mirror of
https://github.com/comfyanonymous/ComfyUI.git
synced 2026-07-10 06:06:14 +08:00
Compare commits
2 Commits
release/v0
...
fix/surfac
| Author | SHA1 | Date | |
|---|---|---|---|
| ffdc23c6dd | |||
| 91f3c0c4d9 |
38
.github/workflows/ci-cursor-review.yml
vendored
38
.github/workflows/ci-cursor-review.yml
vendored
@ -1,38 +0,0 @@
|
||||
name: CI - Cursor Review
|
||||
|
||||
# Thin caller for the shared reusable cursor-review workflow in
|
||||
# Comfy-Org/github-workflows. The review logic (panel matrix, judge
|
||||
# consolidation, prompts, extract/post/notify scripts) lives there as the
|
||||
# single source of truth, so this repo only carries the repo-specific diff
|
||||
# excludes.
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
types: [labeled, unlabeled]
|
||||
|
||||
concurrency:
|
||||
group: cursor-review-pr-${{ github.event.pull_request.number }}-${{ github.event.label.name }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
cursor-review:
|
||||
if: github.event.label.name == 'cursor-review'
|
||||
permissions:
|
||||
contents: read
|
||||
pull-requests: write
|
||||
# SHA-pinned per zizmor `unpinned-uses: hash-pin`. Bump this SHA to pick up
|
||||
# upstream changes; keep `workflows_ref` matching so prompts/scripts load
|
||||
# from the same commit as the workflow definition.
|
||||
uses: Comfy-Org/github-workflows/.github/workflows/cursor-review.yml@047ca48febe3a6647608ed2e0c4331b491cb9d6a # github-workflows#9
|
||||
with:
|
||||
workflows_ref: 047ca48febe3a6647608ed2e0c4331b491cb9d6a
|
||||
diff_excludes: >-
|
||||
:!**/.claude/**
|
||||
:!**/dist/**
|
||||
:!**/vendor/**
|
||||
:!**/*.generated.*
|
||||
:!**/*.min.js
|
||||
:!**/*.min.css
|
||||
secrets:
|
||||
CURSOR_API_KEY: ${{ secrets.CURSOR_API_KEY }}
|
||||
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
|
||||
@ -240,7 +240,6 @@ 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("--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.")
|
||||
|
||||
|
||||
@ -256,7 +256,7 @@ def resolve_cast_module_with_vbar(s, dtype, device, bias_dtype, compute_dtype, w
|
||||
if (want_requant and len(fns) == 0 or update_weight):
|
||||
seed = comfy.utils.string_to_seed(s.seed_key)
|
||||
if isinstance(orig, QuantizedTensor):
|
||||
y = orig.requantize_from_float(x, scale="recalculate", stochastic_rounding=seed)
|
||||
y = QuantizedTensor.from_float(x, s.layout_type, scale="recalculate", stochastic_rounding=seed)
|
||||
else:
|
||||
y = comfy.float.stochastic_rounding(x, orig.dtype, seed=seed)
|
||||
if want_requant and len(fns) == 0:
|
||||
@ -1216,7 +1216,7 @@ def mixed_precision_ops(quant_config={}, compute_dtype=torch.bfloat16, full_prec
|
||||
bias_dtype=input.dtype,
|
||||
offloadable=True,
|
||||
compute_dtype=compute_dtype,
|
||||
want_requant=True,
|
||||
want_requant=want_requant,
|
||||
)
|
||||
weight = weight.to(dtype=input.dtype)
|
||||
else:
|
||||
@ -1306,7 +1306,8 @@ def mixed_precision_ops(quant_config={}, compute_dtype=torch.bfloat16, full_prec
|
||||
|
||||
def set_weight(self, weight, inplace_update=False, seed=None, return_weight=False, **kwargs):
|
||||
if getattr(self, 'layout_type', None) is not None:
|
||||
weight = self.weight.requantize_from_float(weight, scale="recalculate", stochastic_rounding=seed, inplace_ops=True).to(self.weight.dtype)
|
||||
# dtype is now implicit in the layout class
|
||||
weight = QuantizedTensor.from_float(weight, self.layout_type, scale="recalculate", stochastic_rounding=seed, inplace_ops=True).to(self.weight.dtype)
|
||||
else:
|
||||
weight = weight.to(self.weight.dtype)
|
||||
if return_weight:
|
||||
|
||||
@ -281,18 +281,11 @@ class VideoFromFile(VideoInput):
|
||||
video_done = False
|
||||
audio_done = True
|
||||
|
||||
# Use the last decodable audio stream. Streams FFmpeg has no decoder for have no codec context,
|
||||
# and decoding their packets crashes the process. (e.g. APAC spatial-audio track in iPhone)
|
||||
audio_stream = next(
|
||||
(s for s in reversed(container.streams.audio) if s.codec_context is not None),
|
||||
None,
|
||||
)
|
||||
if audio_stream is not None:
|
||||
if len(container.streams.audio):
|
||||
audio_stream = container.streams.audio[-1]
|
||||
streams += [audio_stream]
|
||||
resampler = av.audio.resampler.AudioResampler(format='fltp')
|
||||
audio_done = False
|
||||
elif len(container.streams.audio):
|
||||
logging.warning("No decodable audio stream found in video; ignoring audio.")
|
||||
|
||||
for packet in container.demux(*streams):
|
||||
if video_done and audio_done:
|
||||
@ -464,13 +457,10 @@ class VideoFromFile(VideoInput):
|
||||
else:
|
||||
output_container.metadata[key] = json.dumps(value)
|
||||
|
||||
# Add streams to the new container. Streams with no codec context cannot be used as an output template.
|
||||
# Add streams to the new container
|
||||
stream_map = {}
|
||||
for stream in streams:
|
||||
if isinstance(stream, (av.VideoStream, av.AudioStream, SubtitleStream)):
|
||||
if stream.codec_context is None:
|
||||
logging.warning("Skipping %s stream %d with unsupported codec", stream.type, stream.index)
|
||||
continue
|
||||
out_stream = output_container.add_stream_from_template(template=stream, opaque=True)
|
||||
stream_map[stream] = out_stream
|
||||
|
||||
|
||||
@ -1,4 +1,4 @@
|
||||
from typing import Any, Literal
|
||||
from typing import Literal
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
@ -24,8 +24,8 @@ class Seedream4TaskCreationRequest(BaseModel):
|
||||
image: list[str] | None = Field(None, description="Image URLs")
|
||||
size: str = Field(...)
|
||||
seed: int = Field(..., ge=0, le=2147483647)
|
||||
sequential_image_generation: str | None = Field("disabled")
|
||||
sequential_image_generation_options: Seedream4Options | None = Field(Seedream4Options(max_images=15))
|
||||
sequential_image_generation: str = Field("disabled")
|
||||
sequential_image_generation_options: Seedream4Options = Field(Seedream4Options(max_images=15))
|
||||
watermark: bool = Field(False)
|
||||
output_format: str | None = None
|
||||
|
||||
@ -261,19 +261,6 @@ _PRESETS_SEEDREAM_4K = [
|
||||
|
||||
_CUSTOM_PRESET = [("Custom", None, None)]
|
||||
|
||||
_PRESETS_SEEDREAM_2K_PRO = [
|
||||
("(2K) 2048x2048 (1:1)", 2048, 2048),
|
||||
("(2K) 1728x2304 (3:4)", 1728, 2304),
|
||||
("(2K) 2304x1728 (4:3)", 2304, 1728),
|
||||
# ("(2K) 2848x1600 (16:9)", 2848, 1600), # 4,556,800 px - temporarily unavailable
|
||||
# ("(2K) 1600x2848 (9:16)", 1600, 2848), # 4,556,800 px - temporarily unavailable
|
||||
("(2K) 1664x2496 (2:3)", 1664, 2496),
|
||||
("(2K) 2496x1664 (3:2)", 2496, 1664),
|
||||
# ("(2K) 3136x1344 (21:9)", 3136, 1344), # 4,214,784 px - temporarily unavailable
|
||||
]
|
||||
RECOMMENDED_PRESETS_SEEDREAM_5_PRO = (
|
||||
_PRESETS_SEEDREAM_1K + _PRESETS_SEEDREAM_2K_PRO + _CUSTOM_PRESET
|
||||
)
|
||||
RECOMMENDED_PRESETS_SEEDREAM_5_LITE = (
|
||||
_PRESETS_SEEDREAM_2K + _PRESETS_SEEDREAM_3K + _PRESETS_SEEDREAM_4K + _CUSTOM_PRESET
|
||||
)
|
||||
@ -329,36 +316,3 @@ VIDEO_TASKS_EXECUTION_TIME = {
|
||||
"1080p": 150,
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
class SeedAudioConfig(BaseModel):
|
||||
format: str = Field(default="mp3")
|
||||
sample_rate: int = Field(default=24000)
|
||||
speech_rate: int = Field(default=0)
|
||||
loudness_rate: int = Field(default=0)
|
||||
pitch_rate: int = Field(default=0)
|
||||
|
||||
|
||||
class SeedAudioReference(BaseModel):
|
||||
speaker: str | None = Field(default=None)
|
||||
audio_data: str | None = Field(default=None)
|
||||
audio_url: str | None = Field(default=None)
|
||||
image_data: str | None = Field(default=None)
|
||||
image_url: str | None = Field(default=None)
|
||||
|
||||
|
||||
class SeedAudioRequest(BaseModel):
|
||||
model: str = Field(default="seed-audio-1.0")
|
||||
text_prompt: str = Field(...)
|
||||
references: list[SeedAudioReference] | None = Field(default=None)
|
||||
audio_config: SeedAudioConfig = Field(default_factory=SeedAudioConfig)
|
||||
watermark: dict[str, Any] = Field(default_factory=dict)
|
||||
|
||||
|
||||
class SeedAudioResponse(BaseModel):
|
||||
audio: str | None = Field(default=None)
|
||||
url: str | None = Field(default=None)
|
||||
duration: float | None = Field(default=None)
|
||||
original_duration: float | None = Field(default=None)
|
||||
code: int | None = Field(default=None)
|
||||
message: str | None = Field(default=None)
|
||||
|
||||
@ -121,7 +121,6 @@ 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):
|
||||
|
||||
@ -33,6 +33,53 @@ class IdeogramColorPalette(
|
||||
)
|
||||
|
||||
|
||||
class ImageRequest(BaseModel):
|
||||
aspect_ratio: Optional[str] = Field(
|
||||
None,
|
||||
description="Optional. The aspect ratio (e.g., 'ASPECT_16_9', 'ASPECT_1_1'). Cannot be used with resolution. Defaults to 'ASPECT_1_1' if unspecified.",
|
||||
)
|
||||
color_palette: Optional[Dict[str, Any]] = Field(
|
||||
None, description='Optional. Color palette object. Only for V_2, V_2_TURBO.'
|
||||
)
|
||||
magic_prompt_option: Optional[str] = Field(
|
||||
None, description="Optional. MagicPrompt usage ('AUTO', 'ON', 'OFF')."
|
||||
)
|
||||
model: str = Field(..., description="The model used (e.g., 'V_2', 'V_2A_TURBO')")
|
||||
negative_prompt: Optional[str] = Field(
|
||||
None,
|
||||
description='Optional. Description of what to exclude. Only for V_1, V_1_TURBO, V_2, V_2_TURBO.',
|
||||
)
|
||||
num_images: Optional[int] = Field(
|
||||
1,
|
||||
description='Optional. Number of images to generate (1-8). Defaults to 1.',
|
||||
ge=1,
|
||||
le=8,
|
||||
)
|
||||
prompt: str = Field(
|
||||
..., description='Required. The prompt to use to generate the image.'
|
||||
)
|
||||
resolution: Optional[str] = Field(
|
||||
None,
|
||||
description="Optional. Resolution (e.g., 'RESOLUTION_1024_1024'). Only for model V_2. Cannot be used with aspect_ratio.",
|
||||
)
|
||||
seed: Optional[int] = Field(
|
||||
None,
|
||||
description='Optional. A number between 0 and 2147483647.',
|
||||
ge=0,
|
||||
le=2147483647,
|
||||
)
|
||||
style_type: Optional[str] = Field(
|
||||
None,
|
||||
description="Optional. Style type ('AUTO', 'GENERAL', 'REALISTIC', 'DESIGN', 'RENDER_3D', 'ANIME'). Only for models V_2 and above.",
|
||||
)
|
||||
|
||||
|
||||
class IdeogramGenerateRequest(BaseModel):
|
||||
image_request: ImageRequest = Field(
|
||||
..., description='The image generation request parameters.'
|
||||
)
|
||||
|
||||
|
||||
class Datum(BaseModel):
|
||||
is_image_safe: Optional[bool] = Field(
|
||||
None, description='Indicates whether the image is considered safe.'
|
||||
@ -66,6 +113,20 @@ class StyleCode(RootModel[str]):
|
||||
root: str = Field(..., pattern='^[0-9A-Fa-f]{8}$')
|
||||
|
||||
|
||||
class Datum1(BaseModel):
|
||||
is_image_safe: Optional[bool] = None
|
||||
prompt: Optional[str] = None
|
||||
resolution: Optional[str] = None
|
||||
seed: Optional[int] = None
|
||||
style_type: Optional[str] = None
|
||||
url: Optional[str] = None
|
||||
|
||||
|
||||
class IdeogramV3IdeogramResponse(BaseModel):
|
||||
created: Optional[datetime] = None
|
||||
data: Optional[List[Datum1]] = None
|
||||
|
||||
|
||||
class RenderingSpeed1(str, Enum):
|
||||
TURBO = 'TURBO'
|
||||
DEFAULT = 'DEFAULT'
|
||||
|
||||
147
comfy_api_nodes/apis/stability.py
Normal file
147
comfy_api_nodes/apis/stability.py
Normal file
@ -0,0 +1,147 @@
|
||||
from enum import Enum
|
||||
from typing import Optional
|
||||
|
||||
from pydantic import BaseModel, Field, confloat
|
||||
|
||||
|
||||
class StabilityFormat(str, Enum):
|
||||
png = 'png'
|
||||
jpeg = 'jpeg'
|
||||
webp = 'webp'
|
||||
|
||||
|
||||
class StabilityAspectRatio(str, Enum):
|
||||
ratio_1_1 = "1:1"
|
||||
ratio_16_9 = "16:9"
|
||||
ratio_9_16 = "9:16"
|
||||
ratio_3_2 = "3:2"
|
||||
ratio_2_3 = "2:3"
|
||||
ratio_5_4 = "5:4"
|
||||
ratio_4_5 = "4:5"
|
||||
ratio_21_9 = "21:9"
|
||||
ratio_9_21 = "9:21"
|
||||
|
||||
|
||||
def get_stability_style_presets(include_none=True):
|
||||
presets = []
|
||||
if include_none:
|
||||
presets.append("None")
|
||||
return presets + [x.value for x in StabilityStylePreset]
|
||||
|
||||
|
||||
class StabilityStylePreset(str, Enum):
|
||||
_3d_model = "3d-model"
|
||||
analog_film = "analog-film"
|
||||
anime = "anime"
|
||||
cinematic = "cinematic"
|
||||
comic_book = "comic-book"
|
||||
digital_art = "digital-art"
|
||||
enhance = "enhance"
|
||||
fantasy_art = "fantasy-art"
|
||||
isometric = "isometric"
|
||||
line_art = "line-art"
|
||||
low_poly = "low-poly"
|
||||
modeling_compound = "modeling-compound"
|
||||
neon_punk = "neon-punk"
|
||||
origami = "origami"
|
||||
photographic = "photographic"
|
||||
pixel_art = "pixel-art"
|
||||
tile_texture = "tile-texture"
|
||||
|
||||
|
||||
class Stability_SD3_5_Model(str, Enum):
|
||||
sd3_5_large = "sd3.5-large"
|
||||
# sd3_5_large_turbo = "sd3.5-large-turbo"
|
||||
sd3_5_medium = "sd3.5-medium"
|
||||
|
||||
|
||||
class Stability_SD3_5_GenerationMode(str, Enum):
|
||||
text_to_image = "text-to-image"
|
||||
image_to_image = "image-to-image"
|
||||
|
||||
|
||||
class StabilityStable3_5Request(BaseModel):
|
||||
model: str = Field(...)
|
||||
mode: str = Field(...)
|
||||
prompt: str = Field(...)
|
||||
negative_prompt: Optional[str] = Field(None)
|
||||
aspect_ratio: Optional[str] = Field(None)
|
||||
seed: Optional[int] = Field(None)
|
||||
output_format: Optional[str] = Field(StabilityFormat.png.value)
|
||||
image: Optional[str] = Field(None)
|
||||
style_preset: Optional[str] = Field(None)
|
||||
cfg_scale: float = Field(...)
|
||||
strength: Optional[confloat(ge=0.0, le=1.0)] = Field(None)
|
||||
|
||||
|
||||
class StabilityUpscaleConservativeRequest(BaseModel):
|
||||
prompt: str = Field(...)
|
||||
negative_prompt: Optional[str] = Field(None)
|
||||
seed: Optional[int] = Field(None)
|
||||
output_format: Optional[str] = Field(StabilityFormat.png.value)
|
||||
image: Optional[str] = Field(None)
|
||||
creativity: Optional[confloat(ge=0.2, le=0.5)] = Field(None)
|
||||
|
||||
|
||||
class StabilityUpscaleCreativeRequest(BaseModel):
|
||||
prompt: str = Field(...)
|
||||
negative_prompt: Optional[str] = Field(None)
|
||||
seed: Optional[int] = Field(None)
|
||||
output_format: Optional[str] = Field(StabilityFormat.png.value)
|
||||
image: Optional[str] = Field(None)
|
||||
creativity: Optional[confloat(ge=0.1, le=0.5)] = Field(None)
|
||||
style_preset: Optional[str] = Field(None)
|
||||
|
||||
|
||||
class StabilityStableUltraRequest(BaseModel):
|
||||
prompt: str = Field(...)
|
||||
negative_prompt: Optional[str] = Field(None)
|
||||
aspect_ratio: Optional[str] = Field(None)
|
||||
seed: Optional[int] = Field(None)
|
||||
output_format: Optional[str] = Field(StabilityFormat.png.value)
|
||||
image: Optional[str] = Field(None)
|
||||
style_preset: Optional[str] = Field(None)
|
||||
strength: Optional[confloat(ge=0.0, le=1.0)] = Field(None)
|
||||
|
||||
|
||||
class StabilityStableUltraResponse(BaseModel):
|
||||
image: Optional[str] = Field(None)
|
||||
finish_reason: Optional[str] = Field(None)
|
||||
seed: Optional[int] = Field(None)
|
||||
|
||||
|
||||
class StabilityResultsGetResponse(BaseModel):
|
||||
image: Optional[str] = Field(None)
|
||||
finish_reason: Optional[str] = Field(None)
|
||||
seed: Optional[int] = Field(None)
|
||||
id: Optional[str] = Field(None)
|
||||
name: Optional[str] = Field(None)
|
||||
errors: Optional[list[str]] = Field(None)
|
||||
status: Optional[str] = Field(None)
|
||||
result: Optional[str] = Field(None)
|
||||
|
||||
|
||||
class StabilityAsyncResponse(BaseModel):
|
||||
id: Optional[str] = Field(None)
|
||||
|
||||
|
||||
class StabilityTextToAudioRequest(BaseModel):
|
||||
model: str = Field(...)
|
||||
prompt: str = Field(...)
|
||||
duration: int = Field(190, ge=1, le=190)
|
||||
seed: int = Field(0, ge=0, le=4294967294)
|
||||
steps: int = Field(8, ge=4, le=8)
|
||||
output_format: str = Field("wav")
|
||||
|
||||
|
||||
class StabilityAudioToAudioRequest(StabilityTextToAudioRequest):
|
||||
strength: float = Field(0.01, ge=0.01, le=1.0)
|
||||
|
||||
|
||||
class StabilityAudioInpaintRequest(StabilityTextToAudioRequest):
|
||||
mask_start: int = Field(30, ge=0, le=190)
|
||||
mask_end: int = Field(190, ge=0, le=190)
|
||||
|
||||
|
||||
class StabilityAudioResponse(BaseModel):
|
||||
audio: Optional[str] = Field(None)
|
||||
@ -1,4 +1,3 @@
|
||||
import base64
|
||||
import hashlib
|
||||
import logging
|
||||
import math
|
||||
@ -16,16 +15,11 @@ from comfy_api_nodes.apis.bytedance import (
|
||||
RECOMMENDED_PRESETS_SEEDREAM_4_0,
|
||||
RECOMMENDED_PRESETS_SEEDREAM_4_5,
|
||||
RECOMMENDED_PRESETS_SEEDREAM_5_LITE,
|
||||
RECOMMENDED_PRESETS_SEEDREAM_5_PRO,
|
||||
SEEDANCE2_REF_VIDEO_PIXEL_LIMITS,
|
||||
VIDEO_TASKS_EXECUTION_TIME,
|
||||
GetAssetResponse,
|
||||
Image2VideoTaskCreationRequest,
|
||||
ImageTaskCreationResponse,
|
||||
SeedAudioConfig,
|
||||
SeedAudioReference,
|
||||
SeedAudioRequest,
|
||||
SeedAudioResponse,
|
||||
Seedance2TaskCreationRequest,
|
||||
SeedanceCreateAssetRequest,
|
||||
SeedanceCreateAssetResponse,
|
||||
@ -49,8 +43,6 @@ from comfy_api_nodes.apis.bytedance import (
|
||||
)
|
||||
from comfy_api_nodes.util import (
|
||||
ApiEndpoint,
|
||||
audio_bytes_to_audio_input,
|
||||
audio_input_to_mp3,
|
||||
download_url_to_image_tensor,
|
||||
download_url_to_video_output,
|
||||
downscale_image_tensor_by_max_side,
|
||||
@ -59,14 +51,11 @@ from comfy_api_nodes.util import (
|
||||
image_tensor_pair_to_batch,
|
||||
poll_op,
|
||||
sync_op,
|
||||
tensor_to_base64_string,
|
||||
upload_audio_to_comfyapi,
|
||||
upload_image_to_comfyapi,
|
||||
upload_images_to_comfyapi,
|
||||
upload_video_to_comfyapi,
|
||||
upscale_image_tensor_to_min_pixels,
|
||||
upscale_video_to_min_pixels,
|
||||
validate_audio_duration,
|
||||
validate_image_aspect_ratio,
|
||||
validate_image_dimensions,
|
||||
validate_string,
|
||||
@ -81,14 +70,12 @@ _VERIFICATION_POLL_TIMEOUT_SEC = 120
|
||||
_VERIFICATION_POLL_INTERVAL_SEC = 3
|
||||
|
||||
SEEDREAM_MODELS = {
|
||||
"seedream 5.0 pro": "seedream-5-0-pro-260628",
|
||||
"seedream 5.0 lite": "seedream-5-0-260128",
|
||||
"seedream-4-5-251128": "seedream-4-5-251128",
|
||||
"seedream-4-0-250828": "seedream-4-0-250828",
|
||||
}
|
||||
|
||||
SEEDREAM_PRESETS = {
|
||||
"seedream-5-0-pro-260628": RECOMMENDED_PRESETS_SEEDREAM_5_PRO,
|
||||
"seedream-5-0-260128": RECOMMENDED_PRESETS_SEEDREAM_5_LITE,
|
||||
"seedream-4-5-251128": RECOMMENDED_PRESETS_SEEDREAM_4_5,
|
||||
"seedream-4-0-250828": RECOMMENDED_PRESETS_SEEDREAM_4_0,
|
||||
@ -746,15 +733,8 @@ class ByteDanceSeedreamNode(IO.ComfyNode):
|
||||
return IO.NodeOutput(torch.cat([await download_url_to_image_tensor(i) for i in urls]))
|
||||
|
||||
|
||||
def _seedream_model_inputs(
|
||||
*,
|
||||
max_ref_images: int,
|
||||
presets: list,
|
||||
max_width: int = 6240,
|
||||
max_height: int = 4992,
|
||||
supports_batch: bool = True,
|
||||
):
|
||||
inputs = [
|
||||
def _seedream_model_inputs(*, max_ref_images: int, presets: list):
|
||||
return [
|
||||
IO.Combo.Input(
|
||||
"size_preset",
|
||||
options=[label for label, _, _ in presets],
|
||||
@ -764,7 +744,7 @@ def _seedream_model_inputs(
|
||||
"width",
|
||||
default=2048,
|
||||
min=1024,
|
||||
max=max_width,
|
||||
max=6240,
|
||||
step=2,
|
||||
tooltip="Custom width for image. Value is working only if `size_preset` is set to `Custom`",
|
||||
),
|
||||
@ -772,27 +752,22 @@ def _seedream_model_inputs(
|
||||
"height",
|
||||
default=2048,
|
||||
min=1024,
|
||||
max=max_height,
|
||||
max=4992,
|
||||
step=2,
|
||||
tooltip="Custom height for image. Value is working only if `size_preset` is set to `Custom`",
|
||||
),
|
||||
]
|
||||
if supports_batch:
|
||||
inputs.append(
|
||||
IO.Int.Input(
|
||||
"max_images",
|
||||
default=1,
|
||||
min=1,
|
||||
max=max_ref_images,
|
||||
step=1,
|
||||
display_mode=IO.NumberDisplay.number,
|
||||
tooltip="Maximum number of images to generate. With 1, exactly one image is produced. "
|
||||
"With >1, the model generates between 1 and max_images related images "
|
||||
"(e.g., story scenes, character variations). "
|
||||
"Total images (input + generated) cannot exceed 15.",
|
||||
)
|
||||
)
|
||||
inputs.append(
|
||||
IO.Int.Input(
|
||||
"max_images",
|
||||
default=1,
|
||||
min=1,
|
||||
max=max_ref_images,
|
||||
step=1,
|
||||
display_mode=IO.NumberDisplay.number,
|
||||
tooltip="Maximum number of images to generate. With 1, exactly one image is produced. "
|
||||
"With >1, the model generates between 1 and max_images related images "
|
||||
"(e.g., story scenes, character variations). "
|
||||
"Total images (input + generated) cannot exceed 15.",
|
||||
),
|
||||
IO.Autogrow.Input(
|
||||
"images",
|
||||
template=IO.Autogrow.TemplateNames(
|
||||
@ -802,18 +777,14 @@ def _seedream_model_inputs(
|
||||
),
|
||||
tooltip=f"Optional reference image(s) for image-to-image or multi-reference generation. "
|
||||
f"Up to {max_ref_images} images.",
|
||||
)
|
||||
)
|
||||
if supports_batch:
|
||||
inputs.append(
|
||||
IO.Boolean.Input(
|
||||
"fail_on_partial",
|
||||
default=False,
|
||||
tooltip="If enabled, abort execution if any requested images are missing or return an error.",
|
||||
advanced=True,
|
||||
)
|
||||
)
|
||||
return inputs
|
||||
),
|
||||
IO.Boolean.Input(
|
||||
"fail_on_partial",
|
||||
default=False,
|
||||
tooltip="If enabled, abort execution if any requested images are missing or return an error.",
|
||||
advanced=True,
|
||||
),
|
||||
]
|
||||
|
||||
|
||||
class ByteDanceSeedreamNodeV2(IO.ComfyNode):
|
||||
@ -835,16 +806,6 @@ class ByteDanceSeedreamNodeV2(IO.ComfyNode):
|
||||
IO.DynamicCombo.Input(
|
||||
"model",
|
||||
options=[
|
||||
IO.DynamicCombo.Option(
|
||||
"seedream 5.0 pro",
|
||||
_seedream_model_inputs(
|
||||
max_ref_images=10,
|
||||
presets=RECOMMENDED_PRESETS_SEEDREAM_5_PRO,
|
||||
max_width=3136,
|
||||
max_height=2496,
|
||||
supports_batch=False,
|
||||
),
|
||||
),
|
||||
IO.DynamicCombo.Option(
|
||||
"seedream 5.0 lite",
|
||||
_seedream_model_inputs(max_ref_images=14, presets=RECOMMENDED_PRESETS_SEEDREAM_5_LITE),
|
||||
@ -886,27 +847,15 @@ class ByteDanceSeedreamNodeV2(IO.ComfyNode):
|
||||
],
|
||||
is_api_node=True,
|
||||
price_badge=IO.PriceBadge(
|
||||
depends_on=IO.PriceBadgeDepends(
|
||||
widgets=["model", "model.size_preset", "model.width", "model.height"]
|
||||
),
|
||||
depends_on=IO.PriceBadgeDepends(widgets=["model"]),
|
||||
expr="""
|
||||
(
|
||||
$sp := $lookup(widgets, "model.size_preset");
|
||||
$px := $lookup(widgets, "model.width") * $lookup(widgets, "model.height");
|
||||
$isPro := $contains(widgets.model, "5.0 pro");
|
||||
$price := $isPro
|
||||
? (
|
||||
$contains($sp, "custom")
|
||||
? ($px <= 2360000 ? 0.045 : 0.09)
|
||||
: ($contains($sp, "1k") ? 0.045 : 0.09)
|
||||
)
|
||||
: $contains(widgets.model, "5.0 lite") ? 0.035
|
||||
: $contains(widgets.model, "4-5") ? 0.04
|
||||
: 0.03;
|
||||
$price := $contains(widgets.model, "5.0 lite") ? 0.035 :
|
||||
$contains(widgets.model, "4-5") ? 0.04 : 0.03;
|
||||
{
|
||||
"type": "usd",
|
||||
"type":"usd",
|
||||
"usd": $price,
|
||||
"format": { "suffix": $isPro ? "/Image" : " x images/Run", "approximate": true }
|
||||
"format": { "suffix":" x images/Run", "approximate": true }
|
||||
}
|
||||
)
|
||||
""",
|
||||
@ -924,7 +873,6 @@ class ByteDanceSeedreamNodeV2(IO.ComfyNode):
|
||||
validate_string(prompt, strip_whitespace=True, min_length=1)
|
||||
model_id = SEEDREAM_MODELS[model["model"]]
|
||||
presets = SEEDREAM_PRESETS[model_id]
|
||||
is_pro = "seedream-5-0-pro" in model_id
|
||||
|
||||
size_preset = model.get("size_preset", presets[0][0])
|
||||
width = model.get("width", 2048)
|
||||
@ -944,29 +892,19 @@ class ByteDanceSeedreamNodeV2(IO.ComfyNode):
|
||||
|
||||
out_num_pixels = w * h
|
||||
mp_provided = out_num_pixels / 1_000_000.0
|
||||
if is_pro:
|
||||
if out_num_pixels < 921_600:
|
||||
raise ValueError(
|
||||
f"Minimum image resolution for the selected model is 0.92MP, but {mp_provided:.2f}MP provided."
|
||||
)
|
||||
if out_num_pixels > 4_194_304:
|
||||
raise ValueError(
|
||||
f"Maximum image resolution for the selected model is 4.19MP, but {mp_provided:.2f}MP provided."
|
||||
)
|
||||
else:
|
||||
if ("seedream-4-5" in model_id or "seedream-5-0" in model_id) and out_num_pixels < 3_686_400:
|
||||
raise ValueError(
|
||||
f"Minimum image resolution for the selected model is 3.68MP, but {mp_provided:.2f}MP provided."
|
||||
)
|
||||
if "seedream-4-0" in model_id and out_num_pixels < 921_600:
|
||||
raise ValueError(
|
||||
f"Minimum image resolution that the selected model can generate is 0.92MP, "
|
||||
f"but {mp_provided:.2f}MP provided."
|
||||
)
|
||||
if out_num_pixels > 16_777_216:
|
||||
raise ValueError(
|
||||
f"Maximum image resolution for the selected model is 16.78MP, but {mp_provided:.2f}MP provided."
|
||||
)
|
||||
if ("seedream-4-5" in model_id or "seedream-5-0" in model_id) and out_num_pixels < 3686400:
|
||||
raise ValueError(
|
||||
f"Minimum image resolution for the selected model is 3.68MP, but {mp_provided:.2f}MP provided."
|
||||
)
|
||||
if "seedream-4-0" in model_id and out_num_pixels < 921600:
|
||||
raise ValueError(
|
||||
f"Minimum image resolution that the selected model can generate is 0.92MP, "
|
||||
f"but {mp_provided:.2f}MP provided."
|
||||
)
|
||||
if out_num_pixels > 16_777_216:
|
||||
raise ValueError(
|
||||
f"Maximum image resolution for the selected model is 16.78MP, but {mp_provided:.2f}MP provided."
|
||||
)
|
||||
|
||||
image_tensors: list[Input.Image] = [t for t in images_dict.values() if t is not None]
|
||||
n_input_images = sum(get_number_of_images(t) for t in image_tensors)
|
||||
@ -1002,8 +940,8 @@ class ByteDanceSeedreamNodeV2(IO.ComfyNode):
|
||||
image=reference_images_urls,
|
||||
size=f"{w}x{h}",
|
||||
seed=seed,
|
||||
sequential_image_generation=None if is_pro else sequential_image_generation,
|
||||
sequential_image_generation_options=None if is_pro else Seedream4Options(max_images=max_images),
|
||||
sequential_image_generation=sequential_image_generation,
|
||||
sequential_image_generation_options=Seedream4Options(max_images=max_images),
|
||||
watermark=watermark,
|
||||
),
|
||||
)
|
||||
@ -2536,311 +2474,6 @@ class ByteDanceCreateVideoAsset(IO.ComfyNode):
|
||||
return IO.NodeOutput(asset_id, resolved_group)
|
||||
|
||||
|
||||
MODE_TEXT = "text only"
|
||||
MODE_AUDIO = "audio reference"
|
||||
MODE_IMAGE = "image reference"
|
||||
MODE_SPEAKER = "preset voice"
|
||||
|
||||
# (speaker_id, display_label) for built-in TTS 2.0 voices; resolvable ids are account-scoped.
|
||||
SEED_AUDIO_PRESET_VOICES: list[tuple[str, str]] = [
|
||||
("zh_female_vv_uranus_bigtts", "Vivi (Female, multilingual)"),
|
||||
("zh_female_xiaohe_uranus_bigtts", "Mindy (Female, multilingual)"),
|
||||
("en_female_stokie_uranus_bigtts", "Stokie (Female, English)"),
|
||||
("en_female_dacey_uranus_bigtts", "Dacey (Female, English)"),
|
||||
("en_male_tim_uranus_bigtts", "Tim (Male, English)"),
|
||||
("zh_male_m191_uranus_bigtts", "Kian (Male, multilingual)"),
|
||||
("zh_male_taocheng_uranus_bigtts", "Cedric (Male, multilingual)"),
|
||||
("zh_male_sophie_uranus_bigtts", "Sophie (Female, multilingual)"),
|
||||
("zh_female_yingyujiaoxue_uranus_bigtts", "Jean (Female, multilingual)"),
|
||||
("zh_male_dayi_uranus_bigtts", "Magnus (Male, multilingual)"),
|
||||
("zh_female_mizai_uranus_bigtts", "Mabel (Female, multilingual)"),
|
||||
("zh_female_jitangnv_uranus_bigtts", "Nadia (Female, multilingual)"),
|
||||
("zh_female_meilinvyou_uranus_bigtts", "Opal (Female, multilingual)"),
|
||||
("zh_female_liuchangnv_uranus_bigtts", "Pearl (Female, multilingual)"),
|
||||
("zh_male_ruyayichen_uranus_bigtts", "Quentin (Male, multilingual)"),
|
||||
("zh_female_vivo_uranus_bigtts", "Vienna (Female, multilingual)"),
|
||||
("zh_female_xiaoai_uranus_bigtts", "Alina (Female, multilingual)"),
|
||||
("zh_female_cancan_uranus_bigtts", "Corinne (Female, multilingual)"),
|
||||
("zh_female_tianmeixiaoyuan_uranus_bigtts", "Esther (Female, multilingual)"),
|
||||
("zh_female_tianmeitaozi_uranus_bigtts", "Freya (Female, multilingual)"),
|
||||
("zh_female_shuangkuaisisi_uranus_bigtts", "Gigi (Female, multilingual)"),
|
||||
("zh_female_peiqi_uranus_bigtts", "Holly (Female, multilingual)"),
|
||||
("zh_female_xiaoxue_uranus_bigtts", "Lyla (Female, multilingual)"),
|
||||
("zh_female_yuanqi_uranus_bigtts", "Daisy (Female, multilingual)"),
|
||||
("zh_female_kefunvsheng_uranus_bigtts", "Tracy (Female, multilingual)"),
|
||||
("zh_male_shaonianzixin_uranus_bigtts", "Jess (Male, multilingual)"),
|
||||
("zh_female_linjianvhai_uranus_bigtts", "Pinky (Female, multilingual)"),
|
||||
("zh_female_kiwi_uranus_bigtts", "Sweety (Female, multilingual)"),
|
||||
("zh_female_sajiaoxuemei_uranus_bigtts", "Sandy (Female, multilingual)"),
|
||||
("de_male_seven_uranus_bigtts", "Sven (Male, German)"),
|
||||
("jp_female_minimi_uranus_bigtts", "Minimi (Female, Japanese)"),
|
||||
("fr_male_usseau_uranus_bigtts", "Usseau (Male, French)"),
|
||||
("es_male_felipe_uranus_bigtts", "Felipe (Male, Spanish)"),
|
||||
("id_male_han_uranus_bigtts", "Han (Male, Indonesian)"),
|
||||
("pt_male_martins_uranus_bigtts", "Martins (Male, Portuguese)"),
|
||||
("it_male_enzo_uranus_bigtts", "Enzo (Male, Italian)"),
|
||||
("kr_male_shane_uranus_bigtts", "Shane (Male, Korean)"),
|
||||
("zh_male_liufei_uranus_bigtts", "Felix (Male, Chinese)"),
|
||||
("zh_female_qingxinnvsheng_uranus_bigtts", "Celeste (Female, Chinese)"),
|
||||
("zh_male_sunwukong_uranus_bigtts", "Monkey King (Male, Chinese)"),
|
||||
]
|
||||
SEED_AUDIO_VOICE_OPTIONS = [label for _, label in SEED_AUDIO_PRESET_VOICES]
|
||||
SEED_AUDIO_VOICE_MAP = {label: speaker_id for speaker_id, label in SEED_AUDIO_PRESET_VOICES}
|
||||
|
||||
_AUDIO_TAG_RE = re.compile(r"@Audio(\d+)", re.IGNORECASE)
|
||||
|
||||
|
||||
def max_audio_tag(prompt: str) -> int:
|
||||
"""Highest N referenced as @AudioN in the prompt (0 if none)."""
|
||||
nums = [int(m) for m in _AUDIO_TAG_RE.findall(prompt or "")]
|
||||
return max(nums) if nums else 0
|
||||
|
||||
|
||||
def connected_audio_indices(reference_mode: dict) -> list[int]:
|
||||
"""Indices (1-based) of connected reference_audio sockets, in order."""
|
||||
return [
|
||||
i
|
||||
for i in range(1, 3 + 1)
|
||||
if reference_mode.get(f"reference_audio_{i}") is not None
|
||||
]
|
||||
|
||||
|
||||
def validate_seed_audio_inputs(
|
||||
text_prompt: str,
|
||||
mode: str,
|
||||
audio_indices: list[int],
|
||||
has_image: bool,
|
||||
preset_voice: str | None = None,
|
||||
) -> None:
|
||||
validate_string(text_prompt, field_name="text_prompt", min_length=1, max_length=3000)
|
||||
max_tag = max_audio_tag(text_prompt)
|
||||
|
||||
if mode == MODE_TEXT:
|
||||
if max_tag:
|
||||
raise ValueError(
|
||||
f"The prompt references @Audio{max_tag}, but reference mode is '{MODE_TEXT}'. "
|
||||
f"Switch to '{MODE_AUDIO}' and connect the reference clip(s)."
|
||||
)
|
||||
elif mode == MODE_AUDIO:
|
||||
if not audio_indices:
|
||||
raise ValueError(
|
||||
f"Reference mode '{MODE_AUDIO}' requires at least one reference_audio input "
|
||||
f"(or switch to '{MODE_TEXT}')."
|
||||
)
|
||||
if audio_indices != list(range(1, len(audio_indices) + 1)):
|
||||
raise ValueError(
|
||||
"Connect reference_audio inputs in order without gaps: reference_audio_1, then _2, then _3."
|
||||
)
|
||||
if max_tag > len(audio_indices):
|
||||
raise ValueError(
|
||||
f"The prompt references @Audio{max_tag}, but only {len(audio_indices)} "
|
||||
f"reference audio(s) are connected."
|
||||
)
|
||||
elif mode == MODE_IMAGE:
|
||||
if not has_image:
|
||||
raise ValueError(f"Reference mode '{MODE_IMAGE}' requires a reference_image input.")
|
||||
if max_tag:
|
||||
raise ValueError(
|
||||
f"@AudioN tags are not used in '{MODE_IMAGE}' mode; the prompt should contain "
|
||||
f"only the text to synthesize."
|
||||
)
|
||||
elif mode == MODE_SPEAKER:
|
||||
if not preset_voice or preset_voice not in SEED_AUDIO_VOICE_MAP:
|
||||
raise ValueError(f"Reference mode '{MODE_SPEAKER}' requires selecting a preset voice.")
|
||||
if max_tag > 1:
|
||||
raise ValueError(
|
||||
f"'{MODE_SPEAKER}' mode uses a single voice, so @Audio{max_tag} is out of range. "
|
||||
f"Remove the @AudioN tags — the whole prompt is read in the selected voice."
|
||||
)
|
||||
else:
|
||||
raise ValueError(f"Unknown reference mode: {mode!r}")
|
||||
|
||||
|
||||
class ByteDanceSeedAudioNode(IO.ComfyNode):
|
||||
|
||||
@classmethod
|
||||
def define_schema(cls) -> IO.Schema:
|
||||
return IO.Schema(
|
||||
node_id="ByteDanceSeedAudio",
|
||||
display_name="ByteDance Seed Audio 1.0",
|
||||
category="partner/audio/ByteDance",
|
||||
description=(
|
||||
"Generate speech, music, sound effects and multi-speaker dialogue from a single prompt "
|
||||
"with ByteDance Seed Audio 1.0. Describe the voice(s), emotion, ambience, background music "
|
||||
"and sound effects in the prompt, and include the lines to speak. Optionally pick a built-in "
|
||||
"preset voice, clone voices from up to 3 reference clips (tagged @Audio1-3 in the prompt), "
|
||||
"or derive a voice from a character image. Up to 2 minutes of audio per run."
|
||||
),
|
||||
inputs=[
|
||||
IO.String.Input(
|
||||
"text_prompt",
|
||||
multiline=True,
|
||||
default="",
|
||||
tooltip=(
|
||||
"Describe the voice(s), emotion, pacing, ambience, background music and sound "
|
||||
"effects, and include the lines to speak (name characters inline for dialogue). "
|
||||
"In 'audio reference' mode, refer to connected clips by order as @Audio1, @Audio2, "
|
||||
"@Audio3. Maximum 3000 characters."
|
||||
),
|
||||
),
|
||||
IO.DynamicCombo.Input(
|
||||
"reference_mode",
|
||||
options=[
|
||||
IO.DynamicCombo.Option(MODE_TEXT, []),
|
||||
IO.DynamicCombo.Option(
|
||||
MODE_AUDIO,
|
||||
[
|
||||
IO.Audio.Input(
|
||||
"reference_audio_1",
|
||||
optional=True,
|
||||
tooltip="Reference clip for voice cloning, tagged @Audio1 in the prompt. "
|
||||
"Up to 30s.",
|
||||
),
|
||||
IO.Audio.Input(
|
||||
"reference_audio_2",
|
||||
optional=True,
|
||||
tooltip="Reference clip tagged @Audio2 in the prompt. Up to 30s.",
|
||||
),
|
||||
IO.Audio.Input(
|
||||
"reference_audio_3",
|
||||
optional=True,
|
||||
tooltip="Reference clip tagged @Audio3 in the prompt. Up to 30s.",
|
||||
),
|
||||
],
|
||||
),
|
||||
IO.DynamicCombo.Option(
|
||||
MODE_IMAGE,
|
||||
[
|
||||
IO.Image.Input(
|
||||
"reference_image",
|
||||
optional=True,
|
||||
tooltip="A single character image; the model derives a voice from it. "
|
||||
"Cannot be combined with reference audio.",
|
||||
),
|
||||
],
|
||||
),
|
||||
IO.DynamicCombo.Option(
|
||||
MODE_SPEAKER,
|
||||
[
|
||||
IO.Combo.Input(
|
||||
"preset_voice",
|
||||
options=SEED_AUDIO_VOICE_OPTIONS,
|
||||
default=SEED_AUDIO_VOICE_OPTIONS[0],
|
||||
tooltip="A built-in TTS 2.0 voice that reads the prompt. No reference "
|
||||
"clip needed, and @AudioN tags are not used in this mode.",
|
||||
),
|
||||
],
|
||||
),
|
||||
],
|
||||
tooltip=(
|
||||
"How to condition the voice: 'text only' (describe everything in the prompt), "
|
||||
"'audio reference' (clone up to 3 voices, tagged @Audio1-3), 'image reference' "
|
||||
"(derive a voice from one character image), or 'preset voice' (pick a built-in "
|
||||
"named voice that reads the prompt)."
|
||||
),
|
||||
),
|
||||
IO.Combo.Input(
|
||||
"sample_rate",
|
||||
options=["8000", "16000", "24000", "32000", "44100", "48000"],
|
||||
default="24000",
|
||||
tooltip="Output sample rate in Hz.",
|
||||
),
|
||||
IO.Int.Input(
|
||||
"speech_rate",
|
||||
default=0,
|
||||
min=-50,
|
||||
max=100,
|
||||
tooltip="Speaking speed. 0 = normal, 100 = 2.0x, -50 = 0.5x.",
|
||||
),
|
||||
IO.Int.Input(
|
||||
"loudness_rate",
|
||||
default=0,
|
||||
min=-50,
|
||||
max=100,
|
||||
tooltip="Loudness. 0 = normal, 100 = 2.0x, -50 = 0.5x.",
|
||||
),
|
||||
IO.Int.Input(
|
||||
"pitch_rate",
|
||||
default=0,
|
||||
min=-12,
|
||||
max=12,
|
||||
tooltip="Pitch shift in semitones (-12 to 12).",
|
||||
),
|
||||
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.Audio.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": 0.2145, "format":{"suffix":"/minute","approximate":true}}""",
|
||||
),
|
||||
)
|
||||
|
||||
@classmethod
|
||||
async def execute(
|
||||
cls,
|
||||
text_prompt: str,
|
||||
reference_mode: dict,
|
||||
sample_rate: str,
|
||||
speech_rate: int,
|
||||
loudness_rate: int,
|
||||
pitch_rate: int,
|
||||
seed: int,
|
||||
) -> IO.NodeOutput:
|
||||
mode = reference_mode["reference_mode"]
|
||||
audio_indices = connected_audio_indices(reference_mode)
|
||||
image = reference_mode.get("reference_image")
|
||||
preset_voice = reference_mode.get("preset_voice")
|
||||
validate_seed_audio_inputs(text_prompt, mode, audio_indices, image is not None, preset_voice)
|
||||
|
||||
references: list[SeedAudioReference] | None = None
|
||||
if mode == MODE_AUDIO:
|
||||
references = []
|
||||
for i in audio_indices:
|
||||
clip = reference_mode[f"reference_audio_{i}"]
|
||||
validate_audio_duration(clip, max_duration=30.0)
|
||||
mp3_bytes = audio_input_to_mp3(clip).getvalue()
|
||||
references.append(SeedAudioReference(audio_data=base64.b64encode(mp3_bytes).decode("utf-8")))
|
||||
elif mode == MODE_IMAGE:
|
||||
image = upscale_image_tensor_to_min_pixels(image, 160_000)
|
||||
references = [SeedAudioReference(image_data=tensor_to_base64_string(image, mime_type="image/png"))]
|
||||
elif mode == MODE_SPEAKER:
|
||||
references = [SeedAudioReference(speaker=SEED_AUDIO_VOICE_MAP[preset_voice])]
|
||||
|
||||
response = await sync_op(
|
||||
cls,
|
||||
ApiEndpoint(path="/proxy/byteplus/api/v3/tts/create", method="POST"),
|
||||
response_model=SeedAudioResponse,
|
||||
data=SeedAudioRequest(
|
||||
text_prompt=text_prompt,
|
||||
references=references,
|
||||
audio_config=SeedAudioConfig(
|
||||
sample_rate=int(sample_rate),
|
||||
speech_rate=speech_rate,
|
||||
loudness_rate=loudness_rate,
|
||||
pitch_rate=pitch_rate,
|
||||
),
|
||||
),
|
||||
)
|
||||
if not response.audio:
|
||||
raise Exception(
|
||||
f"Seed Audio returned no audio (code={response.code}): {response.message}"
|
||||
)
|
||||
return IO.NodeOutput(audio_bytes_to_audio_input(base64.b64decode(response.audio)))
|
||||
|
||||
|
||||
class ByteDanceExtension(ComfyExtension):
|
||||
@override
|
||||
async def get_node_list(self) -> list[type[IO.ComfyNode]]:
|
||||
@ -2857,7 +2490,6 @@ class ByteDanceExtension(ComfyExtension):
|
||||
ByteDance2ReferenceNode,
|
||||
ByteDanceCreateImageAsset,
|
||||
ByteDanceCreateVideoAsset,
|
||||
ByteDanceSeedAudioNode,
|
||||
]
|
||||
|
||||
|
||||
|
||||
@ -13,7 +13,7 @@ import torch
|
||||
from typing_extensions import override
|
||||
|
||||
import folder_paths
|
||||
from comfy_api.latest import IO, ComfyExtension, Input, InputImpl, Types
|
||||
from comfy_api.latest import IO, ComfyExtension, Input, Types
|
||||
from comfy_api_nodes.apis.gemini import (
|
||||
GeminiContent,
|
||||
GeminiFileData,
|
||||
@ -37,7 +37,6 @@ 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,
|
||||
@ -46,7 +45,6 @@ from comfy_api_nodes.util import (
|
||||
upload_images_to_comfyapi,
|
||||
upload_video_to_comfyapi,
|
||||
validate_string,
|
||||
validate_video_duration,
|
||||
video_to_base64_string,
|
||||
)
|
||||
|
||||
@ -231,29 +229,10 @@ 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
|
||||
@ -270,27 +249,18 @@ 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 in ("gemini-3.1-flash-lite-preview", "gemini-3.1-flash-lite"):
|
||||
elif response.modelVersion == "gemini-3.1-flash-lite-preview":
|
||||
input_tokens_price = 0.25
|
||||
output_text_tokens_price = 1.50
|
||||
output_image_tokens_price = 0.0
|
||||
elif response.modelVersion in ("gemini-3-pro-image-preview", "gemini-3-pro-image"):
|
||||
elif response.modelVersion == "gemini-3-pro-image-preview":
|
||||
input_tokens_price = 2
|
||||
output_text_tokens_price = 12.0
|
||||
output_image_tokens_price = 120.0
|
||||
elif response.modelVersion in ("gemini-3.1-flash-image-preview", "gemini-3.1-flash-image"):
|
||||
elif response.modelVersion == "gemini-3.1-flash-image-preview":
|
||||
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
|
||||
@ -298,8 +268,6 @@ 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:
|
||||
@ -1334,7 +1302,7 @@ class GeminiNanoBanana2(IO.ComfyNode):
|
||||
)
|
||||
|
||||
|
||||
def _nano_banana_2_v2_model_inputs(resolutions: list[str]):
|
||||
def _nano_banana_2_v2_model_inputs():
|
||||
return [
|
||||
IO.Combo.Input(
|
||||
"aspect_ratio",
|
||||
@ -1361,8 +1329,8 @@ def _nano_banana_2_v2_model_inputs(resolutions: list[str]):
|
||||
),
|
||||
IO.Combo.Input(
|
||||
"resolution",
|
||||
options=resolutions,
|
||||
tooltip="Target output resolution.",
|
||||
options=["1K", "2K", "4K"],
|
||||
tooltip="Target output resolution. For 2K/4K the native Gemini upscaler is used.",
|
||||
),
|
||||
IO.Combo.Input(
|
||||
"thinking_level",
|
||||
@ -1408,11 +1376,7 @@ class GeminiNanoBanana2V2(IO.ComfyNode):
|
||||
options=[
|
||||
IO.DynamicCombo.Option(
|
||||
"Nano Banana 2 (Gemini 3.1 Flash Image)",
|
||||
_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"]),
|
||||
_nano_banana_2_v2_model_inputs(),
|
||||
),
|
||||
],
|
||||
),
|
||||
@ -1481,13 +1445,9 @@ class GeminiNanoBanana2V2(IO.ComfyNode):
|
||||
depends_on=IO.PriceBadgeDepends(widgets=["model", "model.resolution"]),
|
||||
expr="""
|
||||
(
|
||||
$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}}
|
||||
)
|
||||
$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}}
|
||||
)
|
||||
""",
|
||||
),
|
||||
@ -1508,8 +1468,6 @@ 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
|
||||
|
||||
@ -1559,149 +1517,6 @@ 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]]:
|
||||
@ -1712,7 +1527,6 @@ class GeminiExtension(ComfyExtension):
|
||||
GeminiImage2,
|
||||
GeminiNanoBanana2,
|
||||
GeminiNanoBanana2V2,
|
||||
GeminiVideoOmni,
|
||||
GeminiInputFiles,
|
||||
]
|
||||
|
||||
|
||||
@ -5,7 +5,9 @@ from PIL import Image
|
||||
import numpy as np
|
||||
import torch
|
||||
from comfy_api_nodes.apis.ideogram import (
|
||||
IdeogramGenerateRequest,
|
||||
IdeogramGenerateResponse,
|
||||
ImageRequest,
|
||||
IdeogramV3Request,
|
||||
IdeogramV3EditRequest,
|
||||
IdeogramV4Request,
|
||||
@ -19,6 +21,101 @@ from comfy_api_nodes.util import (
|
||||
validate_string,
|
||||
)
|
||||
|
||||
V1_V1_RES_MAP = {
|
||||
"Auto":"AUTO",
|
||||
"512 x 1536":"RESOLUTION_512_1536",
|
||||
"576 x 1408":"RESOLUTION_576_1408",
|
||||
"576 x 1472":"RESOLUTION_576_1472",
|
||||
"576 x 1536":"RESOLUTION_576_1536",
|
||||
"640 x 1024":"RESOLUTION_640_1024",
|
||||
"640 x 1344":"RESOLUTION_640_1344",
|
||||
"640 x 1408":"RESOLUTION_640_1408",
|
||||
"640 x 1472":"RESOLUTION_640_1472",
|
||||
"640 x 1536":"RESOLUTION_640_1536",
|
||||
"704 x 1152":"RESOLUTION_704_1152",
|
||||
"704 x 1216":"RESOLUTION_704_1216",
|
||||
"704 x 1280":"RESOLUTION_704_1280",
|
||||
"704 x 1344":"RESOLUTION_704_1344",
|
||||
"704 x 1408":"RESOLUTION_704_1408",
|
||||
"704 x 1472":"RESOLUTION_704_1472",
|
||||
"720 x 1280":"RESOLUTION_720_1280",
|
||||
"736 x 1312":"RESOLUTION_736_1312",
|
||||
"768 x 1024":"RESOLUTION_768_1024",
|
||||
"768 x 1088":"RESOLUTION_768_1088",
|
||||
"768 x 1152":"RESOLUTION_768_1152",
|
||||
"768 x 1216":"RESOLUTION_768_1216",
|
||||
"768 x 1232":"RESOLUTION_768_1232",
|
||||
"768 x 1280":"RESOLUTION_768_1280",
|
||||
"768 x 1344":"RESOLUTION_768_1344",
|
||||
"832 x 960":"RESOLUTION_832_960",
|
||||
"832 x 1024":"RESOLUTION_832_1024",
|
||||
"832 x 1088":"RESOLUTION_832_1088",
|
||||
"832 x 1152":"RESOLUTION_832_1152",
|
||||
"832 x 1216":"RESOLUTION_832_1216",
|
||||
"832 x 1248":"RESOLUTION_832_1248",
|
||||
"864 x 1152":"RESOLUTION_864_1152",
|
||||
"896 x 960":"RESOLUTION_896_960",
|
||||
"896 x 1024":"RESOLUTION_896_1024",
|
||||
"896 x 1088":"RESOLUTION_896_1088",
|
||||
"896 x 1120":"RESOLUTION_896_1120",
|
||||
"896 x 1152":"RESOLUTION_896_1152",
|
||||
"960 x 832":"RESOLUTION_960_832",
|
||||
"960 x 896":"RESOLUTION_960_896",
|
||||
"960 x 1024":"RESOLUTION_960_1024",
|
||||
"960 x 1088":"RESOLUTION_960_1088",
|
||||
"1024 x 640":"RESOLUTION_1024_640",
|
||||
"1024 x 768":"RESOLUTION_1024_768",
|
||||
"1024 x 832":"RESOLUTION_1024_832",
|
||||
"1024 x 896":"RESOLUTION_1024_896",
|
||||
"1024 x 960":"RESOLUTION_1024_960",
|
||||
"1024 x 1024":"RESOLUTION_1024_1024",
|
||||
"1088 x 768":"RESOLUTION_1088_768",
|
||||
"1088 x 832":"RESOLUTION_1088_832",
|
||||
"1088 x 896":"RESOLUTION_1088_896",
|
||||
"1088 x 960":"RESOLUTION_1088_960",
|
||||
"1120 x 896":"RESOLUTION_1120_896",
|
||||
"1152 x 704":"RESOLUTION_1152_704",
|
||||
"1152 x 768":"RESOLUTION_1152_768",
|
||||
"1152 x 832":"RESOLUTION_1152_832",
|
||||
"1152 x 864":"RESOLUTION_1152_864",
|
||||
"1152 x 896":"RESOLUTION_1152_896",
|
||||
"1216 x 704":"RESOLUTION_1216_704",
|
||||
"1216 x 768":"RESOLUTION_1216_768",
|
||||
"1216 x 832":"RESOLUTION_1216_832",
|
||||
"1232 x 768":"RESOLUTION_1232_768",
|
||||
"1248 x 832":"RESOLUTION_1248_832",
|
||||
"1280 x 704":"RESOLUTION_1280_704",
|
||||
"1280 x 720":"RESOLUTION_1280_720",
|
||||
"1280 x 768":"RESOLUTION_1280_768",
|
||||
"1280 x 800":"RESOLUTION_1280_800",
|
||||
"1312 x 736":"RESOLUTION_1312_736",
|
||||
"1344 x 640":"RESOLUTION_1344_640",
|
||||
"1344 x 704":"RESOLUTION_1344_704",
|
||||
"1344 x 768":"RESOLUTION_1344_768",
|
||||
"1408 x 576":"RESOLUTION_1408_576",
|
||||
"1408 x 640":"RESOLUTION_1408_640",
|
||||
"1408 x 704":"RESOLUTION_1408_704",
|
||||
"1472 x 576":"RESOLUTION_1472_576",
|
||||
"1472 x 640":"RESOLUTION_1472_640",
|
||||
"1472 x 704":"RESOLUTION_1472_704",
|
||||
"1536 x 512":"RESOLUTION_1536_512",
|
||||
"1536 x 576":"RESOLUTION_1536_576",
|
||||
"1536 x 640":"RESOLUTION_1536_640",
|
||||
}
|
||||
|
||||
V1_V2_RATIO_MAP = {
|
||||
"1:1":"ASPECT_1_1",
|
||||
"4:3":"ASPECT_4_3",
|
||||
"3:4":"ASPECT_3_4",
|
||||
"16:9":"ASPECT_16_9",
|
||||
"9:16":"ASPECT_9_16",
|
||||
"2:1":"ASPECT_2_1",
|
||||
"1:2":"ASPECT_1_2",
|
||||
"3:2":"ASPECT_3_2",
|
||||
"2:3":"ASPECT_2_3",
|
||||
"4:5":"ASPECT_4_5",
|
||||
"5:4":"ASPECT_5_4",
|
||||
}
|
||||
|
||||
V3_RATIO_MAP = {
|
||||
"1:3":"1x3",
|
||||
@ -132,6 +229,298 @@ async def download_and_process_images(image_urls):
|
||||
return stacked_tensors
|
||||
|
||||
|
||||
class IdeogramV1(IO.ComfyNode):
|
||||
|
||||
@classmethod
|
||||
def define_schema(cls):
|
||||
return IO.Schema(
|
||||
node_id="IdeogramV1",
|
||||
display_name="Ideogram V1",
|
||||
category="partner/image/Ideogram",
|
||||
description="Generates images using the Ideogram V1 model.",
|
||||
inputs=[
|
||||
IO.String.Input(
|
||||
"prompt",
|
||||
multiline=True,
|
||||
default="",
|
||||
tooltip="Prompt for the image generation",
|
||||
),
|
||||
IO.Boolean.Input(
|
||||
"turbo",
|
||||
default=False,
|
||||
tooltip="Whether to use turbo mode (faster generation, potentially lower quality)",
|
||||
),
|
||||
IO.Combo.Input(
|
||||
"aspect_ratio",
|
||||
options=list(V1_V2_RATIO_MAP.keys()),
|
||||
default="1:1",
|
||||
tooltip="The aspect ratio for image generation.",
|
||||
optional=True,
|
||||
),
|
||||
IO.Combo.Input(
|
||||
"magic_prompt_option",
|
||||
options=["AUTO", "ON", "OFF"],
|
||||
default="AUTO",
|
||||
tooltip="Determine if MagicPrompt should be used in generation",
|
||||
optional=True,
|
||||
advanced=True,
|
||||
),
|
||||
IO.Int.Input(
|
||||
"seed",
|
||||
default=0,
|
||||
min=0,
|
||||
max=2147483647,
|
||||
step=1,
|
||||
control_after_generate=True,
|
||||
display_mode=IO.NumberDisplay.number,
|
||||
optional=True,
|
||||
),
|
||||
IO.String.Input(
|
||||
"negative_prompt",
|
||||
multiline=True,
|
||||
default="",
|
||||
tooltip="Description of what to exclude from the image",
|
||||
optional=True,
|
||||
),
|
||||
IO.Int.Input(
|
||||
"num_images",
|
||||
default=1,
|
||||
min=1,
|
||||
max=8,
|
||||
step=1,
|
||||
display_mode=IO.NumberDisplay.number,
|
||||
optional=True,
|
||||
),
|
||||
],
|
||||
outputs=[
|
||||
IO.Image.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(
|
||||
depends_on=IO.PriceBadgeDepends(widgets=["num_images", "turbo"]),
|
||||
expr="""
|
||||
(
|
||||
$n := widgets.num_images;
|
||||
$base := (widgets.turbo = true) ? 0.0286 : 0.0858;
|
||||
{"type":"usd","usd": $round($base * $n, 2)}
|
||||
)
|
||||
""",
|
||||
),
|
||||
)
|
||||
|
||||
@classmethod
|
||||
async def execute(
|
||||
cls,
|
||||
prompt,
|
||||
turbo=False,
|
||||
aspect_ratio="1:1",
|
||||
magic_prompt_option="AUTO",
|
||||
seed=0,
|
||||
negative_prompt="",
|
||||
num_images=1,
|
||||
):
|
||||
# Determine the model based on turbo setting
|
||||
aspect_ratio = V1_V2_RATIO_MAP.get(aspect_ratio, None)
|
||||
model = "V_1_TURBO" if turbo else "V_1"
|
||||
|
||||
response = await sync_op(
|
||||
cls,
|
||||
ApiEndpoint(path="/proxy/ideogram/generate", method="POST"),
|
||||
response_model=IdeogramGenerateResponse,
|
||||
data=IdeogramGenerateRequest(
|
||||
image_request=ImageRequest(
|
||||
prompt=prompt,
|
||||
model=model,
|
||||
num_images=num_images,
|
||||
seed=seed,
|
||||
aspect_ratio=aspect_ratio if aspect_ratio != "ASPECT_1_1" else None,
|
||||
magic_prompt_option=(magic_prompt_option if magic_prompt_option != "AUTO" else None),
|
||||
negative_prompt=negative_prompt if negative_prompt else None,
|
||||
)
|
||||
),
|
||||
max_retries=1,
|
||||
)
|
||||
|
||||
if not response.data or len(response.data) == 0:
|
||||
raise Exception("No images were generated in the response")
|
||||
|
||||
image_urls = [image_data.url for image_data in response.data if image_data.url]
|
||||
if not image_urls:
|
||||
raise Exception("No image URLs were generated in the response")
|
||||
return IO.NodeOutput(await download_and_process_images(image_urls))
|
||||
|
||||
|
||||
class IdeogramV2(IO.ComfyNode):
|
||||
|
||||
@classmethod
|
||||
def define_schema(cls):
|
||||
return IO.Schema(
|
||||
node_id="IdeogramV2",
|
||||
display_name="Ideogram V2",
|
||||
category="partner/image/Ideogram",
|
||||
description="Generates images using the Ideogram V2 model.",
|
||||
inputs=[
|
||||
IO.String.Input(
|
||||
"prompt",
|
||||
multiline=True,
|
||||
default="",
|
||||
tooltip="Prompt for the image generation",
|
||||
),
|
||||
IO.Boolean.Input(
|
||||
"turbo",
|
||||
default=False,
|
||||
tooltip="Whether to use turbo mode (faster generation, potentially lower quality)",
|
||||
),
|
||||
IO.Combo.Input(
|
||||
"aspect_ratio",
|
||||
options=list(V1_V2_RATIO_MAP.keys()),
|
||||
default="1:1",
|
||||
tooltip="The aspect ratio for image generation. Ignored if resolution is not set to AUTO.",
|
||||
optional=True,
|
||||
),
|
||||
IO.Combo.Input(
|
||||
"resolution",
|
||||
options=list(V1_V1_RES_MAP.keys()),
|
||||
default="Auto",
|
||||
tooltip="The resolution for image generation. "
|
||||
"If not set to AUTO, this overrides the aspect_ratio setting.",
|
||||
optional=True,
|
||||
),
|
||||
IO.Combo.Input(
|
||||
"magic_prompt_option",
|
||||
options=["AUTO", "ON", "OFF"],
|
||||
default="AUTO",
|
||||
tooltip="Determine if MagicPrompt should be used in generation",
|
||||
optional=True,
|
||||
advanced=True,
|
||||
),
|
||||
IO.Int.Input(
|
||||
"seed",
|
||||
default=0,
|
||||
min=0,
|
||||
max=2147483647,
|
||||
step=1,
|
||||
control_after_generate=True,
|
||||
display_mode=IO.NumberDisplay.number,
|
||||
optional=True,
|
||||
),
|
||||
IO.Combo.Input(
|
||||
"style_type",
|
||||
options=["AUTO", "GENERAL", "REALISTIC", "DESIGN", "RENDER_3D", "ANIME"],
|
||||
default="NONE",
|
||||
tooltip="Style type for generation (V2 only)",
|
||||
optional=True,
|
||||
advanced=True,
|
||||
),
|
||||
IO.String.Input(
|
||||
"negative_prompt",
|
||||
multiline=True,
|
||||
default="",
|
||||
tooltip="Description of what to exclude from the image",
|
||||
optional=True,
|
||||
),
|
||||
IO.Int.Input(
|
||||
"num_images",
|
||||
default=1,
|
||||
min=1,
|
||||
max=8,
|
||||
step=1,
|
||||
display_mode=IO.NumberDisplay.number,
|
||||
optional=True,
|
||||
),
|
||||
#"color_palette": (
|
||||
# IO.STRING,
|
||||
# {
|
||||
# "multiline": False,
|
||||
# "default": "",
|
||||
# "tooltip": "Color palette preset name or hex colors with weights",
|
||||
# },
|
||||
#),
|
||||
],
|
||||
outputs=[
|
||||
IO.Image.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(
|
||||
depends_on=IO.PriceBadgeDepends(widgets=["num_images", "turbo"]),
|
||||
expr="""
|
||||
(
|
||||
$n := widgets.num_images;
|
||||
$base := (widgets.turbo = true) ? 0.0715 : 0.1144;
|
||||
{"type":"usd","usd": $round($base * $n, 2)}
|
||||
)
|
||||
""",
|
||||
),
|
||||
)
|
||||
|
||||
@classmethod
|
||||
async def execute(
|
||||
cls,
|
||||
prompt,
|
||||
turbo=False,
|
||||
aspect_ratio="1:1",
|
||||
resolution="Auto",
|
||||
magic_prompt_option="AUTO",
|
||||
seed=0,
|
||||
style_type="NONE",
|
||||
negative_prompt="",
|
||||
num_images=1,
|
||||
color_palette="",
|
||||
):
|
||||
aspect_ratio = V1_V2_RATIO_MAP.get(aspect_ratio, None)
|
||||
resolution = V1_V1_RES_MAP.get(resolution, None)
|
||||
# Determine the model based on turbo setting
|
||||
model = "V_2_TURBO" if turbo else "V_2"
|
||||
|
||||
# Handle resolution vs aspect_ratio logic
|
||||
# If resolution is not AUTO, it overrides aspect_ratio
|
||||
final_resolution = None
|
||||
final_aspect_ratio = None
|
||||
|
||||
if resolution != "AUTO":
|
||||
final_resolution = resolution
|
||||
else:
|
||||
final_aspect_ratio = aspect_ratio if aspect_ratio != "ASPECT_1_1" else None
|
||||
|
||||
response = await sync_op(
|
||||
cls,
|
||||
endpoint=ApiEndpoint(path="/proxy/ideogram/generate", method="POST"),
|
||||
response_model=IdeogramGenerateResponse,
|
||||
data=IdeogramGenerateRequest(
|
||||
image_request=ImageRequest(
|
||||
prompt=prompt,
|
||||
model=model,
|
||||
num_images=num_images,
|
||||
seed=seed,
|
||||
aspect_ratio=final_aspect_ratio,
|
||||
resolution=final_resolution,
|
||||
magic_prompt_option=(magic_prompt_option if magic_prompt_option != "AUTO" else None),
|
||||
style_type=style_type if style_type != "NONE" else None,
|
||||
negative_prompt=negative_prompt if negative_prompt else None,
|
||||
color_palette=color_palette if color_palette else None,
|
||||
)
|
||||
),
|
||||
max_retries=1,
|
||||
)
|
||||
if not response.data or len(response.data) == 0:
|
||||
raise Exception("No images were generated in the response")
|
||||
|
||||
image_urls = [image_data.url for image_data in response.data if image_data.url]
|
||||
if not image_urls:
|
||||
raise Exception("No image URLs were generated in the response")
|
||||
return IO.NodeOutput(await download_and_process_images(image_urls))
|
||||
|
||||
|
||||
class IdeogramV3(IO.ComfyNode):
|
||||
|
||||
@classmethod
|
||||
@ -528,6 +917,8 @@ class IdeogramExtension(ComfyExtension):
|
||||
@override
|
||||
async def get_node_list(self) -> list[type[IO.ComfyNode]]:
|
||||
return [
|
||||
IdeogramV1,
|
||||
IdeogramV2,
|
||||
IdeogramV3,
|
||||
IdeogramV4,
|
||||
]
|
||||
|
||||
932
comfy_api_nodes/nodes_stability.py
Normal file
932
comfy_api_nodes/nodes_stability.py
Normal file
@ -0,0 +1,932 @@
|
||||
from inspect import cleandoc
|
||||
from typing import Optional
|
||||
from typing_extensions import override
|
||||
|
||||
from comfy_api.latest import ComfyExtension, Input, IO
|
||||
from comfy_api_nodes.apis.stability import (
|
||||
StabilityUpscaleConservativeRequest,
|
||||
StabilityUpscaleCreativeRequest,
|
||||
StabilityAsyncResponse,
|
||||
StabilityResultsGetResponse,
|
||||
StabilityStable3_5Request,
|
||||
StabilityStableUltraRequest,
|
||||
StabilityStableUltraResponse,
|
||||
StabilityAspectRatio,
|
||||
Stability_SD3_5_Model,
|
||||
Stability_SD3_5_GenerationMode,
|
||||
get_stability_style_presets,
|
||||
StabilityTextToAudioRequest,
|
||||
StabilityAudioToAudioRequest,
|
||||
StabilityAudioInpaintRequest,
|
||||
StabilityAudioResponse,
|
||||
)
|
||||
from comfy_api_nodes.util import (
|
||||
validate_audio_duration,
|
||||
validate_string,
|
||||
audio_input_to_mp3,
|
||||
bytesio_to_image_tensor,
|
||||
tensor_to_bytesio,
|
||||
audio_bytes_to_audio_input,
|
||||
sync_op,
|
||||
poll_op,
|
||||
ApiEndpoint,
|
||||
)
|
||||
|
||||
import torch
|
||||
import base64
|
||||
from io import BytesIO
|
||||
from enum import Enum
|
||||
|
||||
|
||||
class StabilityPollStatus(str, Enum):
|
||||
finished = "finished"
|
||||
in_progress = "in_progress"
|
||||
failed = "failed"
|
||||
|
||||
|
||||
def get_async_dummy_status(x: StabilityResultsGetResponse):
|
||||
if x.name is not None or x.errors is not None:
|
||||
return StabilityPollStatus.failed
|
||||
elif x.finish_reason is not None:
|
||||
return StabilityPollStatus.finished
|
||||
return StabilityPollStatus.in_progress
|
||||
|
||||
|
||||
class StabilityStableImageUltraNode(IO.ComfyNode):
|
||||
"""
|
||||
Generates images synchronously based on prompt and resolution.
|
||||
"""
|
||||
|
||||
@classmethod
|
||||
def define_schema(cls):
|
||||
return IO.Schema(
|
||||
node_id="StabilityStableImageUltraNode",
|
||||
display_name="Stability AI Stable Image Ultra",
|
||||
category="partner/image/Stability AI",
|
||||
description=cleandoc(cls.__doc__ or ""),
|
||||
inputs=[
|
||||
IO.String.Input(
|
||||
"prompt",
|
||||
multiline=True,
|
||||
default="",
|
||||
tooltip="What you wish to see in the output image. A strong, descriptive prompt that clearly defines" +
|
||||
"elements, colors, and subjects will lead to better results. " +
|
||||
"To control the weight of a given word use the format `(word:weight)`," +
|
||||
"where `word` is the word you'd like to control the weight of and `weight`" +
|
||||
"is a value between 0 and 1. For example: `The sky was a crisp (blue:0.3) and (green:0.8)`" +
|
||||
"would convey a sky that was blue and green, but more green than blue.",
|
||||
),
|
||||
IO.Combo.Input(
|
||||
"aspect_ratio",
|
||||
options=StabilityAspectRatio,
|
||||
default=StabilityAspectRatio.ratio_1_1,
|
||||
tooltip="Aspect ratio of generated image.",
|
||||
),
|
||||
IO.Combo.Input(
|
||||
"style_preset",
|
||||
options=get_stability_style_presets(),
|
||||
tooltip="Optional desired style of generated image.",
|
||||
advanced=True,
|
||||
),
|
||||
IO.Int.Input(
|
||||
"seed",
|
||||
default=0,
|
||||
min=0,
|
||||
max=4294967294,
|
||||
step=1,
|
||||
display_mode=IO.NumberDisplay.number,
|
||||
control_after_generate=True,
|
||||
tooltip="The random seed used for creating the noise.",
|
||||
),
|
||||
IO.Image.Input(
|
||||
"image",
|
||||
optional=True,
|
||||
),
|
||||
IO.String.Input(
|
||||
"negative_prompt",
|
||||
default="",
|
||||
tooltip="A blurb of text describing what you do not wish to see in the output image. This is an advanced feature.",
|
||||
force_input=True,
|
||||
optional=True,
|
||||
advanced=True,
|
||||
),
|
||||
IO.Float.Input(
|
||||
"image_denoise",
|
||||
default=0.5,
|
||||
min=0.0,
|
||||
max=1.0,
|
||||
step=0.01,
|
||||
tooltip="Denoise of input image; 0.0 yields image identical to input, 1.0 is as if no image was provided at all.",
|
||||
optional=True,
|
||||
),
|
||||
],
|
||||
outputs=[
|
||||
IO.Image.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":0.08}""",
|
||||
),
|
||||
)
|
||||
|
||||
@classmethod
|
||||
async def execute(
|
||||
cls,
|
||||
prompt: str,
|
||||
aspect_ratio: str,
|
||||
style_preset: str,
|
||||
seed: int,
|
||||
image: Optional[torch.Tensor] = None,
|
||||
negative_prompt: str = "",
|
||||
image_denoise: Optional[float] = 0.5,
|
||||
) -> IO.NodeOutput:
|
||||
validate_string(prompt, strip_whitespace=False)
|
||||
# prepare image binary if image present
|
||||
image_binary = None
|
||||
if image is not None:
|
||||
image_binary = tensor_to_bytesio(image, total_pixels=1504*1504).read()
|
||||
else:
|
||||
image_denoise = None
|
||||
|
||||
if not negative_prompt:
|
||||
negative_prompt = None
|
||||
if style_preset == "None":
|
||||
style_preset = None
|
||||
|
||||
files = {
|
||||
"image": image_binary
|
||||
}
|
||||
|
||||
response_api = await sync_op(
|
||||
cls,
|
||||
ApiEndpoint(path="/proxy/stability/v2beta/stable-image/generate/ultra", method="POST"),
|
||||
response_model=StabilityStableUltraResponse,
|
||||
data=StabilityStableUltraRequest(
|
||||
prompt=prompt,
|
||||
negative_prompt=negative_prompt,
|
||||
aspect_ratio=aspect_ratio,
|
||||
seed=seed,
|
||||
strength=image_denoise,
|
||||
style_preset=style_preset,
|
||||
),
|
||||
files=files,
|
||||
content_type="multipart/form-data",
|
||||
)
|
||||
|
||||
if response_api.finish_reason != "SUCCESS":
|
||||
raise Exception(f"Stable Image Ultra generation failed: {response_api.finish_reason}.")
|
||||
|
||||
image_data = base64.b64decode(response_api.image)
|
||||
returned_image = bytesio_to_image_tensor(BytesIO(image_data))
|
||||
|
||||
return IO.NodeOutput(returned_image)
|
||||
|
||||
|
||||
class StabilityStableImageSD_3_5Node(IO.ComfyNode):
|
||||
"""
|
||||
Generates images synchronously based on prompt and resolution.
|
||||
"""
|
||||
|
||||
@classmethod
|
||||
def define_schema(cls):
|
||||
return IO.Schema(
|
||||
node_id="StabilityStableImageSD_3_5Node",
|
||||
display_name="Stability AI Stable Diffusion 3.5 Image",
|
||||
category="partner/image/Stability AI",
|
||||
description=cleandoc(cls.__doc__ or ""),
|
||||
inputs=[
|
||||
IO.String.Input(
|
||||
"prompt",
|
||||
multiline=True,
|
||||
default="",
|
||||
tooltip="What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results.",
|
||||
),
|
||||
IO.Combo.Input(
|
||||
"model",
|
||||
options=Stability_SD3_5_Model,
|
||||
),
|
||||
IO.Combo.Input(
|
||||
"aspect_ratio",
|
||||
options=StabilityAspectRatio,
|
||||
default=StabilityAspectRatio.ratio_1_1,
|
||||
tooltip="Aspect ratio of generated image.",
|
||||
),
|
||||
IO.Combo.Input(
|
||||
"style_preset",
|
||||
options=get_stability_style_presets(),
|
||||
tooltip="Optional desired style of generated image.",
|
||||
advanced=True,
|
||||
),
|
||||
IO.Float.Input(
|
||||
"cfg_scale",
|
||||
default=4.0,
|
||||
min=1.0,
|
||||
max=10.0,
|
||||
step=0.1,
|
||||
tooltip="How strictly the diffusion process adheres to the prompt text (higher values keep your image closer to your prompt)",
|
||||
),
|
||||
IO.Int.Input(
|
||||
"seed",
|
||||
default=0,
|
||||
min=0,
|
||||
max=4294967294,
|
||||
step=1,
|
||||
display_mode=IO.NumberDisplay.number,
|
||||
control_after_generate=True,
|
||||
tooltip="The random seed used for creating the noise.",
|
||||
),
|
||||
IO.Image.Input(
|
||||
"image",
|
||||
optional=True,
|
||||
),
|
||||
IO.String.Input(
|
||||
"negative_prompt",
|
||||
default="",
|
||||
tooltip="Keywords of what you do not wish to see in the output image. This is an advanced feature.",
|
||||
force_input=True,
|
||||
optional=True,
|
||||
advanced=True,
|
||||
),
|
||||
IO.Float.Input(
|
||||
"image_denoise",
|
||||
default=0.5,
|
||||
min=0.0,
|
||||
max=1.0,
|
||||
step=0.01,
|
||||
tooltip="Denoise of input image; 0.0 yields image identical to input, 1.0 is as if no image was provided at all.",
|
||||
optional=True,
|
||||
),
|
||||
],
|
||||
outputs=[
|
||||
IO.Image.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(
|
||||
depends_on=IO.PriceBadgeDepends(widgets=["model"]),
|
||||
expr="""
|
||||
(
|
||||
$contains(widgets.model,"large")
|
||||
? {"type":"usd","usd":0.065}
|
||||
: {"type":"usd","usd":0.035}
|
||||
)
|
||||
""",
|
||||
),
|
||||
)
|
||||
|
||||
@classmethod
|
||||
async def execute(
|
||||
cls,
|
||||
model: str,
|
||||
prompt: str,
|
||||
aspect_ratio: str,
|
||||
style_preset: str,
|
||||
seed: int,
|
||||
cfg_scale: float,
|
||||
image: Optional[torch.Tensor] = None,
|
||||
negative_prompt: str = "",
|
||||
image_denoise: Optional[float] = 0.5,
|
||||
) -> IO.NodeOutput:
|
||||
validate_string(prompt, strip_whitespace=False)
|
||||
# prepare image binary if image present
|
||||
image_binary = None
|
||||
mode = Stability_SD3_5_GenerationMode.text_to_image
|
||||
if image is not None:
|
||||
image_binary = tensor_to_bytesio(image, total_pixels=1504*1504).read()
|
||||
mode = Stability_SD3_5_GenerationMode.image_to_image
|
||||
aspect_ratio = None
|
||||
else:
|
||||
image_denoise = None
|
||||
|
||||
if not negative_prompt:
|
||||
negative_prompt = None
|
||||
if style_preset == "None":
|
||||
style_preset = None
|
||||
|
||||
files = {
|
||||
"image": image_binary
|
||||
}
|
||||
|
||||
response_api = await sync_op(
|
||||
cls,
|
||||
ApiEndpoint(path="/proxy/stability/v2beta/stable-image/generate/sd3", method="POST"),
|
||||
response_model=StabilityStableUltraResponse,
|
||||
data=StabilityStable3_5Request(
|
||||
prompt=prompt,
|
||||
negative_prompt=negative_prompt,
|
||||
aspect_ratio=aspect_ratio,
|
||||
seed=seed,
|
||||
strength=image_denoise,
|
||||
style_preset=style_preset,
|
||||
cfg_scale=cfg_scale,
|
||||
model=model,
|
||||
mode=mode,
|
||||
),
|
||||
files=files,
|
||||
content_type="multipart/form-data",
|
||||
)
|
||||
|
||||
if response_api.finish_reason != "SUCCESS":
|
||||
raise Exception(f"Stable Diffusion 3.5 Image generation failed: {response_api.finish_reason}.")
|
||||
|
||||
image_data = base64.b64decode(response_api.image)
|
||||
returned_image = bytesio_to_image_tensor(BytesIO(image_data))
|
||||
|
||||
return IO.NodeOutput(returned_image)
|
||||
|
||||
|
||||
class StabilityUpscaleConservativeNode(IO.ComfyNode):
|
||||
"""
|
||||
Upscale image with minimal alterations to 4K resolution.
|
||||
"""
|
||||
|
||||
@classmethod
|
||||
def define_schema(cls):
|
||||
return IO.Schema(
|
||||
node_id="StabilityUpscaleConservativeNode",
|
||||
display_name="Stability AI Upscale Conservative",
|
||||
category="partner/image/Stability AI",
|
||||
description=cleandoc(cls.__doc__ or ""),
|
||||
inputs=[
|
||||
IO.Image.Input("image"),
|
||||
IO.String.Input(
|
||||
"prompt",
|
||||
multiline=True,
|
||||
default="",
|
||||
tooltip="What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results.",
|
||||
),
|
||||
IO.Float.Input(
|
||||
"creativity",
|
||||
default=0.35,
|
||||
min=0.2,
|
||||
max=0.5,
|
||||
step=0.01,
|
||||
tooltip="Controls the likelihood of creating additional details not heavily conditioned by the init image.",
|
||||
),
|
||||
IO.Int.Input(
|
||||
"seed",
|
||||
default=0,
|
||||
min=0,
|
||||
max=4294967294,
|
||||
step=1,
|
||||
display_mode=IO.NumberDisplay.number,
|
||||
control_after_generate=True,
|
||||
tooltip="The random seed used for creating the noise.",
|
||||
),
|
||||
IO.String.Input(
|
||||
"negative_prompt",
|
||||
default="",
|
||||
tooltip="Keywords of what you do not wish to see in the output image. This is an advanced feature.",
|
||||
force_input=True,
|
||||
optional=True,
|
||||
advanced=True,
|
||||
),
|
||||
],
|
||||
outputs=[
|
||||
IO.Image.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":0.4}""",
|
||||
),
|
||||
)
|
||||
|
||||
@classmethod
|
||||
async def execute(
|
||||
cls,
|
||||
image: torch.Tensor,
|
||||
prompt: str,
|
||||
creativity: float,
|
||||
seed: int,
|
||||
negative_prompt: str = "",
|
||||
) -> IO.NodeOutput:
|
||||
validate_string(prompt, strip_whitespace=False)
|
||||
image_binary = tensor_to_bytesio(image, total_pixels=1024*1024).read()
|
||||
|
||||
if not negative_prompt:
|
||||
negative_prompt = None
|
||||
|
||||
files = {
|
||||
"image": image_binary
|
||||
}
|
||||
|
||||
response_api = await sync_op(
|
||||
cls,
|
||||
ApiEndpoint(path="/proxy/stability/v2beta/stable-image/upscale/conservative", method="POST"),
|
||||
response_model=StabilityStableUltraResponse,
|
||||
data=StabilityUpscaleConservativeRequest(
|
||||
prompt=prompt,
|
||||
negative_prompt=negative_prompt,
|
||||
creativity=round(creativity,2),
|
||||
seed=seed,
|
||||
),
|
||||
files=files,
|
||||
content_type="multipart/form-data",
|
||||
)
|
||||
|
||||
if response_api.finish_reason != "SUCCESS":
|
||||
raise Exception(f"Stability Upscale Conservative generation failed: {response_api.finish_reason}.")
|
||||
|
||||
image_data = base64.b64decode(response_api.image)
|
||||
returned_image = bytesio_to_image_tensor(BytesIO(image_data))
|
||||
|
||||
return IO.NodeOutput(returned_image)
|
||||
|
||||
|
||||
class StabilityUpscaleCreativeNode(IO.ComfyNode):
|
||||
"""
|
||||
Upscale image with minimal alterations to 4K resolution.
|
||||
"""
|
||||
|
||||
@classmethod
|
||||
def define_schema(cls):
|
||||
return IO.Schema(
|
||||
node_id="StabilityUpscaleCreativeNode",
|
||||
display_name="Stability AI Upscale Creative",
|
||||
category="partner/image/Stability AI",
|
||||
description=cleandoc(cls.__doc__ or ""),
|
||||
inputs=[
|
||||
IO.Image.Input("image"),
|
||||
IO.String.Input(
|
||||
"prompt",
|
||||
multiline=True,
|
||||
default="",
|
||||
tooltip="What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results.",
|
||||
),
|
||||
IO.Float.Input(
|
||||
"creativity",
|
||||
default=0.3,
|
||||
min=0.1,
|
||||
max=0.5,
|
||||
step=0.01,
|
||||
tooltip="Controls the likelihood of creating additional details not heavily conditioned by the init image.",
|
||||
),
|
||||
IO.Combo.Input(
|
||||
"style_preset",
|
||||
options=get_stability_style_presets(),
|
||||
tooltip="Optional desired style of generated image.",
|
||||
advanced=True,
|
||||
),
|
||||
IO.Int.Input(
|
||||
"seed",
|
||||
default=0,
|
||||
min=0,
|
||||
max=4294967294,
|
||||
step=1,
|
||||
display_mode=IO.NumberDisplay.number,
|
||||
control_after_generate=True,
|
||||
tooltip="The random seed used for creating the noise.",
|
||||
),
|
||||
IO.String.Input(
|
||||
"negative_prompt",
|
||||
default="",
|
||||
tooltip="Keywords of what you do not wish to see in the output image. This is an advanced feature.",
|
||||
force_input=True,
|
||||
optional=True,
|
||||
advanced=True,
|
||||
),
|
||||
],
|
||||
outputs=[
|
||||
IO.Image.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":0.6}""",
|
||||
),
|
||||
)
|
||||
|
||||
@classmethod
|
||||
async def execute(
|
||||
cls,
|
||||
image: torch.Tensor,
|
||||
prompt: str,
|
||||
creativity: float,
|
||||
style_preset: str,
|
||||
seed: int,
|
||||
negative_prompt: str = "",
|
||||
) -> IO.NodeOutput:
|
||||
validate_string(prompt, strip_whitespace=False)
|
||||
image_binary = tensor_to_bytesio(image, total_pixels=1024*1024).read()
|
||||
|
||||
if not negative_prompt:
|
||||
negative_prompt = None
|
||||
if style_preset == "None":
|
||||
style_preset = None
|
||||
|
||||
files = {
|
||||
"image": image_binary
|
||||
}
|
||||
|
||||
response_api = await sync_op(
|
||||
cls,
|
||||
ApiEndpoint(path="/proxy/stability/v2beta/stable-image/upscale/creative", method="POST"),
|
||||
response_model=StabilityAsyncResponse,
|
||||
data=StabilityUpscaleCreativeRequest(
|
||||
prompt=prompt,
|
||||
negative_prompt=negative_prompt,
|
||||
creativity=round(creativity,2),
|
||||
style_preset=style_preset,
|
||||
seed=seed,
|
||||
),
|
||||
files=files,
|
||||
content_type="multipart/form-data",
|
||||
)
|
||||
|
||||
response_poll = await poll_op(
|
||||
cls,
|
||||
ApiEndpoint(path=f"/proxy/stability/v2beta/results/{response_api.id}"),
|
||||
response_model=StabilityResultsGetResponse,
|
||||
poll_interval=3,
|
||||
status_extractor=lambda x: get_async_dummy_status(x),
|
||||
)
|
||||
|
||||
if response_poll.finish_reason != "SUCCESS":
|
||||
raise Exception(f"Stability Upscale Creative generation failed: {response_poll.finish_reason}.")
|
||||
|
||||
image_data = base64.b64decode(response_poll.result)
|
||||
returned_image = bytesio_to_image_tensor(BytesIO(image_data))
|
||||
|
||||
return IO.NodeOutput(returned_image)
|
||||
|
||||
|
||||
class StabilityUpscaleFastNode(IO.ComfyNode):
|
||||
"""
|
||||
Quickly upscales an image via Stability API call to 4x its original size; intended for upscaling low-quality/compressed images.
|
||||
"""
|
||||
|
||||
@classmethod
|
||||
def define_schema(cls):
|
||||
return IO.Schema(
|
||||
node_id="StabilityUpscaleFastNode",
|
||||
display_name="Stability AI Upscale Fast",
|
||||
category="partner/image/Stability AI",
|
||||
description=cleandoc(cls.__doc__ or ""),
|
||||
inputs=[
|
||||
IO.Image.Input("image"),
|
||||
],
|
||||
outputs=[
|
||||
IO.Image.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":0.02}""",
|
||||
),
|
||||
)
|
||||
|
||||
@classmethod
|
||||
async def execute(cls, image: torch.Tensor) -> IO.NodeOutput:
|
||||
image_binary = tensor_to_bytesio(image, total_pixels=4096*4096).read()
|
||||
|
||||
files = {
|
||||
"image": image_binary
|
||||
}
|
||||
|
||||
response_api = await sync_op(
|
||||
cls,
|
||||
ApiEndpoint(path="/proxy/stability/v2beta/stable-image/upscale/fast", method="POST"),
|
||||
response_model=StabilityStableUltraResponse,
|
||||
files=files,
|
||||
content_type="multipart/form-data",
|
||||
)
|
||||
|
||||
if response_api.finish_reason != "SUCCESS":
|
||||
raise Exception(f"Stability Upscale Fast failed: {response_api.finish_reason}.")
|
||||
|
||||
image_data = base64.b64decode(response_api.image)
|
||||
returned_image = bytesio_to_image_tensor(BytesIO(image_data))
|
||||
|
||||
return IO.NodeOutput(returned_image)
|
||||
|
||||
|
||||
class StabilityTextToAudio(IO.ComfyNode):
|
||||
"""Generates high-quality music and sound effects from text descriptions."""
|
||||
|
||||
@classmethod
|
||||
def define_schema(cls):
|
||||
return IO.Schema(
|
||||
node_id="StabilityTextToAudio",
|
||||
display_name="Stability AI Text To Audio",
|
||||
category="partner/audio/Stability AI",
|
||||
essentials_category="Audio",
|
||||
description=cleandoc(cls.__doc__ or ""),
|
||||
inputs=[
|
||||
IO.Combo.Input(
|
||||
"model",
|
||||
options=["stable-audio-2.5"],
|
||||
),
|
||||
IO.String.Input("prompt", multiline=True, default=""),
|
||||
IO.Int.Input(
|
||||
"duration",
|
||||
default=190,
|
||||
min=1,
|
||||
max=190,
|
||||
step=1,
|
||||
tooltip="Controls the duration in seconds of the generated audio.",
|
||||
optional=True,
|
||||
),
|
||||
IO.Int.Input(
|
||||
"seed",
|
||||
default=0,
|
||||
min=0,
|
||||
max=4294967294,
|
||||
step=1,
|
||||
display_mode=IO.NumberDisplay.number,
|
||||
control_after_generate=True,
|
||||
tooltip="The random seed used for generation.",
|
||||
optional=True,
|
||||
),
|
||||
IO.Int.Input(
|
||||
"steps",
|
||||
default=8,
|
||||
min=4,
|
||||
max=8,
|
||||
step=1,
|
||||
tooltip="Controls the number of sampling steps.",
|
||||
optional=True,
|
||||
advanced=True,
|
||||
),
|
||||
],
|
||||
outputs=[
|
||||
IO.Audio.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":0.2}""",
|
||||
),
|
||||
)
|
||||
|
||||
@classmethod
|
||||
async def execute(cls, model: str, prompt: str, duration: int, seed: int, steps: int) -> IO.NodeOutput:
|
||||
validate_string(prompt, max_length=10000)
|
||||
payload = StabilityTextToAudioRequest(prompt=prompt, model=model, duration=duration, seed=seed, steps=steps)
|
||||
response_api = await sync_op(
|
||||
cls,
|
||||
ApiEndpoint(path="/proxy/stability/v2beta/audio/stable-audio-2/text-to-audio", method="POST"),
|
||||
response_model=StabilityAudioResponse,
|
||||
data=payload,
|
||||
content_type="multipart/form-data",
|
||||
)
|
||||
if not response_api.audio:
|
||||
raise ValueError("No audio file was received in response.")
|
||||
return IO.NodeOutput(audio_bytes_to_audio_input(base64.b64decode(response_api.audio)))
|
||||
|
||||
|
||||
class StabilityAudioToAudio(IO.ComfyNode):
|
||||
"""Transforms existing audio samples into new high-quality compositions using text instructions."""
|
||||
|
||||
@classmethod
|
||||
def define_schema(cls):
|
||||
return IO.Schema(
|
||||
node_id="StabilityAudioToAudio",
|
||||
display_name="Stability AI Audio To Audio",
|
||||
category="partner/audio/Stability AI",
|
||||
description=cleandoc(cls.__doc__ or ""),
|
||||
inputs=[
|
||||
IO.Combo.Input(
|
||||
"model",
|
||||
options=["stable-audio-2.5"],
|
||||
),
|
||||
IO.String.Input("prompt", multiline=True, default=""),
|
||||
IO.Audio.Input("audio", tooltip="Audio must be between 6 and 190 seconds long."),
|
||||
IO.Int.Input(
|
||||
"duration",
|
||||
default=190,
|
||||
min=1,
|
||||
max=190,
|
||||
step=1,
|
||||
tooltip="Controls the duration in seconds of the generated audio.",
|
||||
optional=True,
|
||||
),
|
||||
IO.Int.Input(
|
||||
"seed",
|
||||
default=0,
|
||||
min=0,
|
||||
max=4294967294,
|
||||
step=1,
|
||||
display_mode=IO.NumberDisplay.number,
|
||||
control_after_generate=True,
|
||||
tooltip="The random seed used for generation.",
|
||||
optional=True,
|
||||
),
|
||||
IO.Int.Input(
|
||||
"steps",
|
||||
default=8,
|
||||
min=4,
|
||||
max=8,
|
||||
step=1,
|
||||
tooltip="Controls the number of sampling steps.",
|
||||
optional=True,
|
||||
advanced=True,
|
||||
),
|
||||
IO.Float.Input(
|
||||
"strength",
|
||||
default=1,
|
||||
min=0.01,
|
||||
max=1.0,
|
||||
step=0.01,
|
||||
display_mode=IO.NumberDisplay.slider,
|
||||
tooltip="Parameter controls how much influence the audio parameter has on the generated audio.",
|
||||
optional=True,
|
||||
),
|
||||
],
|
||||
outputs=[
|
||||
IO.Audio.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":0.2}""",
|
||||
),
|
||||
)
|
||||
|
||||
@classmethod
|
||||
async def execute(
|
||||
cls, model: str, prompt: str, audio: Input.Audio, duration: int, seed: int, steps: int, strength: float
|
||||
) -> IO.NodeOutput:
|
||||
validate_string(prompt, max_length=10000)
|
||||
validate_audio_duration(audio, 6, 190)
|
||||
payload = StabilityAudioToAudioRequest(
|
||||
prompt=prompt, model=model, duration=duration, seed=seed, steps=steps, strength=strength
|
||||
)
|
||||
response_api = await sync_op(
|
||||
cls,
|
||||
ApiEndpoint(path="/proxy/stability/v2beta/audio/stable-audio-2/audio-to-audio", method="POST"),
|
||||
response_model=StabilityAudioResponse,
|
||||
data=payload,
|
||||
content_type="multipart/form-data",
|
||||
files={"audio": audio_input_to_mp3(audio)},
|
||||
)
|
||||
if not response_api.audio:
|
||||
raise ValueError("No audio file was received in response.")
|
||||
return IO.NodeOutput(audio_bytes_to_audio_input(base64.b64decode(response_api.audio)))
|
||||
|
||||
|
||||
class StabilityAudioInpaint(IO.ComfyNode):
|
||||
"""Transforms part of existing audio sample using text instructions."""
|
||||
|
||||
@classmethod
|
||||
def define_schema(cls):
|
||||
return IO.Schema(
|
||||
node_id="StabilityAudioInpaint",
|
||||
display_name="Stability AI Audio Inpaint",
|
||||
category="partner/audio/Stability AI",
|
||||
description=cleandoc(cls.__doc__ or ""),
|
||||
inputs=[
|
||||
IO.Combo.Input(
|
||||
"model",
|
||||
options=["stable-audio-2.5"],
|
||||
),
|
||||
IO.String.Input("prompt", multiline=True, default=""),
|
||||
IO.Audio.Input("audio", tooltip="Audio must be between 6 and 190 seconds long."),
|
||||
IO.Int.Input(
|
||||
"duration",
|
||||
default=190,
|
||||
min=1,
|
||||
max=190,
|
||||
step=1,
|
||||
tooltip="Controls the duration in seconds of the generated audio.",
|
||||
optional=True,
|
||||
),
|
||||
IO.Int.Input(
|
||||
"seed",
|
||||
default=0,
|
||||
min=0,
|
||||
max=4294967294,
|
||||
step=1,
|
||||
display_mode=IO.NumberDisplay.number,
|
||||
control_after_generate=True,
|
||||
tooltip="The random seed used for generation.",
|
||||
optional=True,
|
||||
),
|
||||
IO.Int.Input(
|
||||
"steps",
|
||||
default=8,
|
||||
min=4,
|
||||
max=8,
|
||||
step=1,
|
||||
tooltip="Controls the number of sampling steps.",
|
||||
optional=True,
|
||||
advanced=True,
|
||||
),
|
||||
IO.Int.Input(
|
||||
"mask_start",
|
||||
default=30,
|
||||
min=0,
|
||||
max=190,
|
||||
step=1,
|
||||
optional=True,
|
||||
advanced=True,
|
||||
),
|
||||
IO.Int.Input(
|
||||
"mask_end",
|
||||
default=190,
|
||||
min=0,
|
||||
max=190,
|
||||
step=1,
|
||||
optional=True,
|
||||
advanced=True,
|
||||
),
|
||||
],
|
||||
outputs=[
|
||||
IO.Audio.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":0.2}""",
|
||||
),
|
||||
)
|
||||
|
||||
@classmethod
|
||||
async def execute(
|
||||
cls,
|
||||
model: str,
|
||||
prompt: str,
|
||||
audio: Input.Audio,
|
||||
duration: int,
|
||||
seed: int,
|
||||
steps: int,
|
||||
mask_start: int,
|
||||
mask_end: int,
|
||||
) -> IO.NodeOutput:
|
||||
validate_string(prompt, max_length=10000)
|
||||
if mask_end <= mask_start:
|
||||
raise ValueError(f"Value of mask_end({mask_end}) should be greater then mask_start({mask_start})")
|
||||
validate_audio_duration(audio, 6, 190)
|
||||
|
||||
payload = StabilityAudioInpaintRequest(
|
||||
prompt=prompt,
|
||||
model=model,
|
||||
duration=duration,
|
||||
seed=seed,
|
||||
steps=steps,
|
||||
mask_start=mask_start,
|
||||
mask_end=mask_end,
|
||||
)
|
||||
response_api = await sync_op(
|
||||
cls,
|
||||
endpoint=ApiEndpoint(path="/proxy/stability/v2beta/audio/stable-audio-2/inpaint", method="POST"),
|
||||
response_model=StabilityAudioResponse,
|
||||
data=payload,
|
||||
content_type="multipart/form-data",
|
||||
files={"audio": audio_input_to_mp3(audio)},
|
||||
)
|
||||
if not response_api.audio:
|
||||
raise ValueError("No audio file was received in response.")
|
||||
return IO.NodeOutput(audio_bytes_to_audio_input(base64.b64decode(response_api.audio)))
|
||||
|
||||
|
||||
class StabilityExtension(ComfyExtension):
|
||||
@override
|
||||
async def get_node_list(self) -> list[type[IO.ComfyNode]]:
|
||||
return [
|
||||
StabilityStableImageUltraNode,
|
||||
StabilityStableImageSD_3_5Node,
|
||||
StabilityUpscaleConservativeNode,
|
||||
StabilityUpscaleCreativeNode,
|
||||
StabilityUpscaleFastNode,
|
||||
StabilityTextToAudio,
|
||||
StabilityAudioToAudio,
|
||||
StabilityAudioInpaint,
|
||||
]
|
||||
|
||||
|
||||
async def comfy_entrypoint() -> StabilityExtension:
|
||||
return StabilityExtension()
|
||||
@ -26,7 +26,6 @@ from .conversions import (
|
||||
text_filepath_to_base64_string,
|
||||
text_filepath_to_data_uri,
|
||||
trim_video,
|
||||
upscale_image_tensor_to_min_pixels,
|
||||
upscale_video_to_min_pixels,
|
||||
video_to_base64_string,
|
||||
)
|
||||
@ -100,7 +99,6 @@ __all__ = [
|
||||
"text_filepath_to_base64_string",
|
||||
"text_filepath_to_data_uri",
|
||||
"trim_video",
|
||||
"upscale_image_tensor_to_min_pixels",
|
||||
"upscale_video_to_min_pixels",
|
||||
"video_to_base64_string",
|
||||
# Validation utilities
|
||||
|
||||
@ -448,15 +448,6 @@ def _compute_upscale_dims(src_w: int, src_h: int, total_pixels: int) -> tuple[in
|
||||
return new_w, new_h
|
||||
|
||||
|
||||
def upscale_image_tensor_to_min_pixels(image: torch.Tensor, total_pixels: int) -> torch.Tensor:
|
||||
samples = image.movedim(-1, 1)
|
||||
dims = _compute_upscale_dims(samples.shape[3], samples.shape[2], int(total_pixels))
|
||||
if dims is None:
|
||||
return image
|
||||
new_w, new_h = dims
|
||||
return common_upscale(samples, new_w, new_h, "lanczos", "disabled").movedim(1, -1)
|
||||
|
||||
|
||||
def upscale_video_to_min_pixels(video: Input.Video, min_pixels: int) -> Input.Video:
|
||||
"""Upscale a video to meet at least ``min_pixels`` (w * h), preserving aspect ratio.
|
||||
|
||||
|
||||
@ -9,7 +9,6 @@ from typing import Any
|
||||
import folder_paths
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
_SENSITIVE_HEADERS = {"authorization", "x-api-key"}
|
||||
|
||||
|
||||
def get_log_directory():
|
||||
@ -74,10 +73,6 @@ def _format_data_for_logging(data: Any) -> str:
|
||||
return str(data)
|
||||
|
||||
|
||||
def _redact_headers(headers: dict) -> dict:
|
||||
return {k: ("***" if k.lower() in _SENSITIVE_HEADERS else v) for k, v in headers.items()}
|
||||
|
||||
|
||||
def log_request_response(
|
||||
operation_id: str,
|
||||
request_method: str,
|
||||
@ -106,7 +101,7 @@ def log_request_response(
|
||||
log_content.append(f"Method: {request_method}")
|
||||
log_content.append(f"URL: {request_url}")
|
||||
if request_headers:
|
||||
log_content.append(f"Headers:\n{_format_data_for_logging(_redact_headers(request_headers))}")
|
||||
log_content.append(f"Headers:\n{_format_data_for_logging(request_headers)}")
|
||||
if request_params:
|
||||
log_content.append(f"Params:\n{_format_data_for_logging(request_params)}")
|
||||
if request_data is not None:
|
||||
|
||||
@ -158,14 +158,7 @@ async def upload_video_to_comfyapi(
|
||||
|
||||
# Convert VideoInput to BytesIO using specified container/codec
|
||||
video_bytes_io = BytesIO()
|
||||
try:
|
||||
video.save_to(video_bytes_io, format=container, codec=codec)
|
||||
except Exception as e:
|
||||
raise ValueError(
|
||||
f"Could not convert the input video to {container.value.upper()} for upload; "
|
||||
f"the file may be corrupted or use an unsupported codec. "
|
||||
f"Try re-exporting it as MP4 (H.264). Original error: {e}"
|
||||
) from e
|
||||
video.save_to(video_bytes_io, format=container, codec=codec)
|
||||
video_bytes_io.seek(0)
|
||||
|
||||
return await upload_file_to_comfyapi(cls, video_bytes_io, filename, upload_mime_type, wait_label)
|
||||
|
||||
@ -3,6 +3,7 @@ from typing import Type, Literal
|
||||
import nodes
|
||||
import asyncio
|
||||
import inspect
|
||||
import traceback
|
||||
from comfy_execution.graph_utils import is_link, ExecutionBlocker
|
||||
from comfy.comfy_types.node_typing import ComfyNodeABC, InputTypeDict, InputTypeOptions
|
||||
|
||||
@ -263,7 +264,25 @@ class ExecutionList(TopologicalSort):
|
||||
}
|
||||
return None, error_details, ex
|
||||
|
||||
self.staged_node_id = self.ux_friendly_pick_node(available)
|
||||
try:
|
||||
self.staged_node_id = self.ux_friendly_pick_node(available)
|
||||
except Exception as ex:
|
||||
# Backstop: the ordering heuristics in ux_friendly_pick_node are
|
||||
# defensive, but should anything else there fail, surface it as an
|
||||
# execution error instead of letting it kill the prompt worker
|
||||
# thread. Blame an available node (best effort).
|
||||
blamed_node = self.dynprompt.get_display_node_id(available[0])
|
||||
exception_type = type(ex).__qualname__
|
||||
if type(ex).__module__ != "builtins":
|
||||
exception_type = type(ex).__module__ + "." + exception_type
|
||||
error_details = {
|
||||
"node_id": blamed_node,
|
||||
"exception_message": str(ex),
|
||||
"exception_type": exception_type,
|
||||
"traceback": traceback.format_tb(ex.__traceback__),
|
||||
"current_inputs": []
|
||||
}
|
||||
return None, error_details, ex
|
||||
return self.staged_node_id, None, None
|
||||
|
||||
def ux_friendly_pick_node(self, node_list):
|
||||
@ -271,19 +290,28 @@ class ExecutionList(TopologicalSort):
|
||||
# Technically this has no effect on the overall length of execution, but it feels better as a user
|
||||
# for a PreviewImage to display a result as soon as it can
|
||||
# Some other heuristics could probably be used here to improve the UX further.
|
||||
# These node-ordering heuristics only affect *order*, never correctness.
|
||||
# A malformed node (e.g. a FUNCTION typo, or a node whose schema-derived
|
||||
# attributes raise) must not crash scheduling: failing a heuristic just
|
||||
# means "not prioritized". The node then proceeds to normal execution,
|
||||
# where the real error is raised and reported against the correct node.
|
||||
def is_output(node_id):
|
||||
class_type = self.dynprompt.get_node(node_id)["class_type"]
|
||||
class_def = nodes.NODE_CLASS_MAPPINGS[class_type]
|
||||
if hasattr(class_def, 'OUTPUT_NODE') and class_def.OUTPUT_NODE == True:
|
||||
return True
|
||||
return False
|
||||
try:
|
||||
return hasattr(class_def, 'OUTPUT_NODE') and class_def.OUTPUT_NODE == True
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
# If an available node is async, do that first.
|
||||
# This will execute the asynchronous function earlier, reducing the overall time.
|
||||
def is_async(node_id):
|
||||
class_type = self.dynprompt.get_node(node_id)["class_type"]
|
||||
class_def = nodes.NODE_CLASS_MAPPINGS[class_type]
|
||||
return inspect.iscoroutinefunction(getattr(class_def, class_def.FUNCTION))
|
||||
try:
|
||||
return inspect.iscoroutinefunction(getattr(class_def, class_def.FUNCTION))
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
for node_id in node_list:
|
||||
if is_output(node_id) or is_async(node_id):
|
||||
|
||||
@ -8,8 +8,7 @@ class CLIPTextEncodeControlnet(io.ComfyNode):
|
||||
def define_schema(cls) -> io.Schema:
|
||||
return io.Schema(
|
||||
node_id="CLIPTextEncodeControlnet",
|
||||
display_name="CLIP Text Encode (Controlnet)",
|
||||
category="model/conditioning",
|
||||
category="experimental/conditioning",
|
||||
inputs=[
|
||||
io.Clip.Input("clip"),
|
||||
io.Conditioning.Input("conditioning"),
|
||||
@ -36,12 +35,11 @@ class T5TokenizerOptions(io.ComfyNode):
|
||||
def define_schema(cls) -> io.Schema:
|
||||
return io.Schema(
|
||||
node_id="T5TokenizerOptions",
|
||||
display_name="T5 Tokenizer Options",
|
||||
category="model/conditioning",
|
||||
category="experimental/conditioning",
|
||||
inputs=[
|
||||
io.Clip.Input("clip"),
|
||||
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),
|
||||
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),
|
||||
],
|
||||
outputs=[io.Clip.Output()],
|
||||
is_experimental=True,
|
||||
|
||||
@ -1070,7 +1070,7 @@ class AddNoise(io.ComfyNode):
|
||||
def define_schema(cls):
|
||||
return io.Schema(
|
||||
node_id="AddNoise",
|
||||
category="model/sampling/noise",
|
||||
category="experimental/custom_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="model/sampling/sigmas",
|
||||
category="experimental/custom_sampling",
|
||||
is_experimental=True,
|
||||
inputs=[
|
||||
io.String.Input("sigmas", default="1, 0.5", multiline=False)
|
||||
|
||||
@ -1,68 +1,85 @@
|
||||
import os
|
||||
import sys
|
||||
import re
|
||||
import ctypes
|
||||
import logging
|
||||
import ctypes.util
|
||||
import importlib.util
|
||||
from typing import TypedDict
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
|
||||
import nodes
|
||||
import comfy_angle
|
||||
from comfy_api.latest import ComfyExtension, io, ui
|
||||
from typing_extensions import override
|
||||
from utils.install_util import get_missing_requirements_message
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _preload_angle():
|
||||
egl_path = comfy_angle.get_egl_path()
|
||||
gles_path = comfy_angle.get_glesv2_path()
|
||||
def _check_opengl_availability():
|
||||
"""Early check for OpenGL availability. Raises RuntimeError if unlikely to work."""
|
||||
logger.debug("_check_opengl_availability: starting")
|
||||
missing = []
|
||||
|
||||
if sys.platform == "win32":
|
||||
angle_dir = comfy_angle.get_lib_dir()
|
||||
os.add_dll_directory(angle_dir)
|
||||
os.environ["PATH"] = angle_dir + os.pathsep + os.environ.get("PATH", "")
|
||||
# Check Python packages (using find_spec to avoid importing)
|
||||
logger.debug("_check_opengl_availability: checking for glfw package")
|
||||
if importlib.util.find_spec("glfw") is None:
|
||||
missing.append("glfw")
|
||||
|
||||
mode = 0 if sys.platform == "win32" else ctypes.RTLD_GLOBAL
|
||||
ctypes.CDLL(str(egl_path), mode=mode)
|
||||
ctypes.CDLL(str(gles_path), mode=mode)
|
||||
logger.debug("_check_opengl_availability: checking for OpenGL package")
|
||||
if importlib.util.find_spec("OpenGL") is None:
|
||||
missing.append("PyOpenGL")
|
||||
|
||||
if missing:
|
||||
raise RuntimeError(
|
||||
f"OpenGL dependencies not available.\n{get_missing_requirements_message()}\n"
|
||||
)
|
||||
|
||||
# On Linux without display, check if headless backends are available
|
||||
logger.debug(f"_check_opengl_availability: platform={sys.platform}")
|
||||
if sys.platform.startswith("linux"):
|
||||
has_display = os.environ.get("DISPLAY") or os.environ.get("WAYLAND_DISPLAY")
|
||||
logger.debug(f"_check_opengl_availability: has_display={bool(has_display)}")
|
||||
if not has_display:
|
||||
# Check for EGL or OSMesa libraries
|
||||
logger.debug("_check_opengl_availability: checking for EGL library")
|
||||
has_egl = ctypes.util.find_library("EGL")
|
||||
logger.debug("_check_opengl_availability: checking for OSMesa library")
|
||||
has_osmesa = ctypes.util.find_library("OSMesa")
|
||||
|
||||
# Error disabled for CI as it fails this check
|
||||
# if not has_egl and not has_osmesa:
|
||||
# raise RuntimeError(
|
||||
# "GLSL Shader node: No display and no headless backend (EGL/OSMesa) found.\n"
|
||||
# "See error below for installation instructions."
|
||||
# )
|
||||
logger.debug(f"Headless mode: EGL={'yes' if has_egl else 'no'}, OSMesa={'yes' if has_osmesa else 'no'}")
|
||||
|
||||
logger.debug("_check_opengl_availability: completed")
|
||||
|
||||
|
||||
# Pre-load ANGLE *before* any PyOpenGL import so that the EGL platform
|
||||
# plugin picks up ANGLE's libEGL / libGLESv2 instead of system libs.
|
||||
_preload_angle()
|
||||
os.environ.setdefault("PYOPENGL_PLATFORM", "egl")
|
||||
# Run early check at import time
|
||||
logger.debug("nodes_glsl: running _check_opengl_availability at import time")
|
||||
_check_opengl_availability()
|
||||
|
||||
# OpenGL modules - initialized lazily when context is created
|
||||
gl = None
|
||||
glfw = None
|
||||
EGL = None
|
||||
|
||||
|
||||
import OpenGL
|
||||
OpenGL.USE_ACCELERATE = False
|
||||
def _import_opengl():
|
||||
"""Import OpenGL module. Called after context is created."""
|
||||
global gl
|
||||
if gl is None:
|
||||
logger.debug("_import_opengl: importing OpenGL.GL")
|
||||
import OpenGL.GL as _gl
|
||||
gl = _gl
|
||||
logger.debug("_import_opengl: import completed")
|
||||
return gl
|
||||
|
||||
|
||||
def _patch_find_library():
|
||||
"""PyOpenGL's EGL platform looks for 'EGL' and 'GLESv2' by short name
|
||||
via ctypes.util.find_library, but ANGLE ships as 'libEGL' and
|
||||
'libGLESv2'. Patch find_library to return the full ANGLE paths so
|
||||
PyOpenGL loads the same libraries we pre-loaded."""
|
||||
if sys.platform == "linux":
|
||||
return
|
||||
import ctypes.util
|
||||
_orig = ctypes.util.find_library
|
||||
def _patched(name):
|
||||
if name == 'EGL':
|
||||
return comfy_angle.get_egl_path()
|
||||
if name == 'GLESv2':
|
||||
return comfy_angle.get_glesv2_path()
|
||||
return _orig(name)
|
||||
ctypes.util.find_library = _patched
|
||||
|
||||
|
||||
_patch_find_library()
|
||||
|
||||
from OpenGL import EGL
|
||||
from OpenGL import GLES3 as gl
|
||||
|
||||
class SizeModeInput(TypedDict):
|
||||
size_mode: str
|
||||
width: int
|
||||
@ -85,7 +102,7 @@ MAX_OUTPUTS = 4 # fragColor0-3 (MRT)
|
||||
# (-1,-1)---(3,-1)
|
||||
#
|
||||
# v_texCoord is computed from clip space: * 0.5 + 0.5 maps (-1,1) -> (0,1)
|
||||
VERTEX_SHADER = """#version 300 es
|
||||
VERTEX_SHADER = """#version 330 core
|
||||
out vec2 v_texCoord;
|
||||
void main() {
|
||||
vec2 verts[3] = vec2[](vec2(-1, -1), vec2(3, -1), vec2(-1, 3));
|
||||
@ -109,99 +126,14 @@ void main() {
|
||||
"""
|
||||
|
||||
|
||||
|
||||
def _egl_attribs(*values):
|
||||
"""Build an EGL_NONE-terminated EGLint attribute array."""
|
||||
vals = list(values) + [EGL.EGL_NONE]
|
||||
return (ctypes.c_int32 * len(vals))(*vals)
|
||||
|
||||
|
||||
# EGL platform extension constants
|
||||
EGL_PLATFORM_ANGLE_ANGLE = 0x3202
|
||||
EGL_PLATFORM_ANGLE_TYPE_ANGLE = 0x3203
|
||||
EGL_PLATFORM_ANGLE_TYPE_VULKAN_ANGLE = 0x3450
|
||||
EGL_MESA_PLATFORM_SURFACELESS = 0x31DD
|
||||
|
||||
|
||||
_eglGetPlatformDisplayEXT = None
|
||||
|
||||
def _get_egl_platform_display_ext(platform, native_display, attribs):
|
||||
"""Call eglGetPlatformDisplayEXT via ctypes (extension, not in PyOpenGL)."""
|
||||
global _eglGetPlatformDisplayEXT
|
||||
if _eglGetPlatformDisplayEXT is None:
|
||||
from OpenGL import platform as _plat
|
||||
egl_lib = _plat.PLATFORM.EGL
|
||||
_get_proc = egl_lib.eglGetProcAddress
|
||||
_get_proc.restype = ctypes.c_void_p
|
||||
_get_proc.argtypes = [ctypes.c_char_p]
|
||||
ptr = _get_proc(b"eglGetPlatformDisplayEXT")
|
||||
if not ptr:
|
||||
return None
|
||||
func_type = ctypes.CFUNCTYPE(ctypes.c_void_p, ctypes.c_uint32, ctypes.c_void_p, ctypes.c_void_p)
|
||||
_eglGetPlatformDisplayEXT = func_type(ptr)
|
||||
|
||||
raw = _eglGetPlatformDisplayEXT(platform, native_display, attribs)
|
||||
if not raw:
|
||||
return None
|
||||
return ctypes.cast(raw, EGL.EGLDisplay)
|
||||
|
||||
|
||||
def _get_egl_display():
|
||||
"""Get an EGL display, trying the default first then ANGLE's Vulkan
|
||||
platform for headless environments without a display server."""
|
||||
failures = []
|
||||
|
||||
# Try the default display first (works when X11/Wayland is available)
|
||||
display = EGL.eglGetDisplay(EGL.EGL_DEFAULT_DISPLAY)
|
||||
if display:
|
||||
major, minor = ctypes.c_int32(0), ctypes.c_int32(0)
|
||||
try:
|
||||
if EGL.eglInitialize(display, ctypes.byref(major), ctypes.byref(minor)):
|
||||
return display, major.value, minor.value
|
||||
except Exception as e:
|
||||
failures.append(f"default: {e}")
|
||||
|
||||
logger.info("Default EGL display unavailable, trying headless fallbacks")
|
||||
|
||||
# Headless fallback strategies, tried in order:
|
||||
headless_strategies = [
|
||||
("surfaceless", EGL_MESA_PLATFORM_SURFACELESS, None, None),
|
||||
("ANGLE Vulkan", EGL_PLATFORM_ANGLE_ANGLE, None,
|
||||
_egl_attribs(EGL_PLATFORM_ANGLE_TYPE_ANGLE, EGL_PLATFORM_ANGLE_TYPE_VULKAN_ANGLE)),
|
||||
]
|
||||
|
||||
for name, platform, native_display, attribs in headless_strategies:
|
||||
display = _get_egl_platform_display_ext(platform, native_display, attribs)
|
||||
if not display:
|
||||
failures.append(f"{name}: eglGetPlatformDisplayEXT returned no display")
|
||||
continue
|
||||
major, minor = ctypes.c_int32(0), ctypes.c_int32(0)
|
||||
try:
|
||||
if EGL.eglInitialize(display, ctypes.byref(major), ctypes.byref(minor)):
|
||||
logger.info(f"Using EGL {name} platform (headless)")
|
||||
return display, major.value, minor.value
|
||||
failures.append(f"{name}: eglInitialize returned false")
|
||||
except Exception as e:
|
||||
failures.append(f"{name}: {e}")
|
||||
continue
|
||||
|
||||
details = "\n".join(f" - {f}" for f in failures)
|
||||
raise RuntimeError(
|
||||
"Failed to initialize EGL display.\n"
|
||||
"No display server and no headless EGL platform available.\n"
|
||||
f"Tried:\n{details}\n"
|
||||
"Ensure GPU drivers are installed or set DISPLAY for a virtual framebuffer."
|
||||
)
|
||||
|
||||
|
||||
def _gl_str(name):
|
||||
"""Get an OpenGL string parameter."""
|
||||
v = gl.glGetString(name)
|
||||
if not v:
|
||||
return "Unknown"
|
||||
if isinstance(v, bytes):
|
||||
return v.decode(errors="replace")
|
||||
return ctypes.string_at(v).decode(errors="replace")
|
||||
def _convert_es_to_desktop(source: str) -> str:
|
||||
"""Convert GLSL ES (WebGL) shader source to desktop GLSL 330 core."""
|
||||
# Remove any existing #version directive
|
||||
source = re.sub(r"#version\s+\d+(\s+es)?\s*\n?", "", source, flags=re.IGNORECASE)
|
||||
# Remove precision qualifiers (not needed in desktop GLSL)
|
||||
source = re.sub(r"precision\s+(lowp|mediump|highp)\s+\w+\s*;\s*\n?", "", source)
|
||||
# Prepend desktop GLSL version
|
||||
return "#version 330 core\n" + source
|
||||
|
||||
|
||||
def _detect_output_count(source: str) -> int:
|
||||
@ -227,8 +159,163 @@ def _detect_pass_count(source: str) -> int:
|
||||
return 1
|
||||
|
||||
|
||||
def _init_glfw():
|
||||
"""Initialize GLFW. Returns (window, glfw_module). Raises RuntimeError on failure."""
|
||||
logger.debug("_init_glfw: starting")
|
||||
# On macOS, glfw.init() must be called from main thread or it hangs forever
|
||||
if sys.platform == "darwin":
|
||||
logger.debug("_init_glfw: skipping on macOS")
|
||||
raise RuntimeError("GLFW backend not supported on macOS")
|
||||
|
||||
logger.debug("_init_glfw: importing glfw module")
|
||||
import glfw as _glfw
|
||||
|
||||
logger.debug("_init_glfw: calling glfw.init()")
|
||||
if not _glfw.init():
|
||||
raise RuntimeError("glfw.init() failed")
|
||||
|
||||
try:
|
||||
logger.debug("_init_glfw: setting window hints")
|
||||
_glfw.window_hint(_glfw.VISIBLE, _glfw.FALSE)
|
||||
_glfw.window_hint(_glfw.CONTEXT_VERSION_MAJOR, 3)
|
||||
_glfw.window_hint(_glfw.CONTEXT_VERSION_MINOR, 3)
|
||||
_glfw.window_hint(_glfw.OPENGL_PROFILE, _glfw.OPENGL_CORE_PROFILE)
|
||||
|
||||
logger.debug("_init_glfw: calling create_window()")
|
||||
window = _glfw.create_window(64, 64, "ComfyUI GLSL", None, None)
|
||||
if not window:
|
||||
raise RuntimeError("glfw.create_window() failed")
|
||||
|
||||
logger.debug("_init_glfw: calling make_context_current()")
|
||||
_glfw.make_context_current(window)
|
||||
logger.debug("_init_glfw: completed successfully")
|
||||
return window, _glfw
|
||||
except Exception:
|
||||
logger.debug("_init_glfw: failed, terminating glfw")
|
||||
_glfw.terminate()
|
||||
raise
|
||||
|
||||
|
||||
def _init_egl():
|
||||
"""Initialize EGL for headless rendering. Returns (display, context, surface, EGL_module). Raises RuntimeError on failure."""
|
||||
logger.debug("_init_egl: starting")
|
||||
from OpenGL import EGL as _EGL
|
||||
from OpenGL.EGL import (
|
||||
eglGetDisplay, eglInitialize, eglChooseConfig, eglCreateContext,
|
||||
eglMakeCurrent, eglCreatePbufferSurface, eglBindAPI,
|
||||
eglTerminate, eglDestroyContext, eglDestroySurface,
|
||||
EGL_DEFAULT_DISPLAY, EGL_NO_CONTEXT, EGL_NONE,
|
||||
EGL_SURFACE_TYPE, EGL_PBUFFER_BIT, EGL_RENDERABLE_TYPE, EGL_OPENGL_BIT,
|
||||
EGL_RED_SIZE, EGL_GREEN_SIZE, EGL_BLUE_SIZE, EGL_ALPHA_SIZE, EGL_DEPTH_SIZE,
|
||||
EGL_WIDTH, EGL_HEIGHT, EGL_OPENGL_API,
|
||||
)
|
||||
logger.debug("_init_egl: imports completed")
|
||||
|
||||
display = None
|
||||
context = None
|
||||
surface = None
|
||||
|
||||
try:
|
||||
logger.debug("_init_egl: calling eglGetDisplay()")
|
||||
display = eglGetDisplay(EGL_DEFAULT_DISPLAY)
|
||||
if display == _EGL.EGL_NO_DISPLAY:
|
||||
raise RuntimeError("eglGetDisplay() failed")
|
||||
|
||||
logger.debug("_init_egl: calling eglInitialize()")
|
||||
major, minor = _EGL.EGLint(), _EGL.EGLint()
|
||||
if not eglInitialize(display, major, minor):
|
||||
display = None # Not initialized, don't terminate
|
||||
raise RuntimeError("eglInitialize() failed")
|
||||
logger.debug(f"_init_egl: EGL version {major.value}.{minor.value}")
|
||||
|
||||
config_attribs = [
|
||||
EGL_SURFACE_TYPE, EGL_PBUFFER_BIT,
|
||||
EGL_RENDERABLE_TYPE, EGL_OPENGL_BIT,
|
||||
EGL_RED_SIZE, 8, EGL_GREEN_SIZE, 8, EGL_BLUE_SIZE, 8, EGL_ALPHA_SIZE, 8,
|
||||
EGL_DEPTH_SIZE, 0, EGL_NONE
|
||||
]
|
||||
configs = (_EGL.EGLConfig * 1)()
|
||||
num_configs = _EGL.EGLint()
|
||||
if not eglChooseConfig(display, config_attribs, configs, 1, num_configs) or num_configs.value == 0:
|
||||
raise RuntimeError("eglChooseConfig() failed")
|
||||
config = configs[0]
|
||||
logger.debug(f"_init_egl: config chosen, num_configs={num_configs.value}")
|
||||
|
||||
if not eglBindAPI(EGL_OPENGL_API):
|
||||
raise RuntimeError("eglBindAPI() failed")
|
||||
|
||||
logger.debug("_init_egl: calling eglCreateContext()")
|
||||
context_attribs = [
|
||||
_EGL.EGL_CONTEXT_MAJOR_VERSION, 3,
|
||||
_EGL.EGL_CONTEXT_MINOR_VERSION, 3,
|
||||
_EGL.EGL_CONTEXT_OPENGL_PROFILE_MASK, _EGL.EGL_CONTEXT_OPENGL_CORE_PROFILE_BIT,
|
||||
EGL_NONE
|
||||
]
|
||||
context = eglCreateContext(display, config, EGL_NO_CONTEXT, context_attribs)
|
||||
if context == EGL_NO_CONTEXT:
|
||||
raise RuntimeError("eglCreateContext() failed")
|
||||
|
||||
logger.debug("_init_egl: calling eglCreatePbufferSurface()")
|
||||
pbuffer_attribs = [EGL_WIDTH, 64, EGL_HEIGHT, 64, EGL_NONE]
|
||||
surface = eglCreatePbufferSurface(display, config, pbuffer_attribs)
|
||||
if surface == _EGL.EGL_NO_SURFACE:
|
||||
raise RuntimeError("eglCreatePbufferSurface() failed")
|
||||
|
||||
logger.debug("_init_egl: calling eglMakeCurrent()")
|
||||
if not eglMakeCurrent(display, surface, surface, context):
|
||||
raise RuntimeError("eglMakeCurrent() failed")
|
||||
|
||||
logger.debug("_init_egl: completed successfully")
|
||||
return display, context, surface, _EGL
|
||||
|
||||
except Exception:
|
||||
logger.debug("_init_egl: failed, cleaning up")
|
||||
# Clean up any resources on failure
|
||||
if surface is not None:
|
||||
eglDestroySurface(display, surface)
|
||||
if context is not None:
|
||||
eglDestroyContext(display, context)
|
||||
if display is not None:
|
||||
eglTerminate(display)
|
||||
raise
|
||||
|
||||
|
||||
def _init_osmesa():
|
||||
"""Initialize OSMesa for software rendering. Returns (context, buffer). Raises RuntimeError on failure."""
|
||||
import ctypes
|
||||
|
||||
logger.debug("_init_osmesa: starting")
|
||||
os.environ["PYOPENGL_PLATFORM"] = "osmesa"
|
||||
|
||||
logger.debug("_init_osmesa: importing OpenGL.osmesa")
|
||||
from OpenGL import GL as _gl
|
||||
from OpenGL.osmesa import (
|
||||
OSMesaCreateContextExt, OSMesaMakeCurrent, OSMesaDestroyContext,
|
||||
OSMESA_RGBA,
|
||||
)
|
||||
logger.debug("_init_osmesa: imports completed")
|
||||
|
||||
ctx = OSMesaCreateContextExt(OSMESA_RGBA, 24, 0, 0, None)
|
||||
if not ctx:
|
||||
raise RuntimeError("OSMesaCreateContextExt() failed")
|
||||
|
||||
width, height = 64, 64
|
||||
buffer = (ctypes.c_ubyte * (width * height * 4))()
|
||||
|
||||
logger.debug("_init_osmesa: calling OSMesaMakeCurrent()")
|
||||
if not OSMesaMakeCurrent(ctx, buffer, _gl.GL_UNSIGNED_BYTE, width, height):
|
||||
OSMesaDestroyContext(ctx)
|
||||
raise RuntimeError("OSMesaMakeCurrent() failed")
|
||||
|
||||
logger.debug("_init_osmesa: completed successfully")
|
||||
return ctx, buffer
|
||||
|
||||
|
||||
class GLContext:
|
||||
"""Manages an OpenGL ES 3.0 context via EGL/ANGLE (singleton)."""
|
||||
"""Manages OpenGL context and resources for shader execution.
|
||||
|
||||
Tries backends in order: GLFW (desktop) → EGL (headless GPU) → OSMesa (software).
|
||||
"""
|
||||
|
||||
_instance = None
|
||||
_initialized = False
|
||||
@ -240,105 +327,131 @@ class GLContext:
|
||||
|
||||
def __init__(self):
|
||||
if GLContext._initialized:
|
||||
logger.debug("GLContext.__init__: already initialized, skipping")
|
||||
return
|
||||
|
||||
logger.debug("GLContext.__init__: starting initialization")
|
||||
|
||||
global glfw, EGL
|
||||
|
||||
import time
|
||||
start = time.perf_counter()
|
||||
|
||||
self._display = None
|
||||
self._surface = None
|
||||
self._context = None
|
||||
self._backend = None
|
||||
self._window = None
|
||||
self._egl_display = None
|
||||
self._egl_context = None
|
||||
self._egl_surface = None
|
||||
self._osmesa_ctx = None
|
||||
self._osmesa_buffer = None
|
||||
self._vao = None
|
||||
|
||||
# Try backends in order: GLFW → EGL → OSMesa
|
||||
errors = []
|
||||
|
||||
logger.debug("GLContext.__init__: trying GLFW backend")
|
||||
try:
|
||||
self._display, self._egl_major, self._egl_minor = _get_egl_display()
|
||||
self._window, glfw = _init_glfw()
|
||||
self._backend = "glfw"
|
||||
logger.debug("GLContext.__init__: GLFW backend succeeded")
|
||||
except Exception as e:
|
||||
logger.debug(f"GLContext.__init__: GLFW backend failed: {e}")
|
||||
errors.append(("GLFW", e))
|
||||
|
||||
if not EGL.eglBindAPI(EGL.EGL_OPENGL_ES_API):
|
||||
raise RuntimeError("eglBindAPI(EGL_OPENGL_ES_API) failed")
|
||||
if self._backend is None:
|
||||
logger.debug("GLContext.__init__: trying EGL backend")
|
||||
try:
|
||||
self._egl_display, self._egl_context, self._egl_surface, EGL = _init_egl()
|
||||
self._backend = "egl"
|
||||
logger.debug("GLContext.__init__: EGL backend succeeded")
|
||||
except Exception as e:
|
||||
logger.debug(f"GLContext.__init__: EGL backend failed: {e}")
|
||||
errors.append(("EGL", e))
|
||||
|
||||
config = EGL.EGLConfig()
|
||||
n_configs = ctypes.c_int32(0)
|
||||
if not EGL.eglChooseConfig(
|
||||
self._display,
|
||||
_egl_attribs(
|
||||
EGL.EGL_RENDERABLE_TYPE, EGL.EGL_OPENGL_ES3_BIT,
|
||||
EGL.EGL_SURFACE_TYPE, EGL.EGL_PBUFFER_BIT,
|
||||
EGL.EGL_RED_SIZE, 8, EGL.EGL_GREEN_SIZE, 8,
|
||||
EGL.EGL_BLUE_SIZE, 8, EGL.EGL_ALPHA_SIZE, 8,
|
||||
),
|
||||
ctypes.byref(config), 1, ctypes.byref(n_configs),
|
||||
) or n_configs.value == 0:
|
||||
raise RuntimeError("eglChooseConfig() failed")
|
||||
if self._backend is None:
|
||||
logger.debug("GLContext.__init__: trying OSMesa backend")
|
||||
try:
|
||||
self._osmesa_ctx, self._osmesa_buffer = _init_osmesa()
|
||||
self._backend = "osmesa"
|
||||
logger.debug("GLContext.__init__: OSMesa backend succeeded")
|
||||
except Exception as e:
|
||||
logger.debug(f"GLContext.__init__: OSMesa backend failed: {e}")
|
||||
errors.append(("OSMesa", e))
|
||||
|
||||
self._surface = EGL.eglCreatePbufferSurface(
|
||||
self._display, config,
|
||||
_egl_attribs(EGL.EGL_WIDTH, 64, EGL.EGL_HEIGHT, 64),
|
||||
if self._backend is None:
|
||||
if sys.platform == "win32":
|
||||
platform_help = (
|
||||
"Windows: Ensure GPU drivers are installed and display is available.\n"
|
||||
" CPU-only/headless mode is not supported on Windows."
|
||||
)
|
||||
elif sys.platform == "darwin":
|
||||
platform_help = (
|
||||
"macOS: GLFW is not supported.\n"
|
||||
" Install OSMesa via Homebrew: brew install mesa\n"
|
||||
" Then: pip install PyOpenGL PyOpenGL-accelerate"
|
||||
)
|
||||
else:
|
||||
platform_help = (
|
||||
"Linux: Install one of these backends:\n"
|
||||
" Desktop: sudo apt install libgl1-mesa-glx libglfw3\n"
|
||||
" Headless with GPU: sudo apt install libegl1-mesa libgl1-mesa-dri\n"
|
||||
" Headless (CPU): sudo apt install libosmesa6"
|
||||
)
|
||||
|
||||
error_details = "\n".join(f" {name}: {err}" for name, err in errors)
|
||||
raise RuntimeError(
|
||||
f"Failed to create OpenGL context.\n\n"
|
||||
f"Backend errors:\n{error_details}\n\n"
|
||||
f"{platform_help}"
|
||||
)
|
||||
if not self._surface:
|
||||
raise RuntimeError("eglCreatePbufferSurface() failed")
|
||||
|
||||
self._context = EGL.eglCreateContext(
|
||||
self._display, config, EGL.EGL_NO_CONTEXT,
|
||||
_egl_attribs(EGL.EGL_CONTEXT_CLIENT_VERSION, 3),
|
||||
)
|
||||
if not self._context:
|
||||
raise RuntimeError("eglCreateContext() failed")
|
||||
# Now import OpenGL.GL (after context is current)
|
||||
logger.debug("GLContext.__init__: importing OpenGL.GL")
|
||||
_import_opengl()
|
||||
|
||||
if not EGL.eglMakeCurrent(self._display, self._surface, self._surface, self._context):
|
||||
raise RuntimeError("eglMakeCurrent() failed")
|
||||
|
||||
self._vao = gl.glGenVertexArrays(1)
|
||||
gl.glBindVertexArray(self._vao)
|
||||
|
||||
except Exception:
|
||||
self._cleanup()
|
||||
raise
|
||||
# Create VAO (required for core profile, but OSMesa may use compat profile)
|
||||
logger.debug("GLContext.__init__: creating VAO")
|
||||
try:
|
||||
vao = gl.glGenVertexArrays(1)
|
||||
gl.glBindVertexArray(vao)
|
||||
self._vao = vao # Only store after successful bind
|
||||
logger.debug("GLContext.__init__: VAO created successfully")
|
||||
except Exception as e:
|
||||
logger.debug(f"GLContext.__init__: VAO creation failed (may be expected for OSMesa): {e}")
|
||||
# OSMesa with older Mesa may not support VAOs
|
||||
# Clean up if we created but couldn't bind
|
||||
if vao:
|
||||
try:
|
||||
gl.glDeleteVertexArrays(1, [vao])
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
elapsed = (time.perf_counter() - start) * 1000
|
||||
|
||||
renderer = _gl_str(gl.GL_RENDERER)
|
||||
vendor = _gl_str(gl.GL_VENDOR)
|
||||
version = _gl_str(gl.GL_VERSION)
|
||||
# Log device info
|
||||
renderer = gl.glGetString(gl.GL_RENDERER)
|
||||
vendor = gl.glGetString(gl.GL_VENDOR)
|
||||
version = gl.glGetString(gl.GL_VERSION)
|
||||
renderer = renderer.decode() if renderer else "Unknown"
|
||||
vendor = vendor.decode() if vendor else "Unknown"
|
||||
version = version.decode() if version else "Unknown"
|
||||
|
||||
GLContext._initialized = True
|
||||
logger.info(f"GLSL context initialized in {elapsed:.1f}ms - EGL {self._egl_major}.{self._egl_minor}, {renderer} ({vendor}), GL {version}")
|
||||
logger.info(f"GLSL context initialized in {elapsed:.1f}ms ({self._backend}) - {renderer} ({vendor}), GL {version}")
|
||||
|
||||
def make_current(self):
|
||||
if not EGL.eglMakeCurrent(self._display, self._surface, self._surface, self._context):
|
||||
err = EGL.eglGetError()
|
||||
raise RuntimeError(f"eglMakeCurrent() failed (EGL error: 0x{err:04X})")
|
||||
if self._backend == "glfw":
|
||||
glfw.make_context_current(self._window)
|
||||
elif self._backend == "egl":
|
||||
from OpenGL.EGL import eglMakeCurrent
|
||||
eglMakeCurrent(self._egl_display, self._egl_surface, self._egl_surface, self._egl_context)
|
||||
elif self._backend == "osmesa":
|
||||
from OpenGL.osmesa import OSMesaMakeCurrent
|
||||
OSMesaMakeCurrent(self._osmesa_ctx, self._osmesa_buffer, gl.GL_UNSIGNED_BYTE, 64, 64)
|
||||
|
||||
if self._vao is not None:
|
||||
gl.glBindVertexArray(self._vao)
|
||||
|
||||
def _cleanup(self):
|
||||
if not self._display:
|
||||
return
|
||||
try:
|
||||
if self._vao is not None:
|
||||
gl.glDeleteVertexArrays(1, [self._vao])
|
||||
self._vao = None
|
||||
except Exception:
|
||||
pass
|
||||
try:
|
||||
EGL.eglMakeCurrent(self._display, EGL.EGL_NO_SURFACE, EGL.EGL_NO_SURFACE, EGL.EGL_NO_CONTEXT)
|
||||
except Exception:
|
||||
pass
|
||||
try:
|
||||
if self._context:
|
||||
EGL.eglDestroyContext(self._display, self._context)
|
||||
except Exception:
|
||||
pass
|
||||
try:
|
||||
if self._surface:
|
||||
EGL.eglDestroySurface(self._display, self._surface)
|
||||
except Exception:
|
||||
pass
|
||||
try:
|
||||
EGL.eglTerminate(self._display)
|
||||
except Exception:
|
||||
pass
|
||||
self._display = None
|
||||
|
||||
|
||||
def _compile_shader(source: str, shader_type: int) -> int:
|
||||
"""Compile a shader and return its ID."""
|
||||
@ -346,10 +459,8 @@ def _compile_shader(source: str, shader_type: int) -> int:
|
||||
gl.glShaderSource(shader, source)
|
||||
gl.glCompileShader(shader)
|
||||
|
||||
if not gl.glGetShaderiv(shader, gl.GL_COMPILE_STATUS):
|
||||
error = gl.glGetShaderInfoLog(shader)
|
||||
if isinstance(error, bytes):
|
||||
error = error.decode(errors="replace")
|
||||
if gl.glGetShaderiv(shader, gl.GL_COMPILE_STATUS) != gl.GL_TRUE:
|
||||
error = gl.glGetShaderInfoLog(shader).decode()
|
||||
gl.glDeleteShader(shader)
|
||||
raise RuntimeError(f"Shader compilation failed:\n{error}")
|
||||
|
||||
@ -373,10 +484,8 @@ def _create_program(vertex_source: str, fragment_source: str) -> int:
|
||||
gl.glDeleteShader(vertex_shader)
|
||||
gl.glDeleteShader(fragment_shader)
|
||||
|
||||
if not gl.glGetProgramiv(program, gl.GL_LINK_STATUS):
|
||||
error = gl.glGetProgramInfoLog(program)
|
||||
if isinstance(error, bytes):
|
||||
error = error.decode(errors="replace")
|
||||
if gl.glGetProgramiv(program, gl.GL_LINK_STATUS) != gl.GL_TRUE:
|
||||
error = gl.glGetProgramInfoLog(program).decode()
|
||||
gl.glDeleteProgram(program)
|
||||
raise RuntimeError(f"Program linking failed:\n{error}")
|
||||
|
||||
@ -421,6 +530,9 @@ def _render_shader_batch(
|
||||
ctx = GLContext()
|
||||
ctx.make_current()
|
||||
|
||||
# Convert from GLSL ES to desktop GLSL 330
|
||||
fragment_source = _convert_es_to_desktop(fragment_code)
|
||||
|
||||
# Detect how many outputs the shader actually uses
|
||||
num_outputs = _detect_output_count(fragment_code)
|
||||
|
||||
@ -446,9 +558,9 @@ def _render_shader_batch(
|
||||
try:
|
||||
# Compile shaders (once for all batches)
|
||||
try:
|
||||
program = _create_program(VERTEX_SHADER, fragment_code)
|
||||
program = _create_program(VERTEX_SHADER, fragment_source)
|
||||
except RuntimeError:
|
||||
logger.error(f"Fragment shader:\n{fragment_code}")
|
||||
logger.error(f"Fragment shader:\n{fragment_source}")
|
||||
raise
|
||||
|
||||
gl.glUseProgram(program)
|
||||
@ -611,13 +723,13 @@ def _render_shader_batch(
|
||||
gl.glDrawArrays(gl.GL_TRIANGLES, 0, 3)
|
||||
|
||||
# Read back outputs for this batch
|
||||
gl.glBindFramebuffer(gl.GL_FRAMEBUFFER, fbo)
|
||||
# (glGetTexImage is synchronous, implicitly waits for rendering)
|
||||
batch_outputs = []
|
||||
for i in range(num_outputs):
|
||||
gl.glReadBuffer(gl.GL_COLOR_ATTACHMENT0 + i)
|
||||
buf = np.empty((height, width, 4), dtype=np.float32)
|
||||
gl.glReadPixels(0, 0, width, height, gl.GL_RGBA, gl.GL_FLOAT, buf)
|
||||
batch_outputs.append(buf[::-1, :, :].copy())
|
||||
for tex in output_textures:
|
||||
gl.glBindTexture(gl.GL_TEXTURE_2D, tex)
|
||||
data = gl.glGetTexImage(gl.GL_TEXTURE_2D, 0, gl.GL_RGBA, gl.GL_FLOAT)
|
||||
img = np.frombuffer(data, dtype=np.float32).reshape(height, width, 4)
|
||||
batch_outputs.append(img[::-1, :, :].copy())
|
||||
|
||||
# Pad with black images for unused outputs
|
||||
black_img = np.zeros((height, width, 4), dtype=np.float32)
|
||||
@ -638,18 +750,18 @@ def _render_shader_batch(
|
||||
gl.glBindFramebuffer(gl.GL_FRAMEBUFFER, 0)
|
||||
gl.glUseProgram(0)
|
||||
|
||||
if input_textures:
|
||||
gl.glDeleteTextures(len(input_textures), input_textures)
|
||||
if curve_textures:
|
||||
gl.glDeleteTextures(len(curve_textures), curve_textures)
|
||||
if output_textures:
|
||||
gl.glDeleteTextures(len(output_textures), output_textures)
|
||||
if ping_pong_textures:
|
||||
gl.glDeleteTextures(len(ping_pong_textures), ping_pong_textures)
|
||||
for tex in input_textures:
|
||||
gl.glDeleteTextures(int(tex))
|
||||
for tex in curve_textures:
|
||||
gl.glDeleteTextures(int(tex))
|
||||
for tex in output_textures:
|
||||
gl.glDeleteTextures(int(tex))
|
||||
for tex in ping_pong_textures:
|
||||
gl.glDeleteTextures(int(tex))
|
||||
if fbo is not None:
|
||||
gl.glDeleteFramebuffers(1, [fbo])
|
||||
if ping_pong_fbos:
|
||||
gl.glDeleteFramebuffers(len(ping_pong_fbos), ping_pong_fbos)
|
||||
for pp_fbo in ping_pong_fbos:
|
||||
gl.glDeleteFramebuffers(1, [pp_fbo])
|
||||
if program is not None:
|
||||
gl.glDeleteProgram(program)
|
||||
|
||||
|
||||
@ -123,8 +123,7 @@ class PhotoMakerLoader(io.ComfyNode):
|
||||
def define_schema(cls):
|
||||
return io.Schema(
|
||||
node_id="PhotoMakerLoader",
|
||||
display_name="Load PhotoMaker Model",
|
||||
category="model/loaders",
|
||||
category="experimental/photomaker",
|
||||
inputs=[
|
||||
io.Combo.Input("photomaker_model_name", options=folder_paths.get_filename_list("photomaker")),
|
||||
],
|
||||
@ -150,8 +149,7 @@ class PhotoMakerEncode(io.ComfyNode):
|
||||
def define_schema(cls):
|
||||
return io.Schema(
|
||||
node_id="PhotoMakerEncode",
|
||||
display_name="PhotoMaker Encode",
|
||||
category="model/conditioning/photomaker",
|
||||
category="experimental/photomaker",
|
||||
inputs=[
|
||||
io.Photomaker.Input("photomaker"),
|
||||
io.Image.Input("image"),
|
||||
|
||||
@ -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"),
|
||||
|
||||
@ -143,7 +143,7 @@ class VAEDecodeTripoSplat(IO.ComfyNode):
|
||||
return IO.Schema(
|
||||
node_id="VAEDecodeTripoSplat",
|
||||
display_name="TripoSplat Decode",
|
||||
category="model/latent/triposplat",
|
||||
category="3d/latent",
|
||||
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="model/latent/triposplat",
|
||||
category="3d/latent",
|
||||
description="Patch the TripoSplat model for the standard Ksampler node to show a live decoded "
|
||||
"gaussian splat preview at each step.",
|
||||
inputs=[
|
||||
|
||||
@ -1,3 +1,3 @@
|
||||
# This file is automatically generated by the build process when version is
|
||||
# updated in pyproject.toml.
|
||||
__version__ = "0.27.1"
|
||||
__version__ = "0.26.0"
|
||||
|
||||
4
main.py
4
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=args.enable_asset_hashing)
|
||||
asset_seeder.enqueue_enrich(roots=("output",), compute_hashes=True)
|
||||
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=args.enable_asset_hashing):
|
||||
if asset_seeder.start(roots=("models", "input", "output"), prune_first=True, compute_hashes=True):
|
||||
logging.info("Background asset scan initiated for models, input, output")
|
||||
except Exception as e:
|
||||
if "database is locked" in str(e):
|
||||
|
||||
36
nodes.py
36
nodes.py
@ -159,29 +159,6 @@ 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"]
|
||||
|
||||
@ -349,7 +326,7 @@ class VAEDecodeTiled:
|
||||
RETURN_TYPES = ("IMAGE",)
|
||||
FUNCTION = "decode"
|
||||
|
||||
CATEGORY = "model/latent"
|
||||
CATEGORY = "experimental"
|
||||
|
||||
def decode(self, vae, samples, tile_size, overlap=64, temporal_size=64, temporal_overlap=8):
|
||||
if tile_size < overlap * 4:
|
||||
@ -396,7 +373,7 @@ class VAEEncodeTiled:
|
||||
RETURN_TYPES = ("LATENT",)
|
||||
FUNCTION = "encode"
|
||||
|
||||
CATEGORY = "model/latent"
|
||||
CATEGORY = "experimental"
|
||||
|
||||
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)
|
||||
@ -514,7 +491,7 @@ class SaveLatent:
|
||||
|
||||
OUTPUT_NODE = True
|
||||
|
||||
CATEGORY = "model/latent"
|
||||
CATEGORY = "experimental"
|
||||
|
||||
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)
|
||||
@ -559,7 +536,7 @@ 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 = "model/latent"
|
||||
CATEGORY = "experimental"
|
||||
|
||||
RETURN_TYPES = ("LATENT", )
|
||||
FUNCTION = "load"
|
||||
@ -2073,7 +2050,6 @@ NODE_CLASS_MAPPINGS = {
|
||||
"ConditioningAverage": ConditioningAverage,
|
||||
"ConditioningCombine": ConditioningCombine,
|
||||
"ConditioningConcat": ConditioningConcat,
|
||||
"ConditioningMultiply": ConditioningMultiply,
|
||||
"ConditioningSetArea": ConditioningSetArea,
|
||||
"ConditioningSetAreaPercentage": ConditioningSetAreaPercentage,
|
||||
"ConditioningSetAreaStrength": ConditioningSetAreaStrength,
|
||||
@ -2145,7 +2121,6 @@ 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)",
|
||||
@ -2155,8 +2130,6 @@ 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",
|
||||
@ -2191,6 +2164,7 @@ 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)",
|
||||
}
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
[project]
|
||||
name = "ComfyUI"
|
||||
version = "0.27.1"
|
||||
version = "0.26.0"
|
||||
readme = "README.md"
|
||||
license = { file = "LICENSE" }
|
||||
requires-python = ">=3.10"
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
comfyui-frontend-package==1.45.20
|
||||
comfyui-workflow-templates==0.11.6
|
||||
comfyui-embedded-docs==0.5.6
|
||||
comfyui-frontend-package==1.45.19
|
||||
comfyui-workflow-templates==0.10.7
|
||||
comfyui-embedded-docs==0.5.5
|
||||
torch
|
||||
torchsde
|
||||
torchvision
|
||||
@ -22,7 +22,7 @@ alembic
|
||||
SQLAlchemy>=2.0.0
|
||||
filelock
|
||||
av>=16.0.0
|
||||
comfy-kitchen==0.2.16
|
||||
comfy-kitchen==0.2.12
|
||||
comfy-aimdo==0.4.10
|
||||
requests
|
||||
simpleeval>=1.0.0
|
||||
@ -33,5 +33,5 @@ kornia>=0.7.1
|
||||
spandrel
|
||||
pydantic~=2.0
|
||||
pydantic-settings~=2.0
|
||||
PyOpenGL>=3.1.8
|
||||
comfy-angle
|
||||
PyOpenGL
|
||||
glfw
|
||||
|
||||
97
tests-unit/execution_test/scheduler_malformed_node_test.py
Normal file
97
tests-unit/execution_test/scheduler_malformed_node_test.py
Normal file
@ -0,0 +1,97 @@
|
||||
"""Regression tests for scheduler resilience to malformed nodes.
|
||||
|
||||
A node whose FUNCTION points at a method that does not exist (e.g. a typo in a
|
||||
custom node) used to raise inside the scheduling heuristic, escaping the prompt
|
||||
worker's error handling and silently killing the worker thread. Scheduling must
|
||||
instead either proceed (so the error surfaces through normal execution) or report
|
||||
the failure as an execution error.
|
||||
"""
|
||||
import asyncio
|
||||
|
||||
import nodes
|
||||
from comfy_execution.graph import DynamicPrompt, ExecutionList
|
||||
|
||||
|
||||
class _MalformedV1Node:
|
||||
@classmethod
|
||||
def INPUT_TYPES(cls):
|
||||
return {"required": {}}
|
||||
|
||||
RETURN_TYPES = ("IMAGE",)
|
||||
FUNCTION = "invert" # the actual method below is misspelled
|
||||
OUTPUT_NODE = True
|
||||
CATEGORY = "Test"
|
||||
|
||||
def invvert(self):
|
||||
return (None,)
|
||||
|
||||
|
||||
class _RaisingDescriptor:
|
||||
def __get__(self, obj, owner):
|
||||
raise RuntimeError("schema error")
|
||||
|
||||
|
||||
class _SchemaRaisesNode:
|
||||
"""A node whose schema-derived attribute access raises, as a broken V3 node would."""
|
||||
@classmethod
|
||||
def INPUT_TYPES(cls):
|
||||
return {"required": {}}
|
||||
|
||||
RETURN_TYPES = ("IMAGE",)
|
||||
FUNCTION = "run"
|
||||
OUTPUT_NODE = _RaisingDescriptor()
|
||||
CATEGORY = "Test"
|
||||
|
||||
def run(self):
|
||||
return (None,)
|
||||
|
||||
|
||||
class _FakeOutputCache:
|
||||
def all_node_ids(self):
|
||||
return set()
|
||||
|
||||
async def get(self, node_id):
|
||||
return None
|
||||
|
||||
|
||||
def _make_execution_list(class_type, class_def):
|
||||
nodes.NODE_CLASS_MAPPINGS[class_type] = class_def
|
||||
prompt = {"1": {"class_type": class_type, "inputs": {}}}
|
||||
execution_list = ExecutionList(DynamicPrompt(prompt), _FakeOutputCache())
|
||||
execution_list.add_node("1")
|
||||
return execution_list
|
||||
|
||||
|
||||
def test_malformed_function_does_not_crash_scheduler():
|
||||
"""A FUNCTION-typo node schedules without raising; the error surfaces later."""
|
||||
execution_list = _make_execution_list("MalformedV1Node", _MalformedV1Node)
|
||||
node_id, error, ex = asyncio.run(execution_list.stage_node_execution())
|
||||
assert ex is None
|
||||
assert error is None
|
||||
assert node_id == "1"
|
||||
|
||||
|
||||
def test_schema_attribute_error_does_not_crash_scheduler():
|
||||
"""A node whose attribute access raises during heuristics still schedules."""
|
||||
execution_list = _make_execution_list("SchemaRaisesNode", _SchemaRaisesNode)
|
||||
node_id, error, ex = asyncio.run(execution_list.stage_node_execution())
|
||||
assert ex is None
|
||||
assert error is None
|
||||
assert node_id == "1"
|
||||
|
||||
|
||||
def test_pick_node_failure_is_reported_not_raised():
|
||||
"""An unexpected scheduling error is returned as an error, not raised."""
|
||||
execution_list = _make_execution_list("MalformedV1Node", _MalformedV1Node)
|
||||
|
||||
def raise_on_pick(_available):
|
||||
raise RuntimeError("boom")
|
||||
|
||||
execution_list.ux_friendly_pick_node = raise_on_pick
|
||||
node_id, error, ex = asyncio.run(execution_list.stage_node_execution())
|
||||
assert node_id is None
|
||||
assert isinstance(ex, RuntimeError)
|
||||
assert error["node_id"] == "1"
|
||||
assert error["exception_type"] == "RuntimeError"
|
||||
assert error["exception_message"] == "boom"
|
||||
assert error["traceback"]
|
||||
Reference in New Issue
Block a user