixels.
"""
pass
class HiDreamO1Pixel(ChromaRadiance):
"""Pixel-space latent format for HiDream-O1.
No VAE — model patches/unpatches raw RGB internally with patch_size=32.
"""
pass
class CogVideoX(LatentFormat):
"""Latent format for CogVideoX-2b (THUDM/CogVideoX-2b).
scale_factor matches the vae/config.json scaling_factor for the 2b variant.
The 5b-class checkpoints (CogVideoX-5b, CogVideoX-1.5-5B, CogVideoX-Fun-V1.5-*)
use a different value; see CogVideoX1_5 below.
"""
latent_channels = 16
latent_dimensions = 3
temporal_downscale_ratio = 4
def __init__(self):
self.scale_factor = 1.15258426
class CogVideoX1_5(CogVideoX):
"""Latent format for 5b-class CogVideoX checkpoints.
Covers THUDM/CogVideoX-5b, THUDM/CogVideoX-1.5-5B, and the CogVideoX-Fun
V1.5-5b family (including VOID inpainting). All of these have
scaling_factor=0.7 in their vae/config.json. Auto-selected in
supported_models.CogVideoX_T2V based on transformer hidden dim.
"""
def __init__(self):
self.scale_factor = 0.7

Some files were not shown because too many files have changed in this diff Show More