feat: add bboxes input to Create Bounding Boxes node

Add a --enable-asset-hashing CLI flag (action=store_true, default False)
and plumb it into the two asset-seeder call sites in main.py that
previously hardcoded compute_hashes=True (the startup scan and the
post-job output enqueue). Local runs now skip blake3 hashing unless the
user opts in, avoiding the startup/per-output cost on large models
directories while keeping hashing available for asset-portability
features.

Co-authored-by: Alexis Rolland <alexisrolland@hotmail.com>

.github/workflows/cla.yml

@@ -1,91 +0,0 @@
-name: CLA Assistant
-
-on:
-  issue_comment:
-    types: [created]
-  pull_request_target:
-    types: [opened, synchronize, closed]
-
-permissions:
-  actions: write
-  contents: read # 'read' is enough because signatures live in a REMOTE repo
-  pull-requests: write
-  statuses: write
-
-jobs:
-  cla-assistant:
-    runs-on: ubuntu-latest
-    steps:
-      # The CLA action normally requires every commit author in a PR to sign.
-      # We only want the PR author to sign, so we allowlist all other committers
-      # by computing them from the PR's commits and excluding the PR author.
-      - name: Build author-only allowlist
-        id: allowlist
-        if: >
-          github.event_name == 'pull_request_target' ||
-          (github.event_name == 'issue_comment' && github.event.issue.pull_request && (
-            github.event.comment.body == 'recheck' ||
-            github.event.comment.body == 'I have read and agree to the Contributor License Agreement'
-          ))
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          PR_NUMBER: ${{ github.event.pull_request.number || github.event.issue.number }}
-          PR_AUTHOR: ${{ github.event.pull_request.user.login || github.event.issue.user.login }}
-          BASE_ALLOWLIST: action@github.com,actions-user,ampagent,claude,comfy-pr-bot,GitHub Action,github-actions,github-actions[bot],Glary Bot,Glary-Bot,*[bot]
-        run: |
-          others=$(gh api "repos/${{ github.repository }}/pulls/${PR_NUMBER}/commits" --paginate \
-            --jq '.[] | (.author.login // empty), (.committer.login // empty)' \
-            | sort -u | grep -vix "${PR_AUTHOR}" | paste -sd, -)
-          if [ -n "$others" ]; then
-            echo "allowlist=${BASE_ALLOWLIST},${others}" >> "$GITHUB_OUTPUT"
-          else
-            echo "allowlist=${BASE_ALLOWLIST}" >> "$GITHUB_OUTPUT"
-          fi
-
-      - name: CLA Assistant
-        # Run on PR events, on "recheck" comment, or when someone posts the exact signing phrase.
-        # IMPORTANT: this phrase must match `custom-pr-sign-comment` below.
-        if: >
-          github.event_name == 'pull_request_target' ||
-          (github.event_name == 'issue_comment' && github.event.issue.pull_request && (
-            github.event.comment.body == 'recheck' ||
-            github.event.comment.body == 'I have read and agree to the Contributor License Agreement'
-          ))
-        uses: contributor-assistant/github-action@ca4a40a7d1004f18d9960b404b97e5f30a505a08 # v2.6.1
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          # PAT required to write to the centralized signatures repo.
-          PERSONAL_ACCESS_TOKEN: ${{ secrets.PERSONAL_ACCESS_TOKEN }}
-        with:
-          # Where the CLA document lives (shown to contributors)
-          path-to-document: https://github.com/Comfy-Org/comfy-cla/blob/main/comfyui_icla.md
-
-          # Centralized signature storage
-          remote-organization-name: comfy-org
-          remote-repository-name: comfy-cla
-          path-to-signatures: signatures/cla.json
-          branch: main
-
-          # Only the PR author must sign: bots plus every non-author committer
-          # are allowlisted via the "Build author-only allowlist" step above.
-          # *[bot] is a catch-all for any GitHub App bot account.
-          allowlist: ${{ steps.allowlist.outputs.allowlist }}
-
-          # Custom PR comment messages
-          custom-notsigned-prcomment: |
-            🎉 Thank you for your contribution, we really appreciate it! 🎉
-
-            Like many open source projects, we require contributors to sign our [Contributor License Agreement (CLA)](https://github.com/Comfy-Org/comfy-cla/blob/main/comfyui_icla.md). A CLA makes the ownership of contributions explicit, so contributors and the project share a clear understanding of how the code can be used. By signing, you:
-
-            - Confirm that you own your contribution.
-            - Keep the right to reuse your own code.
-            - Grant us a copyright license to include and share it within our projects.
-
-            CLAs are standard practice across major open source projects including those under the Apache Software Foundation and the Linux Foundation. Ours is based on the Apache Software Foundation's CLA. Most importantly, it would enable us to relicense the project under a more permissive license in the future, giving the project and its community greater flexibility.
-
-            ✍ **To sign, please post a new comment on this PR with exactly the following text:** ✍
-
-          custom-pr-sign-comment: I have read and agree to the Contributor License Agreement
-
-          custom-allsigned-prcomment: |
-            ✅ All contributors have signed the CLA. Thank you! This PR is ready to be merged.

AGENTS.md

@@ -0,0 +1,166 @@
+## Engineering Style
+
+- Keep changes small and direct. Most fixes should touch the narrowest code path
+  that explains the bug, performance issue, dtype issue, model-format issue, or
+  user-facing behavior.
+- Change the least amount of files possible. A change that touches many files is
+  more likely to be a bad change than a good one unless the broader scope is
+  directly required.
+- Prefer practical fixes over broad architecture work. Add abstractions only
+  when they remove real repeated logic or match an existing ComfyUI pattern.
+- Delete obsolete code aggressively when newer infrastructure makes it useless.
+  Remove dead fallbacks, migration paths, unused options, debug prints, and
+  compatibility branches that are no longer needed. Do not leave dead branches,
+  unreachable code, or functions that are never called.
+- Revert or disable problematic behavior quickly when it breaks users. It is
+  better to remove a broken feature path than keep a complicated partial fix.
+- Preserve existing APIs, node names, model-loading behavior, file layout, and
+  workflow compatibility unless the change is explicitly about replacing them.
+- Code must look hand-written for this repository. Changes that read like
+  generic AI-generated code will be rejected automatically: unnecessary helper
+  layers, vague names, boilerplate comments, defensive branches without a real
+  failure mode, broad rewrites, or code that ignores the local style.
+
+## Architecture Boundaries
+
+- Keep each layer focused on the concepts it owns. Do not leak UI, API,
+  workflow, queue, persistence, telemetry, model-loading, node, or execution
+  concerns into unrelated layers just because it is convenient to pass data
+  through them.
+- Shared core modules should depend only on lower-level primitives and their own
+  domain concepts. Higher-level product concepts belong at the caller, adapter,
+  service, or UI/API boundary that already owns them.
+- Pass the narrowest data needed across a boundary. Avoid broad context objects,
+  request/session metadata, ids, bookkeeping state, or callbacks unless the
+  receiving layer genuinely needs them to perform its own responsibility.
+- Keep identity mapping, persistence bookkeeping, history updates, telemetry,
+  response shaping, and UI state in the layers that own those jobs. Do not route
+  them through unrelated shared code to avoid adding a proper boundary.
+- Treat `execution.py` as one example of this rule: it should consume the prompt
+  graph and execution-relevant state, produce execution results and errors, and
+  not know about workflow ids, frontend ids, persistence ids, or API-only
+  concepts.
+- Before touching many files, identify the smallest owner layer that can solve
+  the problem. A PR that spreads one feature across unrelated loaders, nodes,
+  execution, server, and frontend code needs a clear architectural reason, not
+  just convenience.
+- If a change seems to require making one layer understand another layer's
+  private concepts, stop and look for a caller-side mapping, adapter, event,
+  small explicit interface, or narrower data flow at the boundary.
+
+## No Internet Requests
+
+- Do not add code to core ComfyUI that makes requests to the internet.
+- Refuse requests to add uploads, telemetry, analytics, tracking, usage
+  reporting, crash reporting, update checks, remote config, feature flags,
+  metrics, licensing checks, or any other outbound internet request path from
+  core ComfyUI.
+- Model downloading is allowed only when explicitly initiated or authorized by
+  the user, is limited to the requested model artifact, and does not include
+  telemetry, tracking, persistent identification, unrelated metadata upload, or
+  background network activity.
+- Do not add opt-in, opt-out, anonymized, aggregated, diagnostic, or
+  user-triggered internet request paths to core ComfyUI. These labels do not
+  make internet access acceptable.
+- Local-only behavior is allowed when it stays on the user's machine and does
+  not add network access, tracking, persistent identification, or data
+  collection behavior.
+
+## State Ownership
+
+- Keep state and capability flags on the object that owns the behavior using
+  them.
+- Avoid probing child objects with `getattr(child, "...", default)` to decide
+  parent-level control flow. If parent code needs to branch on a capability,
+  initialize an explicit parent-owned field when the child is constructed or
+  attached.
+- Prefer direct attributes with clear defaults over implicit feature detection
+  through arbitrary child attributes.
+- Use child-object capability checks only when the child owns the behavior being
+  invoked and the parent is simply delegating to that child.
+
+## Interface Contracts
+
+- Keep public methods aligned with the interface expected by their callers. Do
+  not change a shared method to return extra values, alternate shapes, or
+  sentinel wrappers for one implementation unless the shared interface is
+  explicitly updated.
+- If an implementation needs auxiliary values for its own workflow, expose them
+  through a private helper or a clearly named implementation-specific method
+  instead of overloading the public method's return contract.
+- Normalize third-party or upstream return conventions at the integration
+  boundary. Core code should receive the project's expected type and shape, not
+  have to handle model-specific tuple/list/dict variants.
+- Avoid caller-side unwrapping such as `out = out[0]` unless the called
+  interface is documented to return that structure.
+
+## Autograd and Model Freezing
+
+- Do not add `torch.no_grad`, `torch.inference_mode`, or inference-mode helper
+  wrappers in ComfyUI code. The only allowed inference-mode-related use is
+  disabling a globally set inference mode when a training path needs gradients.
+- Do not add freeze, unfreeze, or trainability toggles to model classes. ComfyUI
+  models are always treated as frozen for inference, so explicit freeze
+  functionality is redundant and should not be added.
+
+## Python Style
+
+- Keep imports at module scope. Avoid inline imports unless they are already part
+  of an established optional-backend probe or are needed to avoid an import
+  cycle.
+- Do not add unnecessary `try`/`except` blocks. Use them for optional dependency,
+  platform, or backend capability detection only when the program has a useful
+  fallback. Prefer specific exception types when changing new code.
+- Let unsupported model formats, invalid quantization metadata, and bad states
+  fail with clear errors instead of silently producing lower quality output.
+- Match the existing local style in the file you edit. This codebase tolerates
+  long lines, simple helper functions, module-level state, and direct tensor
+  operations when they make the code easier to follow.
+- Keep comments sparse and useful. Strip useless comments that restate the code
+  or describe obvious behavior. Short TODOs are fine when they name the concrete
+  missing follow-up.
+
+## Model, Device, and Memory Behavior
+
+- Treat dtype, device placement, VRAM usage, and offloading behavior as core
+  correctness concerns. Check CPU, CUDA, ROCm, MPS, DirectML, XPU, NPU, and low
+  VRAM implications when touching shared execution or loading code.
+- Prefer native ComfyUI formats and existing quantization/offload helpers over
+  adding parallel code paths. Use `comfy.quant_ops`, `comfy.model_management`,
+  `comfy.memory_management`, `comfy.pinned_memory`, `comfy_aimdo`, and
+  `comfy-kitchen` helpers where they already solve the problem.
+- Avoid unnecessary casts and transfers. Preserve the intended compute dtype,
+  storage dtype, bias dtype, and original tensor shape metadata.
+- When optimizing, favor small measurable changes: fewer allocations, fewer
+  device transfers, less peak memory, better batching, or use of a faster
+  existing backend op.
+
+## Nodes and User-Facing Behavior
+
+- Follow existing node conventions: `INPUT_TYPES`, `RETURN_TYPES`, `FUNCTION`,
+  `CATEGORY`, and registration through the local mapping used by that file.
+- Keep node changes backward compatible by default. Add inputs with sensible
+  defaults and avoid changing output types unless the request requires it.
+- The official mascot of ComfyUI is a very cute anime girl with massive fennec
+  ears, a big fluffy tail, long blonde wavy hair, and blue eyes. Feel free to
+  use her in ComfyUI materials, UI text, examples, tests, generated assets, or
+  comments, but do not disrespect her.
+- Warning and info messages should be short and actionable. Remove noisy or
+  misleading messages rather than adding more logging.
+- Documentation and README edits should be concise, factual, and tied to the
+  changed behavior.
+
+## Commit and Review Habits
+
+- If asked to write commit messages, use short direct subjects like the existing
+  history: `Fix ...`, `Add ...`, `Support ...`, `Remove ...`, `Update ...`,
+  `Make ...`, `Use ...`, `Disable ...`, `Bump ...`, or `Revert ...`.
+- Keep PR descriptions short and reviewable. State the problem, the behavioral
+  change, and the tests run; avoid long narrative explanations, implementation
+  diaries, or exhaustive file-by-file summaries unless the reviewer explicitly
+  needs that context.
+- Prefer one coherent behavioral change per commit. Dependency pins, tests, and
+  the code that needs them may be in the same commit when they are inseparable.
+- In reviews, prioritize real user impact: crashes, wrong dtype/device behavior,
+  memory regressions, broken model loading, workflow incompatibility, and noisy
+  or misleading user-facing output.

comfy/cli_args.py

@@ -240,6 +240,7 @@ 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("--enable-asset-hashing", action="store_true", help="Compute blake3 content hashes when scanning assets. Hashing enables future asset-portability features (deduplication, cross-machine model resolution) but adds startup cost and per-output cost on large models directories. Off by default; enable to opt in.")
 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.")
 

comfy_api_nodes/apis/gemini.py

@@ -121,6 +121,7 @@ class GeminiGenerationConfig(BaseModel):
     topK: int | None = Field(None, ge=1)
     topP: float | None = Field(None, ge=0.0, le=1.0)
     thinkingConfig: GeminiThinkingConfig | None = Field(None)
+    responseModalities: list[str] | None = Field(None)
 
 
 class GeminiImageOutputOptions(BaseModel):

comfy_api_nodes/nodes_gemini.py

@@ -13,7 +13,7 @@ import torch
 from typing_extensions import override
 
 import folder_paths
-from comfy_api.latest import IO, ComfyExtension, Input, Types
+from comfy_api.latest import IO, ComfyExtension, Input, InputImpl, Types
 from comfy_api_nodes.apis.gemini import (
     GeminiContent,
     GeminiFileData,
@@ -37,6 +37,7 @@ from comfy_api_nodes.util import (
     audio_to_base64_string,
     bytesio_to_image_tensor,
     download_url_to_image_tensor,
+    download_url_to_video_output,
     get_number_of_images,
     sync_op,
     tensor_to_base64_string,
@@ -45,6 +46,7 @@ from comfy_api_nodes.util import (
     upload_images_to_comfyapi,
     upload_video_to_comfyapi,
     validate_string,
+    validate_video_duration,
     video_to_base64_string,
 )
 
@@ -229,10 +231,29 @@ async def get_image_from_response(response: GeminiGenerateContentResponse, thoug
     return torch.cat(image_tensors, dim=0)
 
 
+async def get_video_from_response(
+    response: GeminiGenerateContentResponse, cls: type[IO.ComfyNode] | None = None
+) -> InputImpl.VideoFromFile:
+    parts = get_parts_by_type(response, "video/*")
+    for part in parts:
+        if part.inlineData and part.inlineData.data:
+            return InputImpl.VideoFromFile(BytesIO(base64.b64decode(part.inlineData.data)))
+        if part.fileData and part.fileData.fileUri:
+            return await download_url_to_video_output(part.fileData.fileUri, cls=cls)
+    model_message = get_text_from_response(response).strip()
+    if model_message:
+        raise ValueError(f"Gemini did not generate a video. Model response: {model_message}")
+    raise ValueError(
+        "Gemini did not generate a video. Try rephrasing your prompt, "
+        "shortening the requested duration, or reducing the number of input images/videos."
+    )
+
+
 def calculate_tokens_price(response: GeminiGenerateContentResponse) -> float | None:
     if not response.modelVersion:
         return None
     # Define prices (Cost per 1,000,000 tokens), see https://cloud.google.com/vertex-ai/generative-ai/pricing
+    output_video_tokens_price = 0.0
     if response.modelVersion == "gemini-2.5-pro":
         input_tokens_price = 1.25
         output_text_tokens_price = 10.0
@@ -249,18 +270,27 @@ def calculate_tokens_price(response: GeminiGenerateContentResponse) -> float | N
         input_tokens_price = 2
         output_text_tokens_price = 12.0
         output_image_tokens_price = 0.0
-    elif response.modelVersion == "gemini-3.1-flash-lite-preview":
+    elif response.modelVersion in ("gemini-3.1-flash-lite-preview", "gemini-3.1-flash-lite"):
         input_tokens_price = 0.25
         output_text_tokens_price = 1.50
         output_image_tokens_price = 0.0
-    elif response.modelVersion == "gemini-3-pro-image-preview":
+    elif response.modelVersion in ("gemini-3-pro-image-preview", "gemini-3-pro-image"):
         input_tokens_price = 2
         output_text_tokens_price = 12.0
         output_image_tokens_price = 120.0
-    elif response.modelVersion == "gemini-3.1-flash-image-preview":
+    elif response.modelVersion in ("gemini-3.1-flash-image-preview", "gemini-3.1-flash-image"):
         input_tokens_price = 0.5
         output_text_tokens_price = 3.0
         output_image_tokens_price = 60.0
+    elif response.modelVersion == "gemini-3.1-flash-lite-image":
+        input_tokens_price = 0.25
+        output_text_tokens_price = 1.50
+        output_image_tokens_price = 30.0
+    elif response.modelVersion == "gemini-omni-flash-preview":
+        input_tokens_price = 2.145
+        output_text_tokens_price = 12.87
+        output_image_tokens_price = 0.0
+        output_video_tokens_price = 25.025
     else:
         return None
     final_price = response.usageMetadata.promptTokenCount * input_tokens_price
@@ -268,6 +298,8 @@ def calculate_tokens_price(response: GeminiGenerateContentResponse) -> float | N
         for i in response.usageMetadata.candidatesTokensDetails:
             if i.modality == Modality.IMAGE:
                 final_price += output_image_tokens_price * i.tokenCount  # for Nano Banana models
+            elif i.modality == Modality.VIDEO:
+                final_price += output_video_tokens_price * i.tokenCount  # for Omni Flash
             else:
                 final_price += output_text_tokens_price * i.tokenCount
     if response.usageMetadata.thoughtsTokenCount:
@@ -1302,7 +1334,7 @@ class GeminiNanoBanana2(IO.ComfyNode):
         )
 
 
-def _nano_banana_2_v2_model_inputs():
+def _nano_banana_2_v2_model_inputs(resolutions: list[str]):
     return [
         IO.Combo.Input(
             "aspect_ratio",
@@ -1329,8 +1361,8 @@ def _nano_banana_2_v2_model_inputs():
         ),
         IO.Combo.Input(
             "resolution",
-            options=["1K", "2K", "4K"],
-            tooltip="Target output resolution. For 2K/4K the native Gemini upscaler is used.",
+            options=resolutions,
+            tooltip="Target output resolution.",
         ),
         IO.Combo.Input(
             "thinking_level",
@@ -1376,7 +1408,11 @@ class GeminiNanoBanana2V2(IO.ComfyNode):
                     options=[
                         IO.DynamicCombo.Option(
                             "Nano Banana 2 (Gemini 3.1 Flash Image)",
-                            _nano_banana_2_v2_model_inputs(),
+                            _nano_banana_2_v2_model_inputs(resolutions=["1K", "2K", "4K"]),
+                        ),
+                        IO.DynamicCombo.Option(
+                            "Nano Banana 2 Lite",
+                            _nano_banana_2_v2_model_inputs(resolutions=["1K"]),
                         ),
                     ],
                 ),
@@ -1445,9 +1481,13 @@ class GeminiNanoBanana2V2(IO.ComfyNode):
                 depends_on=IO.PriceBadgeDepends(widgets=["model", "model.resolution"]),
                 expr="""
                 (
-                  $r := $lookup(widgets, "model.resolution");
-                  $prices := {"1k": 0.0696, "2k": 0.1014, "4k": 0.154};
-                  {"type":"usd","usd": $lookup($prices, $r), "format":{"suffix":"/Image","approximate":true}}
+                  $contains(widgets.model, "lite")
+                    ? {"type":"usd","usd": 0.034, "format":{"suffix":"/Image","approximate":true}}
+                    : (
+                        $r := $lookup(widgets, "model.resolution");
+                        $prices := {"1k": 0.0696, "2k": 0.1014, "4k": 0.154};
+                        {"type":"usd","usd": $lookup($prices, $r), "format":{"suffix":"/Image","approximate":true}}
+                      )
                 )
                 """,
             ),
@@ -1468,6 +1508,8 @@ class GeminiNanoBanana2V2(IO.ComfyNode):
         model_choice = model["model"]
         if model_choice == "Nano Banana 2 (Gemini 3.1 Flash Image)":
             model_id = "gemini-3.1-flash-image-preview"
+        elif model_choice == "Nano Banana 2 Lite":
+            model_id = "gemini-3.1-flash-lite-image"
         else:
             model_id = model_choice
 
@@ -1517,6 +1559,149 @@ class GeminiNanoBanana2V2(IO.ComfyNode):
         )
 
 
+OMNI_MAX_IMAGES = 14
+OMNI_MAX_VIDEOS = 3
+
+OMNI_MODELS: dict[str, str] = {
+    "Omni Flash": "gemini-omni-flash-preview",
+}
+
+
+def _omni_flash_inputs() -> list[Input]:
+    """Per-model inputs for the Omni video DynamicCombo (prompt + reference media + sampling)."""
+    return [
+        IO.String.Input(
+            "prompt",
+            multiline=True,
+            default="",
+            tooltip="Describe the video to generate. Specify the length and aspect ratio directly in the "
+            'prompt, e.g. "a 6-second clip in 16:9". Length may be 3-10 seconds; the aspect ratio must be '
+            "16:9 (landscape) or 9:16 (portrait). The output is 720p, 24 FPS, with audio.",
+        ),
+        IO.Autogrow.Input(
+            "images",
+            template=IO.Autogrow.TemplateNames(
+                IO.Image.Input("image"),
+                names=[f"image_{i}" for i in range(1, OMNI_MAX_IMAGES + 1)],
+                min=0,
+            ),
+            tooltip=f"Optional reference image(s) to guide or animate the video. Up to {OMNI_MAX_IMAGES} images.",
+        ),
+        IO.Autogrow.Input(
+            "videos",
+            template=IO.Autogrow.TemplateNames(
+                IO.Video.Input("video"),
+                names=[f"video_{i}" for i in range(1, OMNI_MAX_VIDEOS + 1)],
+                min=0,
+            ),
+            tooltip=f"Optional reference video(s) to guide or edit. Up to {OMNI_MAX_VIDEOS} videos, "
+            f"each up to 10 seconds long.",
+        ),
+        IO.Float.Input(
+            "temperature",
+            default=1.0,
+            min=0.0,
+            max=2.0,
+            step=0.01,
+            tooltip="Controls randomness. Lower is more focused/deterministic, higher is more varied.",
+            advanced=True,
+        ),
+        IO.Float.Input(
+            "top_p",
+            default=0.95,
+            min=0.0,
+            max=1.0,
+            step=0.01,
+            tooltip="Nucleus sampling: sample from the smallest token set whose cumulative probability reaches top_p.",
+            advanced=True,
+        ),
+    ]
+
+
+class GeminiVideoOmni(IO.ComfyNode):
+
+    @classmethod
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="GeminiVideoOmni",
+            display_name="Google Gemini Omni (Video)",
+            category="partner/video/Gemini",
+            essentials_category="Video Generation",
+            description="Generate a video with audio from a text prompt using Google's Gemini Omni Flash model. "
+            "Optionally provide reference images and/or videos to guide or edit the result. Describe the desired "
+            "length (3-10s) and aspect ratio (16:9 or 9:16) directly in the prompt.",
+            inputs=[
+                IO.DynamicCombo.Input(
+                    "model",
+                    options=[
+                        IO.DynamicCombo.Option("Omni Flash", _omni_flash_inputs()),
+                    ],
+                    tooltip="The Gemini video model used to generate the video.",
+                ),
+                IO.Int.Input(
+                    "seed",
+                    default=42,
+                    min=0,
+                    max=2147483647,
+                    control_after_generate=True,
+                    tooltip="Seed controls whether the node should re-run; "
+                    "results are non-deterministic regardless of seed.",
+                ),
+            ],
+            outputs=[
+                IO.Video.Output(),
+                IO.String.Output(),
+            ],
+            hidden=[
+                IO.Hidden.auth_token_comfy_org,
+                IO.Hidden.api_key_comfy_org,
+                IO.Hidden.unique_id,
+            ],
+            is_api_node=True,
+            price_badge=IO.PriceBadge(
+                expr='{"type":"usd","usd":0.146,"format":{"suffix":"/second","approximate":true}}'
+            ),
+        )
+
+    @classmethod
+    async def execute(cls, model: dict, seed: int) -> IO.NodeOutput:
+        prompt = model.get("prompt") or ""
+        validate_string(prompt, strip_whitespace=True, min_length=1)
+        model_id = OMNI_MODELS[model["model"]]
+
+        images = [t for t in (model.get("images") or {}).values() if t is not None]
+        videos = [v for v in (model.get("videos") or {}).values() if v is not None]
+        if sum(get_number_of_images(t) for t in images) > OMNI_MAX_IMAGES:
+            raise ValueError(f"The current maximum number of supported images is {OMNI_MAX_IMAGES}.")
+        if len(videos) > OMNI_MAX_VIDEOS:
+            raise ValueError(f"The current maximum number of supported videos is {OMNI_MAX_VIDEOS}.")
+        for video in videos:
+            validate_video_duration(video, max_duration=10)
+
+        parts: list[GeminiPart] = []
+        if images or videos:
+            parts.extend(await build_gemini_media_parts(cls, images, [], videos))
+        parts.append(GeminiPart(text=prompt))
+        response = await sync_op(
+            cls,
+            ApiEndpoint(path=f"{GEMINI_BASE_ENDPOINT}/{model_id}", method="POST"),
+            data=GeminiGenerateContentRequest(
+                contents=[GeminiContent(role=GeminiRole.user, parts=parts)],
+                generationConfig=GeminiGenerationConfig(
+                    responseModalities=["TEXT", "VIDEO"],
+                    temperature=model.get("temperature", 1.0),
+                    topP=model.get("top_p", 0.95),
+                ),
+            ),
+            response_model=GeminiGenerateContentResponse,
+            price_extractor=calculate_tokens_price,
+        )
+        return IO.NodeOutput(
+            await get_video_from_response(response, cls=cls),
+            get_text_from_response(response),
+        )
+
+
 class GeminiExtension(ComfyExtension):
     @override
     async def get_node_list(self) -> list[type[IO.ComfyNode]]:
@@ -1527,6 +1712,7 @@ class GeminiExtension(ComfyExtension):
             GeminiImage2,
             GeminiNanoBanana2,
             GeminiNanoBanana2V2,
+            GeminiVideoOmni,
             GeminiInputFiles,
         ]
 

comfy_extras/nodes_bounding_boxes.py

@@ -166,6 +166,32 @@ def boxes_to_regions(boxes, width: int, height: int) -> list:
     return regions
 
 
+def normalize_incoming_boxes(bboxes) -> list:
+    if isinstance(bboxes, dict):
+        frame = [bboxes]
+    elif not isinstance(bboxes, list) or not bboxes:
+        frame = []
+    elif isinstance(bboxes[0], dict):
+        frame = bboxes
+    else:
+        frame = bboxes[0] if isinstance(bboxes[0], list) else []
+    boxes = []
+    for box in frame:
+        if not isinstance(box, dict):
+            continue
+        norm = {
+            "x": box.get("x", 0),
+            "y": box.get("y", 0),
+            "width": box.get("width", 0),
+            "height": box.get("height", 0),
+        }
+        meta = box.get("metadata")
+        if isinstance(meta, dict):
+            norm["metadata"] = meta
+        boxes.append(norm)
+    return boxes
+
+
 def _norm_bbox(region: dict) -> list[int]:
     def grid(value: float) -> int:
         return max(0, min(1000, round(value * 1000)))
@@ -199,6 +225,8 @@ def build_elements(regions: list) -> list:
 
 
 class CreateBoundingBoxes(io.ComfyNode):
+    _last_incoming: dict = {}
+
     @classmethod
     def define_schema(cls):
         editor_state = io.BoundingBoxes.Input(
@@ -217,6 +245,12 @@ class CreateBoundingBoxes(io.ComfyNode):
                     optional=True,
                     tooltip="Optional image used as background in the canvas and preview.",
                 ),
+                io.BoundingBox.Input(
+                    "bboxes",
+                    force_input=True,
+                    optional=True,
+                    tooltip="Bounding boxes from an upstream node. A new upstream value seeds the canvas; edits you make on the canvas take priority and are kept until the upstream value changes again.",
+                ),
                 io.Int.Input("width", default=1024, min=64, max=16384, step=16,
                              tooltip="Width of the canvas and the pixel grid for the bounding boxes."),
                 io.Int.Input("height", default=1024, min=64, max=16384, step=16,
@@ -228,18 +262,33 @@ class CreateBoundingBoxes(io.ComfyNode):
                 io.BoundingBox.Output(display_name="bboxes"),
                 io.Array.Output(display_name="elements"),
             ],
+            hidden=[io.Hidden.unique_id],
+            is_output_node=True,
             is_experimental=True,
         )
 
     @classmethod
-    def execute(cls, width, height, editor_state=None, background=None) -> io.NodeOutput:
-        regions = boxes_to_regions(editor_state, width, height)
+    def execute(cls, width, height, editor_state=None, background=None, bboxes=None) -> io.NodeOutput:
+        incoming = normalize_incoming_boxes(bboxes)
+        node_id = cls.hidden.unique_id
+        if incoming:
+            changed = cls._last_incoming.get(node_id) != incoming
+            if changed:
+                cls._last_incoming[node_id] = incoming
+        else:
+            changed = False
+            cls._last_incoming.pop(node_id, None)
+        source = incoming if changed else (editor_state or incoming)
+        regions = boxes_to_regions(source, width, height)
         preview = render_preview(regions, width, height, _bg_from_image(background))
+        ui = {"dims": [width, height]}
+        if incoming:
+            ui["input_bboxes"] = incoming
         return io.NodeOutput(
             preview,
             fractions_to_bbox_frame(regions, width, height),
             build_elements(regions),
-            ui={"dims": [width, height]},
+            ui=ui,
         )
 
 

comfy_extras/nodes_cond.py

@@ -8,7 +8,8 @@ class CLIPTextEncodeControlnet(io.ComfyNode):
     def define_schema(cls) -> io.Schema:
         return io.Schema(
             node_id="CLIPTextEncodeControlnet",
-            category="experimental/conditioning",
+            display_name="CLIP Text Encode (Controlnet)",
+            category="model/conditioning",
             inputs=[
                 io.Clip.Input("clip"),
                 io.Conditioning.Input("conditioning"),
@@ -35,11 +36,12 @@ class T5TokenizerOptions(io.ComfyNode):
     def define_schema(cls) -> io.Schema:
         return io.Schema(
             node_id="T5TokenizerOptions",
-            category="experimental/conditioning",
+            display_name="T5 Tokenizer Options",
+            category="model/conditioning",
             inputs=[
                 io.Clip.Input("clip"),
-                io.Int.Input("min_padding", default=0, min=0, max=10000, step=1, advanced=True),
-                io.Int.Input("min_length", default=0, min=0, max=10000, step=1, advanced=True),
+                io.Int.Input("min_padding", default=0, min=0, max=10000, step=1),
+                io.Int.Input("min_length", default=0, min=0, max=10000, step=1),
             ],
             outputs=[io.Clip.Output()],
             is_experimental=True,

comfy_extras/nodes_custom_sampler.py

@@ -1070,7 +1070,7 @@ class AddNoise(io.ComfyNode):
     def define_schema(cls):
         return io.Schema(
             node_id="AddNoise",
-            category="experimental/custom_sampling/noise",
+            category="model/sampling/noise",
             is_experimental=True,
             inputs=[
                 io.Model.Input("model"),
@@ -1120,7 +1120,7 @@ class ManualSigmas(io.ComfyNode):
         return io.Schema(
             node_id="ManualSigmas",
             search_aliases=["custom noise schedule", "define sigmas"],
-            category="experimental/custom_sampling",
+            category="model/sampling/sigmas",
             is_experimental=True,
             inputs=[
                 io.String.Input("sigmas", default="1, 0.5", multiline=False)

comfy_extras/nodes_photomaker.py

@@ -123,7 +123,8 @@ class PhotoMakerLoader(io.ComfyNode):
     def define_schema(cls):
         return io.Schema(
             node_id="PhotoMakerLoader",
-            category="experimental/photomaker",
+            display_name="Load PhotoMaker Model",
+            category="model/loaders",
             inputs=[
                 io.Combo.Input("photomaker_model_name", options=folder_paths.get_filename_list("photomaker")),
             ],
@@ -149,7 +150,8 @@ class PhotoMakerEncode(io.ComfyNode):
     def define_schema(cls):
         return io.Schema(
             node_id="PhotoMakerEncode",
-            category="experimental/photomaker",
+            display_name="PhotoMaker Encode",
+            category="model/conditioning/photomaker",
             inputs=[
                 io.Photomaker.Input("photomaker"),
                 io.Image.Input("image"),

comfy_extras/nodes_stable_cascade.py

@@ -119,7 +119,7 @@ class StableCascade_SuperResolutionControlnet(io.ComfyNode):
     def define_schema(cls):
         return io.Schema(
             node_id="StableCascade_SuperResolutionControlnet",
-            category="experimental/stable_cascade",
+            category="experimental/stable cascade",
             is_experimental=True,
             inputs=[
                 io.Image.Input("image"),

comfy_extras/nodes_triposplat.py

@@ -143,7 +143,7 @@ class VAEDecodeTripoSplat(IO.ComfyNode):
         return IO.Schema(
             node_id="VAEDecodeTripoSplat",
             display_name="TripoSplat Decode",
-            category="3d/latent",
+            category="model/latent/triposplat",
             description="Decode the sampled TripoSplat latent into a 3D gaussian splat. "
                         "Modify the number of gaussians to vary the density.",
             inputs=[
@@ -188,7 +188,7 @@ class TripoSplatSamplingPreview(IO.ComfyNode):
         return IO.Schema(
             node_id="TripoSplatSamplingPreview",
             display_name="TripoSplat Sampling Preview",
-            category="3d/latent",
+            category="model/latent/triposplat",
             description="Patch the TripoSplat model for the standard Ksampler node to show a live decoded "
                         "gaussian splat preview at each step.",
             inputs=[

comfyui_version.py

@@ -1,3 +1,3 @@
 # This file is automatically generated by the build process when version is
 # updated in pyproject.toml.
-__version__ = "0.26.0"
+__version__ = "0.27.0"

main.py

@@ -403,7 +403,7 @@ def prompt_worker(q, server_instance):
                 hook_breaker_ac10a0.restore_functions()
 
                 if not asset_seeder.is_disabled():
-                    asset_seeder.enqueue_enrich(roots=("output",), compute_hashes=True)
+                    asset_seeder.enqueue_enrich(roots=("output",), compute_hashes=args.enable_asset_hashing)
                 asset_seeder.resume()
 
 
@@ -458,7 +458,7 @@ def setup_database():
         if dependencies_available():
             init_db()
             if args.enable_assets:
-                if asset_seeder.start(roots=("models", "input", "output"), prune_first=True, compute_hashes=True):
+                if asset_seeder.start(roots=("models", "input", "output"), prune_first=True, compute_hashes=args.enable_asset_hashing):
                     logging.info("Background asset scan initiated for models, input, output")
     except Exception as e:
         if "database is locked" in str(e):

nodes.py

@@ -159,6 +159,29 @@ class ConditioningConcat:
 
         return (out, )
 
+class ConditioningMultiply:
+    SEARCH_ALIASES = ["scale conditioning", "scale prompt", "multiply conditioning", "multiply prompt"]
+
+    @classmethod
+    def INPUT_TYPES(cls):
+        return {"required": {"conditioning": ("CONDITIONING", ),
+                            "multiplier": ("FLOAT", {"default": 1.0, "min": -100.0, "max": 100.0, "step": 0.01})
+                            }}
+    RETURN_TYPES = ("CONDITIONING",)
+    FUNCTION     = "multiply"
+    CATEGORY     = "model/conditioning/transform"
+
+    def multiply(self, conditioning, multiplier):
+        c = []
+        for t in conditioning:
+            values = {}
+            pooled_output = t[1].get("pooled_output", None)
+            if pooled_output is not None:
+                values["pooled_output"] = pooled_output * multiplier
+            scaled = node_helpers.conditioning_set_values([[t[0] * multiplier, t[1]]], values)[0]
+            c.append(scaled)
+        return (c,)
+
 class ConditioningSetArea:
     SEARCH_ALIASES = ["regional prompt", "area prompt", "spatial conditioning", "localized prompt"]
 
@@ -326,7 +349,7 @@ class VAEDecodeTiled:
     RETURN_TYPES = ("IMAGE",)
     FUNCTION = "decode"
 
-    CATEGORY = "experimental"
+    CATEGORY = "model/latent"
 
     def decode(self, vae, samples, tile_size, overlap=64, temporal_size=64, temporal_overlap=8):
         if tile_size < overlap * 4:
@@ -373,7 +396,7 @@ class VAEEncodeTiled:
     RETURN_TYPES = ("LATENT",)
     FUNCTION = "encode"
 
-    CATEGORY = "experimental"
+    CATEGORY = "model/latent"
 
     def encode(self, vae, pixels, tile_size, overlap, temporal_size=64, temporal_overlap=8):
         t = vae.encode_tiled(pixels, tile_x=tile_size, tile_y=tile_size, overlap=overlap, tile_t=temporal_size, overlap_t=temporal_overlap)
@@ -491,7 +514,7 @@ class SaveLatent:
 
     OUTPUT_NODE = True
 
-    CATEGORY = "experimental"
+    CATEGORY = "model/latent"
 
     def save(self, samples, filename_prefix="ComfyUI", prompt=None, extra_pnginfo=None):
         full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(filename_prefix, self.output_dir)
@@ -536,7 +559,7 @@ class LoadLatent:
         files = [f for f in os.listdir(input_dir) if os.path.isfile(os.path.join(input_dir, f)) and f.endswith(".latent")]
         return {"required": {"latent": [sorted(files), ]}, }
 
-    CATEGORY = "experimental"
+    CATEGORY = "model/latent"
 
     RETURN_TYPES = ("LATENT", )
     FUNCTION = "load"
@@ -2050,6 +2073,7 @@ NODE_CLASS_MAPPINGS = {
     "ConditioningAverage": ConditioningAverage,
     "ConditioningCombine": ConditioningCombine,
     "ConditioningConcat": ConditioningConcat,
+    "ConditioningMultiply": ConditioningMultiply,
     "ConditioningSetArea": ConditioningSetArea,
     "ConditioningSetAreaPercentage": ConditioningSetAreaPercentage,
     "ConditioningSetAreaStrength": ConditioningSetAreaStrength,
@@ -2121,6 +2145,7 @@ NODE_DISPLAY_NAME_MAPPINGS = {
     "ConditioningAverage ": "Conditioning (Average)",
     "ConditioningAverage": "Conditioning (Average)",
     "ConditioningConcat": "Conditioning (Concat)",
+    "ConditioningMultiply": "Conditioning (Multiply)",
     "ConditioningSetArea": "Conditioning (Set Area)",
     "ConditioningSetAreaPercentage": "Conditioning (Set Area with Percentage)",
     "ConditioningSetAreaStrength": "Conditioning (Set Area Strength)",
@@ -2130,6 +2155,8 @@ NODE_DISPLAY_NAME_MAPPINGS = {
     "GLIGENTextBoxApply": "Apply GLIGEN Text Box",
     "ConditioningZeroOut": "Conditioning Zero Out",
     # Latent
+    "LoadLatent": "Load Latent",
+    "SaveLatent": "Save Latent",
     "VAEEncodeForInpaint": "VAE Encode (for Inpainting)",
     "SetLatentNoiseMask": "Set Latent Noise Mask",
     "VAEDecode": "VAE Decode",
@@ -2164,7 +2191,6 @@ NODE_DISPLAY_NAME_MAPPINGS = {
     "ImageSharpen": "Sharpen Image",
     "ImageScaleToTotalPixels": "Scale Image to Total Pixels",
     "GetImageSize": "Get Image Size",
-    # experimental
     "VAEDecodeTiled": "VAE Decode (Tiled)",
     "VAEEncodeTiled": "VAE Encode (Tiled)",
 }

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ComfyUI"
-version = "0.26.0"
+version = "0.27.0"
 readme = "README.md"
 license = { file = "LICENSE" }
 requires-python = ">=3.10"

requirements.txt

@@ -1,6 +1,6 @@
-comfyui-frontend-package==1.45.19
-comfyui-workflow-templates==0.10.7
-comfyui-embedded-docs==0.5.5
+comfyui-frontend-package==1.45.20
+comfyui-workflow-templates==0.11.1
+comfyui-embedded-docs==0.5.6
 torch
 torchsde
 torchvision
@@ -22,7 +22,7 @@ alembic
 SQLAlchemy>=2.0.0
 filelock
 av>=16.0.0
-comfy-kitchen==0.2.14
+comfy-kitchen==0.2.16
 comfy-aimdo==0.4.10
 requests
 simpleeval>=1.0.0