youngkingdom/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-05-05 17:57:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into toolkit/wire-essentials-categorization

Browse Source
This commit is contained in:
Christian Byrne
2026-03-14 21:33:16 -07:00
committed by GitHub
parent ad5b8ca494 0904cc3fe5
commit 4d40630dd9
161 changed files with 17716 additions and 3588 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
comfy_api_nodes/apis/bytedance.py
View File

@ -27,6 +27,7 @@ class Seedream4TaskCreationRequest(BaseModel):
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
class ImageTaskCreationResponse(BaseModel):
@ -106,6 +107,7 @@ RECOMMENDED_PRESETS_SEEDREAM_4 = [
("2496x1664 (3:2)", 2496, 1664),
("1664x2496 (2:3)", 1664, 2496),
("3024x1296 (21:9)", 3024, 1296),
("3072x3072 (1:1)", 3072, 3072),
("4096x4096 (1:1)", 4096, 4096),
("Custom", None, None),
]

6
comfy_api_nodes/apis/gemini.py
View File

@ -127,9 +127,15 @@ class GeminiImageConfig(BaseModel):
imageOutputOptions: GeminiImageOutputOptions = Field(default_factory=GeminiImageOutputOptions)
class GeminiThinkingConfig(BaseModel):
includeThoughts: bool | None = Field(None)
thinkingLevel: str = Field(...)
class GeminiImageGenerationConfig(GeminiGenerationConfig):
responseModalities: list[str] | None = Field(None)
imageConfig: GeminiImageConfig | None = Field(None)
thinkingConfig: GeminiThinkingConfig | None = Field(None)
class GeminiImageGenerateContentRequest(BaseModel):

14
comfy_api_nodes/apis/grok.py
View File

@ -7,7 +7,8 @@ class ImageGenerationRequest(BaseModel):
aspect_ratio: str = Field(...)
n: int = Field(...)
seed: int = Field(...)
response_for: str = Field("url")
response_format: str = Field("url")
resolution: str = Field(...)
class InputUrlObject(BaseModel):
@ -16,12 +17,13 @@ class InputUrlObject(BaseModel):
class ImageEditRequest(BaseModel):
model: str = Field(...)
image: InputUrlObject = Field(...)
images: list[InputUrlObject] = Field(...)
prompt: str = Field(...)
resolution: str = Field(...)
n: int = Field(...)
seed: int = Field(...)
response_for: str = Field("url")
response_format: str = Field("url")
aspect_ratio: str | None = Field(...)
class VideoGenerationRequest(BaseModel):
@ -47,8 +49,13 @@ class ImageResponseObject(BaseModel):
revised_prompt: str | None = Field(None)
class UsageObject(BaseModel):
cost_in_usd_ticks: int | None = Field(None)
class ImageGenerationResponse(BaseModel):
data: list[ImageResponseObject] = Field(...)
usage: UsageObject | None = Field(None)
class VideoGenerationResponse(BaseModel):
@ -65,3 +72,4 @@ class VideoStatusResponse(BaseModel):
status: str | None = Field(None)
video: VideoResponseObject | None = Field(None)
model: str | None = Field(None)
usage: UsageObject | None = Field(None)

16
comfy_api_nodes/apis/hunyuan3d.py
View File

@ -66,13 +66,17 @@ class To3DProTaskQueryRequest(BaseModel):
JobId: str = Field(...)
class To3DUVFileInput(BaseModel):
class TaskFile3DInput(BaseModel):
Type: str = Field(..., description="File type: GLB, OBJ, or FBX")
Url: str = Field(...)
class To3DUVTaskRequest(BaseModel):
File: To3DUVFileInput = Field(...)
File: TaskFile3DInput = Field(...)
class To3DPartTaskRequest(BaseModel):
File: TaskFile3DInput = Field(...)
class TextureEditImageInfo(BaseModel):
@ -80,7 +84,13 @@ class TextureEditImageInfo(BaseModel):
class TextureEditTaskRequest(BaseModel):
File3D: To3DUVFileInput = Field(...)
File3D: TaskFile3DInput = Field(...)
Image: TextureEditImageInfo | None = Field(None)
Prompt: str | None = Field(None)
EnablePBR: bool | None = Field(None)
class SmartTopologyRequest(BaseModel):
File3D: TaskFile3DInput = Field(...)
PolygonType: str | None = Field(...)
FaceLevel: str | None = Field(...)

8
comfy_api_nodes/apis/kling.py
View File

@ -134,6 +134,13 @@ class ImageToVideoWithAudioRequest(BaseModel):
shot_type: str | None = Field(None)
class KlingAvatarRequest(BaseModel):
image: str = Field(...)
sound_file: str = Field(...)
prompt: str | None = Field(None)
mode: str = Field(...)
class MotionControlRequest(BaseModel):
prompt: str = Field(...)
image_url: str = Field(...)
@ -141,3 +148,4 @@ class MotionControlRequest(BaseModel):
keep_original_sound: str = Field(...)
character_orientation: str = Field(...)
mode: str = Field(..., description="'pro' or 'std'")
model_name: str = Field(...)

68
comfy_api_nodes/apis/reve.py Normal file
View File

@ -0,0 +1,68 @@
from pydantic import BaseModel, Field
class RevePostprocessingOperation(BaseModel):
process: str = Field(..., description="The postprocessing operation: upscale or remove_background.")
upscale_factor: int | None = Field(
None,
description="Upscale factor (2, 3, or 4). Only used when process is upscale.",
ge=2,
le=4,
)
class ReveImageCreateRequest(BaseModel):
prompt: str = Field(...)
aspect_ratio: str | None = Field(...)
version: str = Field(...)
test_time_scaling: int = Field(
...,
description="If included, the model will spend more effort making better images. Values between 1 and 15.",
ge=1,
le=15,
)
postprocessing: list[RevePostprocessingOperation] | None = Field(
None, description="Optional postprocessing operations to apply after generation."
)
class ReveImageEditRequest(BaseModel):
edit_instruction: str = Field(...)
reference_image: str = Field(..., description="A base64 encoded image to use as reference for the edit.")
aspect_ratio: str | None = Field(...)
version: str = Field(...)
test_time_scaling: int | None = Field(
...,
description="If included, the model will spend more effort making better images. Values between 1 and 15.",
ge=1,
le=15,
)
postprocessing: list[RevePostprocessingOperation] | None = Field(
None, description="Optional postprocessing operations to apply after generation."
)
class ReveImageRemixRequest(BaseModel):
prompt: str = Field(...)
reference_images: list[str] = Field(..., description="A list of 1-6 base64 encoded reference images.")
aspect_ratio: str | None = Field(...)
version: str = Field(...)
test_time_scaling: int | None = Field(
...,
description="If included, the model will spend more effort making better images. Values between 1 and 15.",
ge=1,
le=15,
)
postprocessing: list[RevePostprocessingOperation] | None = Field(
None, description="Optional postprocessing operations to apply after generation."
)
class ReveImageResponse(BaseModel):
image: str | None = Field(None, description="The base64 encoded image data.")
request_id: str | None = Field(None, description="A unique id for the request.")
credits_used: float | None = Field(None, description="The number of credits used for this request.")
version: str | None = Field(None, description="The specific model version used.")
content_violation: bool | None = Field(
None, description="Indicates whether the generated image violates the content policy."
)

48
comfy_api_nodes/nodes_bytedance.py
View File

@ -37,6 +37,12 @@ from comfy_api_nodes.util import (
BYTEPLUS_IMAGE_ENDPOINT = "/proxy/byteplus/api/v3/images/generations"
SEEDREAM_MODELS = {
"seedream 5.0 lite": "seedream-5-0-260128",
"seedream-4-5-251128": "seedream-4-5-251128",
"seedream-4-0-250828": "seedream-4-0-250828",
}
# Long-running tasks endpoints(e.g., video)
BYTEPLUS_TASK_ENDPOINT = "/proxy/byteplus/api/v3/contents/generations/tasks"
BYTEPLUS_TASK_STATUS_ENDPOINT = "/proxy/byteplus/api/v3/contents/generations/tasks" # + /{task_id}
@ -180,14 +186,13 @@ class ByteDanceSeedreamNode(IO.ComfyNode):
def define_schema(cls):
return IO.Schema(
node_id="ByteDanceSeedreamNode",
display_name="ByteDance Seedream 4.5",
display_name="ByteDance Seedream 4.5 & 5.0",
category="api node/image/ByteDance",
description="Unified text-to-image generation and precise single-sentence editing at up to 4K resolution.",
inputs=[
IO.Combo.Input(
"model",
options=["seedream-4-5-251128", "seedream-4-0-250828"],
tooltip="Model name",
options=list(SEEDREAM_MODELS.keys()),
),
IO.String.Input(
"prompt",
@ -198,7 +203,7 @@ class ByteDanceSeedreamNode(IO.ComfyNode):
IO.Image.Input(
"image",
tooltip="Input image(s) for image-to-image generation. "
"List of 1-10 images for single or multi-reference generation.",
"Reference image(s) for single or multi-reference generation.",
optional=True,
),
IO.Combo.Input(
@ -210,8 +215,8 @@ class ByteDanceSeedreamNode(IO.ComfyNode):
"width",
default=2048,
min=1024,
max=4096,
step=8,
max=6240,
step=2,
tooltip="Custom width for image. Value is working only if `size_preset` is set to `Custom`",
optional=True,
),
@ -219,8 +224,8 @@ class ByteDanceSeedreamNode(IO.ComfyNode):
"height",
default=2048,
min=1024,
max=4096,
step=8,
max=4992,
step=2,
tooltip="Custom height for image. Value is working only if `size_preset` is set to `Custom`",
optional=True,
),
@ -283,7 +288,8 @@ class ByteDanceSeedreamNode(IO.ComfyNode):
depends_on=IO.PriceBadgeDepends(widgets=["model"]),
expr="""
(
$price := $contains(widgets.model, "seedream-4-5-251128") ? 0.04 : 0.03;
$price := $contains(widgets.model, "5.0 lite") ? 0.035 :
$contains(widgets.model, "4-5") ? 0.04 : 0.03;
{
"type":"usd",
"usd": $price,
@ -309,6 +315,7 @@ class ByteDanceSeedreamNode(IO.ComfyNode):
watermark: bool = False,
fail_on_partial: bool = True,
) -> IO.NodeOutput:
model = SEEDREAM_MODELS[model]
validate_string(prompt, strip_whitespace=True, min_length=1)
w = h = None
for label, tw, th in RECOMMENDED_PRESETS_SEEDREAM_4:
@ -318,15 +325,12 @@ class ByteDanceSeedreamNode(IO.ComfyNode):
if w is None or h is None:
w, h = width, height
if not (1024 <= w <= 4096) or not (1024 <= h <= 4096):
raise ValueError(
f"Custom size out of range: {w}x{h}. " "Both width and height must be between 1024 and 4096 pixels."
)
out_num_pixels = w * h
mp_provided = out_num_pixels / 1_000_000.0
if "seedream-4-5" in model and out_num_pixels < 3686400:
if ("seedream-4-5" in model or "seedream-5-0" in model) and out_num_pixels < 3686400:
raise ValueError(
f"Minimum image resolution that Seedream 4.5 can generate is 3.68MP, "
f"Minimum image resolution for the selected model is 3.68MP, "
f"but {mp_provided:.2f}MP provided."
)
if "seedream-4-0" in model and out_num_pixels < 921600:
@ -334,9 +338,18 @@ class ByteDanceSeedreamNode(IO.ComfyNode):
f"Minimum image resolution that the selected model can generate is 0.92MP, "
f"but {mp_provided:.2f}MP provided."
)
max_pixels = 10_404_496 if "seedream-5-0" in model else 16_777_216
if out_num_pixels > max_pixels:
raise ValueError(
f"Maximum image resolution for the selected model is {max_pixels / 1_000_000:.2f}MP, "
f"but {mp_provided:.2f}MP provided."
)
n_input_images = get_number_of_images(image) if image is not None else 0
if n_input_images > 10:
raise ValueError(f"Maximum of 10 reference images are supported, but {n_input_images} received.")
max_num_of_images = 14 if model == "seedream-5-0-260128" else 10
if n_input_images > max_num_of_images:
raise ValueError(
f"Maximum of {max_num_of_images} reference images are supported, but {n_input_images} received."
)
if sequential_image_generation == "auto" and n_input_images + max_images > 15:
raise ValueError(
"The maximum number of generated images plus the number of reference images cannot exceed 15."
@ -364,6 +377,7 @@ class ByteDanceSeedreamNode(IO.ComfyNode):
sequential_image_generation=sequential_image_generation,
sequential_image_generation_options=Seedream4Options(max_images=max_images),
watermark=watermark,
output_format="png" if model == "seedream-5-0-260128" else None,
),
)
if len(response.data) == 1:

247
comfy_api_nodes/nodes_gemini.py
View File

@ -29,6 +29,7 @@ from comfy_api_nodes.apis.gemini import (
GeminiRole,
GeminiSystemInstructionContent,
GeminiTextPart,
GeminiThinkingConfig,
Modality,
)
from comfy_api_nodes.util import (
@ -55,17 +56,20 @@ GEMINI_IMAGE_SYS_PROMPT = (
"Prioritize generating the visual representation above any text, formatting, or conversational requests."
)
class GeminiModel(str, Enum):
"""
Gemini Model Names allowed by comfy-api
"""
gemini_2_5_pro_preview_05_06 = "gemini-2.5-pro-preview-05-06"
gemini_2_5_flash_preview_04_17 = "gemini-2.5-flash-preview-04-17"
gemini_2_5_pro = "gemini-2.5-pro"
gemini_2_5_flash = "gemini-2.5-flash"
gemini_3_0_pro = "gemini-3-pro-preview"
GEMINI_IMAGE_2_PRICE_BADGE = IO.PriceBadge(
depends_on=IO.PriceBadgeDepends(widgets=["model", "resolution"]),
expr="""
(
$m := widgets.model;
$r := widgets.resolution;
$isFlash := $contains($m, "nano banana 2");
$flashPrices := {"1k": 0.0696, "2k": 0.0696, "4k": 0.123};
$proPrices := {"1k": 0.134, "2k": 0.134, "4k": 0.24};
$prices := $isFlash ? $flashPrices : $proPrices;
{"type":"usd","usd": $lookup($prices, $r), "format":{"suffix":"/Image","approximate":true}}
)
""",
)
class GeminiImageModel(str, Enum):
@ -221,14 +225,22 @@ def calculate_tokens_price(response: GeminiGenerateContentResponse) -> float | N
input_tokens_price = 0.30
output_text_tokens_price = 2.50
output_image_tokens_price = 30.0
elif response.modelVersion == "gemini-3-pro-preview":
elif response.modelVersion in ("gemini-3-pro-preview", "gemini-3.1-pro-preview"):
input_tokens_price = 2
output_text_tokens_price = 12.0
output_image_tokens_price = 0.0
elif response.modelVersion == "gemini-3.1-flash-lite-preview":
input_tokens_price = 0.25
output_text_tokens_price = 1.50
output_image_tokens_price = 0.0
elif response.modelVersion == "gemini-3-pro-image-preview":
input_tokens_price = 2
output_text_tokens_price = 12.0
output_image_tokens_price = 120.0
elif response.modelVersion == "gemini-3.1-flash-image-preview":
input_tokens_price = 0.5
output_text_tokens_price = 3.0
output_image_tokens_price = 60.0
else:
return None
final_price = response.usageMetadata.promptTokenCount * input_tokens_price
@ -272,8 +284,16 @@ class GeminiNode(IO.ComfyNode):
),
IO.Combo.Input(
"model",
options=GeminiModel,
default=GeminiModel.gemini_2_5_pro,
options=[
"gemini-2.5-pro-preview-05-06",
"gemini-2.5-flash-preview-04-17",
"gemini-2.5-pro",
"gemini-2.5-flash",
"gemini-3-pro-preview",
"gemini-3-1-pro",
"gemini-3-1-flash-lite",
],
default="gemini-3-1-pro",
tooltip="The Gemini model to use for generating responses.",
),
IO.Int.Input(
@ -343,11 +363,16 @@ class GeminiNode(IO.ComfyNode):
"usd": [0.00125, 0.01],
"format": { "approximate": true, "separator": "-", "suffix": " per 1K tokens" }
}
: $contains($m, "gemini-3-pro-preview") ? {
: ($contains($m, "gemini-3-pro-preview") or $contains($m, "gemini-3-1-pro")) ? {
"type": "list_usd",
"usd": [0.002, 0.012],
"format": { "approximate": true, "separator": "-", "suffix": " per 1K tokens" }
}
: $contains($m, "gemini-3-1-flash-lite") ? {
"type": "list_usd",
"usd": [0.00025, 0.0015],
"format": { "approximate": true, "separator": "-", "suffix": " per 1K tokens" }
}
: {"type":"text", "text":"Token-based"}
)
""",
@ -416,12 +441,14 @@ class GeminiNode(IO.ComfyNode):
files: list[GeminiPart] | None = None,
system_prompt: str = "",
) -> IO.NodeOutput:
validate_string(prompt, strip_whitespace=False)
if model == "gemini-3-pro-preview":
model = "gemini-3.1-pro-preview" # model "gemini-3-pro-preview" will be soon deprecated by Google
elif model == "gemini-3-1-pro":
model = "gemini-3.1-pro-preview"
elif model == "gemini-3-1-flash-lite":
model = "gemini-3.1-flash-lite-preview"
# Create parts list with text prompt as the first part
parts: list[GeminiPart] = [GeminiPart(text=prompt)]
# Add other modal parts
if images is not None:
parts.extend(await create_image_parts(cls, images))
if audio is not None:
@ -686,7 +713,7 @@ class GeminiImage2(IO.ComfyNode):
),
IO.Combo.Input(
"model",
options=["gemini-3-pro-image-preview"],
options=["gemini-3-pro-image-preview", "Nano Banana 2 (Gemini 3.1 Flash Image)"],
),
IO.Int.Input(
"seed",
@ -750,19 +777,7 @@ class GeminiImage2(IO.ComfyNode):
IO.Hidden.unique_id,
],
is_api_node=True,
price_badge=IO.PriceBadge(
depends_on=IO.PriceBadgeDepends(widgets=["resolution"]),
expr="""
(
$r := widgets.resolution;
($contains($r,"1k") or $contains($r,"2k"))
? {"type":"usd","usd":0.134,"format":{"suffix":"/Image","approximate":true}}
: $contains($r,"4k")
? {"type":"usd","usd":0.24,"format":{"suffix":"/Image","approximate":true}}
: {"type":"text","text":"Token-based"}
)
""",
),
price_badge=GEMINI_IMAGE_2_PRICE_BADGE,
)
@classmethod
@ -779,6 +794,8 @@ class GeminiImage2(IO.ComfyNode):
system_prompt: str = "",
) -> IO.NodeOutput:
validate_string(prompt, strip_whitespace=True, min_length=1)
if model == "Nano Banana 2 (Gemini 3.1 Flash Image)":
model = "gemini-3.1-flash-image-preview"
parts: list[GeminiPart] = [GeminiPart(text=prompt)]
if images is not None:
@ -815,6 +832,169 @@ class GeminiImage2(IO.ComfyNode):
return IO.NodeOutput(await get_image_from_response(response), get_text_from_response(response))
class GeminiNanoBanana2(IO.ComfyNode):
@classmethod
def define_schema(cls):
return IO.Schema(
node_id="GeminiNanoBanana2",
display_name="Nano Banana 2",
category="api node/image/Gemini",
description="Generate or edit images synchronously via Google Vertex API.",
inputs=[
IO.String.Input(
"prompt",
multiline=True,
tooltip="Text prompt describing the image to generate or the edits to apply. "
"Include any constraints, styles, or details the model should follow.",
default="",
),
IO.Combo.Input(
"model",
options=["Nano Banana 2 (Gemini 3.1 Flash Image)"],
),
IO.Int.Input(
"seed",
default=42,
min=0,
max=0xFFFFFFFFFFFFFFFF,
control_after_generate=True,
tooltip="When the seed is fixed to a specific value, the model makes a best effort to provide "
"the same response for repeated requests. Deterministic output isn't guaranteed. "
"Also, changing the model or parameter settings, such as the temperature, "
"can cause variations in the response even when you use the same seed value. "
"By default, a random seed value is used.",
),
IO.Combo.Input(
"aspect_ratio",
options=[
"auto",
"1:1",
"2:3",
"3:2",
"3:4",
"4:3",
"4:5",
"5:4",
"9:16",
"16:9",
"21:9",
# "1:4",
# "4:1",
# "8:1",
# "1:8",
],
default="auto",
tooltip="If set to 'auto', matches your input image's aspect ratio; "
"if no image is provided, a 16:9 square is usually generated.",
),
IO.Combo.Input(
"resolution",
options=[
# "512px",
"1K",
"2K",
"4K",
],
tooltip="Target output resolution. For 2K/4K the native Gemini upscaler is used.",
),
IO.Combo.Input(
"response_modalities",
options=["IMAGE", "IMAGE+TEXT"],
advanced=True,
),
IO.Combo.Input(
"thinking_level",
options=["MINIMAL", "HIGH"],
),
IO.Image.Input(
"images",
optional=True,
tooltip="Optional reference image(s). "
"To include multiple images, use the Batch Images node (up to 14).",
),
IO.Custom("GEMINI_INPUT_FILES").Input(
"files",
optional=True,
tooltip="Optional file(s) to use as context for the model. "
"Accepts inputs from the Gemini Generate Content Input Files node.",
),
IO.String.Input(
"system_prompt",
multiline=True,
default=GEMINI_IMAGE_SYS_PROMPT,
optional=True,
tooltip="Foundational instructions that dictate an AI's behavior.",
advanced=True,
),
],
outputs=[
IO.Image.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=GEMINI_IMAGE_2_PRICE_BADGE,
)
@classmethod
async def execute(
cls,
prompt: str,
model: str,
seed: int,
aspect_ratio: str,
resolution: str,
response_modalities: str,
thinking_level: str,
images: Input.Image | None = None,
files: list[GeminiPart] | None = None,
system_prompt: str = "",
) -> IO.NodeOutput:
validate_string(prompt, strip_whitespace=True, min_length=1)
if model == "Nano Banana 2 (Gemini 3.1 Flash Image)":
model = "gemini-3.1-flash-image-preview"
parts: list[GeminiPart] = [GeminiPart(text=prompt)]
if images is not None:
if get_number_of_images(images) > 14:
raise ValueError("The current maximum number of supported images is 14.")
parts.extend(await create_image_parts(cls, images))
if files is not None:
parts.extend(files)
image_config = GeminiImageConfig(imageSize=resolution)
if aspect_ratio != "auto":
image_config.aspectRatio = aspect_ratio
gemini_system_prompt = None
if system_prompt:
gemini_system_prompt = GeminiSystemInstructionContent(parts=[GeminiTextPart(text=system_prompt)], role=None)
response = await sync_op(
cls,
ApiEndpoint(path=f"/proxy/vertexai/gemini/{model}", method="POST"),
data=GeminiImageGenerateContentRequest(
contents=[
GeminiContent(role=GeminiRole.user, parts=parts),
],
generationConfig=GeminiImageGenerationConfig(
responseModalities=(["IMAGE"] if response_modalities == "IMAGE" else ["TEXT", "IMAGE"]),
imageConfig=image_config,
thinkingConfig=GeminiThinkingConfig(thinkingLevel=thinking_level),
),
systemInstruction=gemini_system_prompt,
),
response_model=GeminiGenerateContentResponse,
price_extractor=calculate_tokens_price,
)
return IO.NodeOutput(await get_image_from_response(response), get_text_from_response(response))
class GeminiExtension(ComfyExtension):
@override
async def get_node_list(self) -> list[type[IO.ComfyNode]]:
@ -822,6 +1002,7 @@ class GeminiExtension(ComfyExtension):
GeminiNode,
GeminiImage,
GeminiImage2,
GeminiNanoBanana2,
GeminiInputFiles,
]

92
comfy_api_nodes/nodes_grok.py
View File

@ -27,6 +27,12 @@ from comfy_api_nodes.util import (
)
def _extract_grok_price(response) -> float | None:
if response.usage and response.usage.cost_in_usd_ticks is not None:
return response.usage.cost_in_usd_ticks / 10_000_000_000
return None
class GrokImageNode(IO.ComfyNode):
@classmethod
@ -37,7 +43,10 @@ class GrokImageNode(IO.ComfyNode):
category="api node/image/Grok",
description="Generate images using Grok based on a text prompt",
inputs=[
IO.Combo.Input("model", options=["grok-imagine-image-beta"]),
IO.Combo.Input(
"model",
options=["grok-imagine-image-pro", "grok-imagine-image", "grok-imagine-image-beta"],
),
IO.String.Input(
"prompt",
multiline=True,
@ -81,6 +90,7 @@ class GrokImageNode(IO.ComfyNode):
tooltip="Seed to determine if node should re-run; "
"actual results are nondeterministic regardless of seed.",
),
IO.Combo.Input("resolution", options=["1K", "2K"], optional=True),
],
outputs=[
IO.Image.Output(),
@ -92,8 +102,13 @@ class GrokImageNode(IO.ComfyNode):
],
is_api_node=True,
price_badge=IO.PriceBadge(
depends_on=IO.PriceBadgeDepends(widgets=["number_of_images"]),
expr="""{"type":"usd","usd":0.033 * widgets.number_of_images}""",
depends_on=IO.PriceBadgeDepends(widgets=["model", "number_of_images"]),
expr="""
(
$rate := $contains(widgets.model, "pro") ? 0.07 : 0.02;
{"type":"usd","usd": $rate * widgets.number_of_images}
)
""",
),
)
@ -105,6 +120,7 @@ class GrokImageNode(IO.ComfyNode):
aspect_ratio: str,
number_of_images: int,
seed: int,
resolution: str = "1K",
) -> IO.NodeOutput:
validate_string(prompt, strip_whitespace=True, min_length=1)
response = await sync_op(
@ -116,8 +132,10 @@ class GrokImageNode(IO.ComfyNode):
aspect_ratio=aspect_ratio,
n=number_of_images,
seed=seed,
resolution=resolution.lower(),
),
response_model=ImageGenerationResponse,
price_extractor=_extract_grok_price,
)
if len(response.data) == 1:
return IO.NodeOutput(await download_url_to_image_tensor(response.data[0].url))
@ -138,14 +156,17 @@ class GrokImageEditNode(IO.ComfyNode):
category="api node/image/Grok",
description="Modify an existing image based on a text prompt",
inputs=[
IO.Combo.Input("model", options=["grok-imagine-image-beta"]),
IO.Image.Input("image"),
IO.Combo.Input(
"model",
options=["grok-imagine-image-pro", "grok-imagine-image", "grok-imagine-image-beta"],
),
IO.Image.Input("image", display_name="images"),
IO.String.Input(
"prompt",
multiline=True,
tooltip="The text prompt used to generate the image",
),
IO.Combo.Input("resolution", options=["1K"]),
IO.Combo.Input("resolution", options=["1K", "2K"]),
IO.Int.Input(
"number_of_images",
default=1,
@ -166,6 +187,27 @@ class GrokImageEditNode(IO.ComfyNode):
tooltip="Seed to determine if node should re-run; "
"actual results are nondeterministic regardless of seed.",
),
IO.Combo.Input(
"aspect_ratio",
options=[
"auto",
"1:1",
"2:3",
"3:2",
"3:4",
"4:3",
"9:16",
"16:9",
"9:19.5",
"19.5:9",
"9:20",
"20:9",
"1:2",
"2:1",
],
optional=True,
tooltip="Only allowed when multiple images are connected to the image input.",
),
],
outputs=[
IO.Image.Output(),
@ -177,8 +219,13 @@ class GrokImageEditNode(IO.ComfyNode):
],
is_api_node=True,
price_badge=IO.PriceBadge(
depends_on=IO.PriceBadgeDepends(widgets=["number_of_images"]),
expr="""{"type":"usd","usd":0.002 + 0.033 * widgets.number_of_images}""",
depends_on=IO.PriceBadgeDepends(widgets=["model", "number_of_images"]),
expr="""
(
$rate := $contains(widgets.model, "pro") ? 0.07 : 0.02;
{"type":"usd","usd": 0.002 + $rate * widgets.number_of_images}
)
""",
),
)
@ -191,22 +238,32 @@ class GrokImageEditNode(IO.ComfyNode):
resolution: str,
number_of_images: int,
seed: int,
aspect_ratio: str = "auto",
) -> IO.NodeOutput:
validate_string(prompt, strip_whitespace=True, min_length=1)
if get_number_of_images(image) != 1:
raise ValueError("Only one input image is supported.")
if model == "grok-imagine-image-pro":
if get_number_of_images(image) > 1:
raise ValueError("The pro model supports only 1 input image.")
elif get_number_of_images(image) > 3:
raise ValueError("A maximum of 3 input images is supported.")
if aspect_ratio != "auto" and get_number_of_images(image) == 1:
raise ValueError(
"Custom aspect ratio is only allowed when multiple images are connected to the image input."
)
response = await sync_op(
cls,
ApiEndpoint(path="/proxy/xai/v1/images/edits", method="POST"),
data=ImageEditRequest(
model=model,
image=InputUrlObject(url=f"data:image/png;base64,{tensor_to_base64_string(image)}"),
images=[InputUrlObject(url=f"data:image/png;base64,{tensor_to_base64_string(i)}") for i in image],
prompt=prompt,
resolution=resolution.lower(),
n=number_of_images,
seed=seed,
aspect_ratio=None if aspect_ratio == "auto" else aspect_ratio,
),
response_model=ImageGenerationResponse,
price_extractor=_extract_grok_price,
)
if len(response.data) == 1:
return IO.NodeOutput(await download_url_to_image_tensor(response.data[0].url))
@ -227,7 +284,7 @@ class GrokVideoNode(IO.ComfyNode):
category="api node/video/Grok",
description="Generate video from a prompt or an image",
inputs=[
IO.Combo.Input("model", options=["grok-imagine-video-beta"]),
IO.Combo.Input("model", options=["grok-imagine-video", "grok-imagine-video-beta"]),
IO.String.Input(
"prompt",
multiline=True,
@ -275,10 +332,11 @@ class GrokVideoNode(IO.ComfyNode):
],
is_api_node=True,
price_badge=IO.PriceBadge(
depends_on=IO.PriceBadgeDepends(widgets=["duration"], inputs=["image"]),
depends_on=IO.PriceBadgeDepends(widgets=["duration", "resolution"], inputs=["image"]),
expr="""
(
$base := 0.181 * widgets.duration;
$rate := widgets.resolution = "720p" ? 0.07 : 0.05;
$base := $rate * widgets.duration;
{"type":"usd","usd": inputs.image.connected ? $base + 0.002 : $base}
)
""",
@ -321,6 +379,7 @@ class GrokVideoNode(IO.ComfyNode):
ApiEndpoint(path=f"/proxy/xai/v1/videos/{initial_response.request_id}"),
status_extractor=lambda r: r.status if r.status is not None else "complete",
response_model=VideoStatusResponse,
price_extractor=_extract_grok_price,
)
return IO.NodeOutput(await download_url_to_video_output(response.video.url))
@ -335,7 +394,7 @@ class GrokVideoEditNode(IO.ComfyNode):
category="api node/video/Grok",
description="Edit an existing video based on a text prompt.",
inputs=[
IO.Combo.Input("model", options=["grok-imagine-video-beta"]),
IO.Combo.Input("model", options=["grok-imagine-video", "grok-imagine-video-beta"]),
IO.String.Input(
"prompt",
multiline=True,
@ -364,7 +423,7 @@ class GrokVideoEditNode(IO.ComfyNode):
],
is_api_node=True,
price_badge=IO.PriceBadge(
expr="""{"type":"usd","usd": 0.191, "format": {"suffix": "/sec", "approximate": true}}""",
expr="""{"type":"usd","usd": 0.06, "format": {"suffix": "/sec", "approximate": true}}""",
),
)
@ -398,6 +457,7 @@ class GrokVideoEditNode(IO.ComfyNode):
ApiEndpoint(path=f"/proxy/xai/v1/videos/{initial_response.request_id}"),
status_extractor=lambda r: r.status if r.status is not None else "complete",
response_model=VideoStatusResponse,
price_extractor=_extract_grok_price,
)
return IO.NodeOutput(await download_url_to_video_output(response.video.url))

204
comfy_api_nodes/nodes_hunyuan3d.py
View File

@ -1,3 +1,7 @@
import zipfile
from io import BytesIO
import torch
from typing_extensions import override
from comfy_api.latest import IO, ComfyExtension, Input, Types
@ -5,16 +9,20 @@ from comfy_api_nodes.apis.hunyuan3d import (
Hunyuan3DViewImage,
InputGenerateType,
ResultFile3D,
SmartTopologyRequest,
TaskFile3DInput,
TextureEditTaskRequest,
To3DPartTaskRequest,
To3DProTaskCreateResponse,
To3DProTaskQueryRequest,
To3DProTaskRequest,
To3DProTaskResultResponse,
To3DUVFileInput,
To3DUVTaskRequest,
)
from comfy_api_nodes.util import (
ApiEndpoint,
bytesio_to_image_tensor,
download_url_to_bytesio,
download_url_to_file_3d,
download_url_to_image_tensor,
downscale_image_tensor_by_max_side,
@ -35,6 +43,68 @@ def _is_tencent_rate_limited(status: int, body: object) -> bool:
)
class ObjZipResult:
__slots__ = ("obj", "texture", "metallic", "normal", "roughness")
def __init__(
self,
obj: Types.File3D,
texture: Input.Image | None = None,
metallic: Input.Image | None = None,
normal: Input.Image | None = None,
roughness: Input.Image | None = None,
):
self.obj = obj
self.texture = texture
self.metallic = metallic
self.normal = normal
self.roughness = roughness
async def download_and_extract_obj_zip(url: str) -> ObjZipResult:
"""The Tencent API returns OBJ results as ZIP archives containing the .obj mesh, and texture images.
When PBR is enabled, the ZIP may contain additional metallic, normal, and roughness maps
identified by their filename suffixes.
"""
data = BytesIO()
await download_url_to_bytesio(url, data)
data.seek(0)
if not zipfile.is_zipfile(data):
data.seek(0)
return ObjZipResult(obj=Types.File3D(source=data, file_format="obj"))
data.seek(0)
obj_bytes = None
textures: dict[str, Input.Image] = {}
with zipfile.ZipFile(data) as zf:
for name in zf.namelist():
lower = name.lower()
if lower.endswith(".obj"):
obj_bytes = zf.read(name)
elif any(lower.endswith(ext) for ext in (".png", ".jpg", ".jpeg", ".bmp", ".tiff", ".webp")):
stem = lower.rsplit(".", 1)[0]
tensor = bytesio_to_image_tensor(BytesIO(zf.read(name)), mode="RGB")
matched_key = "texture"
for suffix, key in {
"_metallic": "metallic",
"_normal": "normal",
"_roughness": "roughness",
}.items():
if stem.endswith(suffix):
matched_key = key
break
textures[matched_key] = tensor
if obj_bytes is None:
raise ValueError("ZIP archive does not contain an OBJ file.")
return ObjZipResult(
obj=Types.File3D(source=BytesIO(obj_bytes), file_format="obj"),
texture=textures.get("texture"),
metallic=textures.get("metallic"),
normal=textures.get("normal"),
roughness=textures.get("roughness"),
)
def get_file_from_response(
response_objs: list[ResultFile3D], file_type: str, raise_if_not_found: bool = True
) -> ResultFile3D | None:
@ -92,6 +162,7 @@ class TencentTextToModelNode(IO.ComfyNode):
IO.String.Output(display_name="model_file"), # for backward compatibility only
IO.File3DGLB.Output(display_name="GLB"),
IO.File3DOBJ.Output(display_name="OBJ"),
IO.Image.Output(display_name="texture_image"),
],
hidden=[
IO.Hidden.auth_token_comfy_org,
@ -150,14 +221,14 @@ class TencentTextToModelNode(IO.ComfyNode):
response_model=To3DProTaskResultResponse,
status_extractor=lambda r: r.Status,
)
obj_result = await download_and_extract_obj_zip(get_file_from_response(result.ResultFile3Ds, "obj").Url)
return IO.NodeOutput(
f"{task_id}.glb",
await download_url_to_file_3d(
get_file_from_response(result.ResultFile3Ds, "glb").Url, "glb", task_id=task_id
),
await download_url_to_file_3d(
get_file_from_response(result.ResultFile3Ds, "obj").Url, "obj", task_id=task_id
),
obj_result.obj,
obj_result.texture,
)
@ -210,6 +281,10 @@ class TencentImageToModelNode(IO.ComfyNode):
IO.String.Output(display_name="model_file"), # for backward compatibility only
IO.File3DGLB.Output(display_name="GLB"),
IO.File3DOBJ.Output(display_name="OBJ"),
IO.Image.Output(display_name="texture_image"),
IO.Image.Output(display_name="optional_metallic"),
IO.Image.Output(display_name="optional_normal"),
IO.Image.Output(display_name="optional_roughness"),
],
hidden=[
IO.Hidden.auth_token_comfy_org,
@ -303,14 +378,17 @@ class TencentImageToModelNode(IO.ComfyNode):
response_model=To3DProTaskResultResponse,
status_extractor=lambda r: r.Status,
)
obj_result = await download_and_extract_obj_zip(get_file_from_response(result.ResultFile3Ds, "obj").Url)
return IO.NodeOutput(
f"{task_id}.glb",
await download_url_to_file_3d(
get_file_from_response(result.ResultFile3Ds, "glb").Url, "glb", task_id=task_id
),
await download_url_to_file_3d(
get_file_from_response(result.ResultFile3Ds, "obj").Url, "obj", task_id=task_id
),
obj_result.obj,
obj_result.texture,
obj_result.metallic if obj_result.metallic is not None else torch.zeros(1, 1, 1, 3),
obj_result.normal if obj_result.normal is not None else torch.zeros(1, 1, 1, 3),
obj_result.roughness if obj_result.roughness is not None else torch.zeros(1, 1, 1, 3),
)
@ -344,7 +422,6 @@ class TencentModelTo3DUVNode(IO.ComfyNode):
outputs=[
IO.File3DOBJ.Output(display_name="OBJ"),
IO.File3DFBX.Output(display_name="FBX"),
IO.Image.Output(),
],
hidden=[
IO.Hidden.auth_token_comfy_org,
@ -375,7 +452,7 @@ class TencentModelTo3DUVNode(IO.ComfyNode):
ApiEndpoint(path="/proxy/tencent/hunyuan/3d-uv", method="POST"),
response_model=To3DProTaskCreateResponse,
data=To3DUVTaskRequest(
File=To3DUVFileInput(
File=TaskFile3DInput(
Type=file_format.upper(),
Url=await upload_3d_model_to_comfyapi(cls, model_3d, file_format),
)
@ -394,7 +471,6 @@ class TencentModelTo3DUVNode(IO.ComfyNode):
return IO.NodeOutput(
await download_url_to_file_3d(get_file_from_response(result.ResultFile3Ds, "obj").Url, "obj"),
await download_url_to_file_3d(get_file_from_response(result.ResultFile3Ds, "fbx").Url, "fbx"),
await download_url_to_image_tensor(get_file_from_response(result.ResultFile3Ds, "image").Url),
)
@ -432,7 +508,8 @@ class Tencent3DTextureEditNode(IO.ComfyNode):
],
outputs=[
IO.File3DGLB.Output(display_name="GLB"),
IO.File3DFBX.Output(display_name="FBX"),
IO.File3DOBJ.Output(display_name="OBJ"),
IO.Image.Output(display_name="texture_image"),
],
hidden=[
IO.Hidden.auth_token_comfy_org,
@ -463,7 +540,7 @@ class Tencent3DTextureEditNode(IO.ComfyNode):
ApiEndpoint(path="/proxy/tencent/hunyuan/3d-texture-edit", method="POST"),
response_model=To3DProTaskCreateResponse,
data=TextureEditTaskRequest(
File3D=To3DUVFileInput(Type=file_format.upper(), Url=model_url),
File3D=TaskFile3DInput(Type=file_format.upper(), Url=model_url),
Prompt=prompt,
EnablePBR=True,
),
@ -481,7 +558,8 @@ class Tencent3DTextureEditNode(IO.ComfyNode):
)
return IO.NodeOutput(
await download_url_to_file_3d(get_file_from_response(result.ResultFile3Ds, "glb").Url, "glb"),
await download_url_to_file_3d(get_file_from_response(result.ResultFile3Ds, "fbx").Url, "fbx"),
await download_url_to_file_3d(get_file_from_response(result.ResultFile3Ds, "obj").Url, "obj"),
await download_url_to_image_tensor(get_file_from_response(result.ResultFile3Ds, "texture_image").Url),
)
@ -538,8 +616,8 @@ class Tencent3DPartNode(IO.ComfyNode):
cls,
ApiEndpoint(path="/proxy/tencent/hunyuan/3d-part", method="POST"),
response_model=To3DProTaskCreateResponse,
data=To3DUVTaskRequest(
File=To3DUVFileInput(Type=file_format.upper(), Url=model_url),
data=To3DPartTaskRequest(
File=TaskFile3DInput(Type=file_format.upper(), Url=model_url),
),
is_rate_limited=_is_tencent_rate_limited,
)
@ -557,15 +635,107 @@ class Tencent3DPartNode(IO.ComfyNode):
)
class TencentSmartTopologyNode(IO.ComfyNode):
@classmethod
def define_schema(cls):
return IO.Schema(
node_id="TencentSmartTopologyNode",
display_name="Hunyuan3D: Smart Topology",
category="api node/3d/Tencent",
description="Perform smart retopology on a 3D model. "
"Supports GLB/OBJ formats; max 200MB; recommended for high-poly models.",
inputs=[
IO.MultiType.Input(
"model_3d",
types=[IO.File3DGLB, IO.File3DOBJ, IO.File3DAny],
tooltip="Input 3D model (GLB or OBJ)",
),
IO.Combo.Input(
"polygon_type",
options=["triangle", "quadrilateral"],
tooltip="Surface composition type.",
),
IO.Combo.Input(
"face_level",
options=["medium", "high", "low"],
tooltip="Polygon reduction level.",
),
IO.Int.Input(
"seed",
default=0,
min=0,
max=2147483647,
display_mode=IO.NumberDisplay.number,
control_after_generate=True,
tooltip="Seed controls whether the node should re-run; "
"results are non-deterministic regardless of seed.",
),
],
outputs=[
IO.File3DOBJ.Output(display_name="OBJ"),
],
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":1.0}'),
)
SUPPORTED_FORMATS = {"glb", "obj"}
@classmethod
async def execute(
cls,
model_3d: Types.File3D,
polygon_type: str,
face_level: str,
seed: int,
) -> IO.NodeOutput:
_ = seed
file_format = model_3d.format.lower()
if file_format not in cls.SUPPORTED_FORMATS:
raise ValueError(
f"Unsupported file format: '{file_format}'. " f"Supported: {', '.join(sorted(cls.SUPPORTED_FORMATS))}."
)
model_url = await upload_3d_model_to_comfyapi(cls, model_3d, file_format)
response = await sync_op(
cls,
ApiEndpoint(path="/proxy/tencent/hunyuan/3d-smart-topology", method="POST"),
response_model=To3DProTaskCreateResponse,
data=SmartTopologyRequest(
File3D=TaskFile3DInput(Type=file_format.upper(), Url=model_url),
PolygonType=polygon_type,
FaceLevel=face_level,
),
is_rate_limited=_is_tencent_rate_limited,
)
if response.Error:
raise ValueError(f"Task creation failed: [{response.Error.Code}] {response.Error.Message}")
result = await poll_op(
cls,
ApiEndpoint(path="/proxy/tencent/hunyuan/3d-smart-topology/query", method="POST"),
data=To3DProTaskQueryRequest(JobId=response.JobId),
response_model=To3DProTaskResultResponse,
status_extractor=lambda r: r.Status,
)
return IO.NodeOutput(
await download_url_to_file_3d(get_file_from_response(result.ResultFile3Ds, "obj").Url, "obj"),
)
class TencentHunyuan3DExtension(ComfyExtension):
@override
async def get_node_list(self) -> list[type[IO.ComfyNode]]:
return [
TencentTextToModelNode,
TencentImageToModelNode,
# TencentModelTo3DUVNode,
# Tencent3DTextureEditNode,
TencentModelTo3DUVNode,
Tencent3DTextureEditNode,
Tencent3DPartNode,
TencentSmartTopologyNode,
]

103
comfy_api_nodes/nodes_kling.py
View File

@ -50,6 +50,7 @@ from comfy_api_nodes.apis import (
)
from comfy_api_nodes.apis.kling import (
ImageToVideoWithAudioRequest,
KlingAvatarRequest,
MotionControlRequest,
MultiPromptEntry,
OmniImageParamImage,
@ -74,6 +75,7 @@ from comfy_api_nodes.util import (
upload_image_to_comfyapi,
upload_images_to_comfyapi,
upload_video_to_comfyapi,
validate_audio_duration,
validate_image_aspect_ratio,
validate_image_dimensions,
validate_string,
@ -2746,6 +2748,7 @@ class MotionControl(IO.ComfyNode):
"but the character orientation matches the reference image (camera/other details via prompt).",
),
IO.Combo.Input("mode", options=["pro", "std"]),
IO.Combo.Input("model", options=["kling-v3", "kling-v2-6"], optional=True),
],
outputs=[
IO.Video.Output(),
@ -2776,6 +2779,7 @@ class MotionControl(IO.ComfyNode):
keep_original_sound: bool,
character_orientation: str,
mode: str,
model: str = "kling-v2-6",
) -> IO.NodeOutput:
validate_string(prompt, max_length=2500)
validate_image_dimensions(reference_image, min_width=340, min_height=340)
@ -2796,6 +2800,7 @@ class MotionControl(IO.ComfyNode):
keep_original_sound="yes" if keep_original_sound else "no",
character_orientation=character_orientation,
mode=mode,
model_name=model,
),
)
if response.code:
@ -3140,6 +3145,103 @@ class KlingFirstLastFrameNode(IO.ComfyNode):
return IO.NodeOutput(await download_url_to_video_output(final_response.data.task_result.videos[0].url))
class KlingAvatarNode(IO.ComfyNode):
@classmethod
def define_schema(cls) -> IO.Schema:
return IO.Schema(
node_id="KlingAvatarNode",
display_name="Kling Avatar 2.0",
category="api node/video/Kling",
description="Generate broadcast-style digital human videos from a single photo and an audio file.",
inputs=[
IO.Image.Input(
"image",
tooltip="Avatar reference image. "
"Width and height must be at least 300px. Aspect ratio must be between 1:2.5 and 2.5:1.",
),
IO.Audio.Input(
"sound_file",
tooltip="Audio input. Must be between 2 and 300 seconds in duration.",
),
IO.Combo.Input("mode", options=["std", "pro"]),
IO.String.Input(
"prompt",
multiline=True,
default="",
optional=True,
tooltip="Optional prompt to define avatar actions, emotions, and camera movements.",
),
IO.Int.Input(
"seed",
default=0,
min=0,
max=2147483647,
display_mode=IO.NumberDisplay.number,
control_after_generate=True,
tooltip="Seed controls whether the node should re-run; "
"results are non-deterministic regardless of seed.",
),
],
outputs=[
IO.Video.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=["mode"]),
expr="""
(
$prices := {"std": 0.056, "pro": 0.112};
{"type":"usd","usd": $lookup($prices, widgets.mode), "format":{"suffix":"/second"}}
)
""",
),
)
@classmethod
async def execute(
cls,
image: Input.Image,
sound_file: Input.Audio,
mode: str,
seed: int,
prompt: str = "",
) -> IO.NodeOutput:
validate_image_dimensions(image, min_width=300, min_height=300)
validate_image_aspect_ratio(image, (1, 2.5), (2.5, 1))
validate_audio_duration(sound_file, min_duration=2, max_duration=300)
response = await sync_op(
cls,
ApiEndpoint(path="/proxy/kling/v1/videos/avatar/image2video", method="POST"),
response_model=TaskStatusResponse,
data=KlingAvatarRequest(
image=await upload_image_to_comfyapi(cls, image),
sound_file=await upload_audio_to_comfyapi(
cls, sound_file, container_format="mp3", codec_name="libmp3lame", mime_type="audio/mpeg"
),
prompt=prompt or None,
mode=mode,
),
)
if response.code:
raise RuntimeError(
f"Kling request failed. Code: {response.code}, Message: {response.message}, Data: {response.data}"
)
final_response = await poll_op(
cls,
ApiEndpoint(path=f"/proxy/kling/v1/videos/avatar/image2video/{response.data.task_id}"),
response_model=TaskStatusResponse,
status_extractor=lambda r: (r.data.task_status if r.data else None),
max_poll_attempts=800,
)
return IO.NodeOutput(await download_url_to_video_output(final_response.data.task_result.videos[0].url))
class KlingExtension(ComfyExtension):
@override
async def get_node_list(self) -> list[type[IO.ComfyNode]]:
@ -3168,6 +3270,7 @@ class KlingExtension(ComfyExtension):
MotionControl,
KlingVideoNode,
KlingFirstLastFrameNode,
KlingAvatarNode,
]

395
comfy_api_nodes/nodes_reve.py Normal file
View File

@ -0,0 +1,395 @@
from io import BytesIO
from typing_extensions import override
from comfy_api.latest import IO, ComfyExtension, Input
from comfy_api_nodes.apis.reve import (
ReveImageCreateRequest,
ReveImageEditRequest,
ReveImageRemixRequest,
RevePostprocessingOperation,
)
from comfy_api_nodes.util import (
ApiEndpoint,
bytesio_to_image_tensor,
sync_op_raw,
tensor_to_base64_string,
validate_string,
)
def _build_postprocessing(upscale: dict, remove_background: bool) -> list[RevePostprocessingOperation] | None:
ops = []
if upscale["upscale"] == "enabled":
ops.append(
RevePostprocessingOperation(
process="upscale",
upscale_factor=upscale["upscale_factor"],
)
)
if remove_background:
ops.append(RevePostprocessingOperation(process="remove_background"))
return ops or None
def _postprocessing_inputs():
return [
IO.DynamicCombo.Input(
"upscale",
options=[
IO.DynamicCombo.Option("disabled", []),
IO.DynamicCombo.Option(
"enabled",
[
IO.Int.Input(
"upscale_factor",
default=2,
min=2,
max=4,
step=1,
tooltip="Upscale factor (2x, 3x, or 4x).",
),
],
),
],
tooltip="Upscale the generated image. May add additional cost.",
),
IO.Boolean.Input(
"remove_background",
default=False,
tooltip="Remove the background from the generated image. May add additional cost.",
),
]
def _reve_price_extractor(headers: dict) -> float | None:
credits_used = headers.get("x-reve-credits-used")
if credits_used is not None:
return float(credits_used) / 524.48
return None
def _reve_response_header_validator(headers: dict) -> None:
error_code = headers.get("x-reve-error-code")
if error_code:
raise ValueError(f"Reve API error: {error_code}")
if headers.get("x-reve-content-violation", "").lower() == "true":
raise ValueError("The generated image was flagged for content policy violation.")
def _model_inputs(versions: list[str], aspect_ratios: list[str]):
return [
IO.DynamicCombo.Option(
version,
[
IO.Combo.Input(
"aspect_ratio",
options=aspect_ratios,
tooltip="Aspect ratio of the output image.",
),
IO.Int.Input(
"test_time_scaling",
default=1,
min=1,
max=5,
step=1,
tooltip="Higher values produce better images but cost more credits.",
advanced=True,
),
],
)
for version in versions
]
class ReveImageCreateNode(IO.ComfyNode):
@classmethod
def define_schema(cls):
return IO.Schema(
node_id="ReveImageCreateNode",
display_name="Reve Image Create",
category="api node/image/Reve",
description="Generate images from text descriptions using Reve.",
inputs=[
IO.String.Input(
"prompt",
multiline=True,
default="",
tooltip="Text description of the desired image. Maximum 2560 characters.",
),
IO.DynamicCombo.Input(
"model",
options=_model_inputs(
["reve-create@20250915"],
aspect_ratios=["3:2", "16:9", "9:16", "2:3", "4:3", "3:4", "1:1"],
),
tooltip="Model version to use for generation.",
),
*_postprocessing_inputs(),
IO.Int.Input(
"seed",
default=0,
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.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":0.03432,"format":{"approximate":true,"note":"(base)"}}""",
),
)
@classmethod
async def execute(
cls,
prompt: str,
model: dict,
upscale: dict,
remove_background: bool,
seed: int,
) -> IO.NodeOutput:
validate_string(prompt, min_length=1, max_length=2560)
response = await sync_op_raw(
cls,
ApiEndpoint(
path="/proxy/reve/v1/image/create",
method="POST",
headers={"Accept": "image/webp"},
),
as_binary=True,
price_extractor=_reve_price_extractor,
response_header_validator=_reve_response_header_validator,
data=ReveImageCreateRequest(
prompt=prompt,
aspect_ratio=model["aspect_ratio"],
version=model["model"],
test_time_scaling=model["test_time_scaling"],
postprocessing=_build_postprocessing(upscale, remove_background),
),
)
return IO.NodeOutput(bytesio_to_image_tensor(BytesIO(response)))
class ReveImageEditNode(IO.ComfyNode):
@classmethod
def define_schema(cls):
return IO.Schema(
node_id="ReveImageEditNode",
display_name="Reve Image Edit",
category="api node/image/Reve",
description="Edit images using natural language instructions with Reve.",
inputs=[
IO.Image.Input("image", tooltip="The image to edit."),
IO.String.Input(
"edit_instruction",
multiline=True,
default="",
tooltip="Text description of how to edit the image. Maximum 2560 characters.",
),
IO.DynamicCombo.Input(
"model",
options=_model_inputs(
["reve-edit@20250915", "reve-edit-fast@20251030"],
aspect_ratios=["auto", "16:9", "9:16", "3:2", "2:3", "4:3", "3:4", "1:1"],
),
tooltip="Model version to use for editing.",
),
*_postprocessing_inputs(),
IO.Int.Input(
"seed",
default=0,
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.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="""
(
$isFast := $contains(widgets.model, "fast");
$base := $isFast ? 0.01001 : 0.0572;
{"type": "usd", "usd": $base, "format": {"approximate": true, "note": "(base)"}}
)
""",
),
)
@classmethod
async def execute(
cls,
image: Input.Image,
edit_instruction: str,
model: dict,
upscale: dict,
remove_background: bool,
seed: int,
) -> IO.NodeOutput:
validate_string(edit_instruction, min_length=1, max_length=2560)
tts = model["test_time_scaling"]
ar = model["aspect_ratio"]
response = await sync_op_raw(
cls,
ApiEndpoint(
path="/proxy/reve/v1/image/edit",
method="POST",
headers={"Accept": "image/webp"},
),
as_binary=True,
price_extractor=_reve_price_extractor,
response_header_validator=_reve_response_header_validator,
data=ReveImageEditRequest(
edit_instruction=edit_instruction,
reference_image=tensor_to_base64_string(image),
aspect_ratio=ar if ar != "auto" else None,
version=model["model"],
test_time_scaling=tts if tts and tts > 1 else None,
postprocessing=_build_postprocessing(upscale, remove_background),
),
)
return IO.NodeOutput(bytesio_to_image_tensor(BytesIO(response)))
class ReveImageRemixNode(IO.ComfyNode):
@classmethod
def define_schema(cls):
return IO.Schema(
node_id="ReveImageRemixNode",
display_name="Reve Image Remix",
category="api node/image/Reve",
description="Combine reference images with text prompts to create new images using Reve.",
inputs=[
IO.Autogrow.Input(
"reference_images",
template=IO.Autogrow.TemplatePrefix(
IO.Image.Input("image"),
prefix="image_",
min=1,
max=6,
),
),
IO.String.Input(
"prompt",
multiline=True,
default="",
tooltip="Text description of the desired image. "
"May include XML img tags to reference specific images by index, "
"e.g. <img>0</img>, <img>1</img>, etc.",
),
IO.DynamicCombo.Input(
"model",
options=_model_inputs(
["reve-remix@20250915", "reve-remix-fast@20251030"],
aspect_ratios=["auto", "16:9", "9:16", "3:2", "2:3", "4:3", "3:4", "1:1"],
),
tooltip="Model version to use for remixing.",
),
*_postprocessing_inputs(),
IO.Int.Input(
"seed",
default=0,
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.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="""
(
$isFast := $contains(widgets.model, "fast");
$base := $isFast ? 0.01001 : 0.0572;
{"type": "usd", "usd": $base, "format": {"approximate": true, "note": "(base)"}}
)
""",
),
)
@classmethod
async def execute(
cls,
reference_images: IO.Autogrow.Type,
prompt: str,
model: dict,
upscale: dict,
remove_background: bool,
seed: int,
) -> IO.NodeOutput:
validate_string(prompt, min_length=1, max_length=2560)
if not reference_images:
raise ValueError("At least one reference image is required.")
ref_base64_list = []
for key in reference_images:
ref_base64_list.append(tensor_to_base64_string(reference_images[key]))
if len(ref_base64_list) > 6:
raise ValueError("Maximum 6 reference images are allowed.")
tts = model["test_time_scaling"]
ar = model["aspect_ratio"]
response = await sync_op_raw(
cls,
ApiEndpoint(
path="/proxy/reve/v1/image/remix",
method="POST",
headers={"Accept": "image/webp"},
),
as_binary=True,
price_extractor=_reve_price_extractor,
response_header_validator=_reve_response_header_validator,
data=ReveImageRemixRequest(
prompt=prompt,
reference_images=ref_base64_list,
aspect_ratio=ar if ar != "auto" else None,
version=model["model"],
test_time_scaling=tts if tts and tts > 1 else None,
postprocessing=_build_postprocessing(upscale, remove_background),
),
)
return IO.NodeOutput(bytesio_to_image_tensor(BytesIO(response)))
class ReveExtension(ComfyExtension):
@override
async def get_node_list(self) -> list[type[IO.ComfyNode]]:
return [
ReveImageCreateNode,
ReveImageEditNode,
ReveImageRemixNode,
]
async def comfy_entrypoint() -> ReveExtension:
return ReveExtension()

14
comfy_api_nodes/util/client.py
View File

@ -67,6 +67,7 @@ class _RequestConfig:
progress_origin_ts: float | None = None
price_extractor: Callable[[dict[str, Any]], float | None] | None = None
is_rate_limited: Callable[[int, Any], bool] | None = None
response_header_validator: Callable[[dict[str, str]], None] | None = None
@dataclass
@ -83,7 +84,7 @@ class _PollUIState:
_RETRY_STATUS = {408, 500, 502, 503, 504} # status 429 is handled separately
COMPLETED_STATUSES = ["succeeded", "succeed", "success", "completed", "finished", "done", "complete"]
FAILED_STATUSES = ["cancelled", "canceled", "canceling", "fail", "failed", "error"]
QUEUED_STATUSES = ["created", "queued", "queueing", "submitted", "initializing"]
QUEUED_STATUSES = ["created", "queued", "queueing", "submitted", "initializing", "wait"]
async def sync_op(
@ -202,11 +203,13 @@ async def sync_op_raw(
monitor_progress: bool = True,
max_retries_on_rate_limit: int = 16,
is_rate_limited: Callable[[int, Any], bool] | None = None,
response_header_validator: Callable[[dict[str, str]], None] | None = None,
) -> dict[str, Any] | bytes:
"""
Make a single network request.
- If as_binary=False (default): returns JSON dict (or {'_raw': '<text>'} if non-JSON).
- If as_binary=True: returns bytes.
- response_header_validator: optional callback receiving response headers dict
"""
if isinstance(data, BaseModel):
data = data.model_dump(exclude_none=True)
@ -232,6 +235,7 @@ async def sync_op_raw(
price_extractor=price_extractor,
max_retries_on_rate_limit=max_retries_on_rate_limit,
is_rate_limited=is_rate_limited,
response_header_validator=response_header_validator,
)
return await _request_base(cfg, expect_binary=as_binary)
@ -769,6 +773,12 @@ async def _request_base(cfg: _RequestConfig, expect_binary: bool):
cfg.node_cls, cfg.wait_label, int(now - start_time), cfg.estimated_total
)
bytes_payload = bytes(buff)
resp_headers = {k.lower(): v for k, v in resp.headers.items()}
if cfg.price_extractor:
with contextlib.suppress(Exception):
extracted_price = cfg.price_extractor(resp_headers)
if cfg.response_header_validator:
cfg.response_header_validator(resp_headers)
operation_succeeded = True
final_elapsed_seconds = int(time.monotonic() - start_time)
request_logger.log_request_response(
@ -776,7 +786,7 @@ async def _request_base(cfg: _RequestConfig, expect_binary: bool):
request_method=method,
request_url=url,
response_status_code=resp.status,
response_headers=dict(resp.headers),
response_headers=resp_headers,
response_content=bytes_payload,
)
return bytes_payload