andreas/ComfyUI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat(api-nodes): network client v2: async ops, cancellation, downloads, refactor (#10390)

Browse Source 
* feat(api-nodes): implement new API client for V3 nodes

* feat(api-nodes): implement new API client for V3 nodes

* feat(api-nodes): implement new API client for V3 nodes

* converted WAN nodes to use new client; polishing

* fix(auth): do not leak authentification for the absolute urls

* convert BFL API nodes to use new API client; remove deprecated BFL nodes

* converted Google Veo nodes

* fix(Veo3.1 model): take into account "generate_audio" parameter
This commit is contained in:
Alexander Piskun
2025-10-24 08:37:16 +03:00
committed by GitHub
parent 24188b3141
commit 388b306a2b
29 changed files with 2935 additions and 2298 deletions
Download Patch File Download Diff File Expand all files Collapse all files

245
comfy_api_nodes/nodes_wan.py
View File

@@ -1,28 +1,24 @@
import re
from typing import Optional, Type, Union
from typing_extensions import override
from typing import Optional
import torch
from pydantic import BaseModel, Field
from comfy_api.latest import ComfyExtension, Input, IO
from comfy_api_nodes.apis.client import (
ApiEndpoint,
HttpMethod,
SynchronousOperation,
PollingOperation,
EmptyRequest,
R,
T,
)
from comfy_api_nodes.util.validation_utils import get_number_of_images, validate_audio_duration
from typing_extensions import override
from comfy_api_nodes.apinode_utils import (
from comfy_api.latest import IO, ComfyExtension, Input
from comfy_api_nodes.util import (
ApiEndpoint,
audio_to_base64_string,
download_url_to_image_tensor,
download_url_to_video_output,
get_number_of_images,
poll_op,
sync_op,
tensor_to_base64_string,
audio_to_base64_string,
validate_audio_duration,
)
class Text2ImageInputField(BaseModel):
prompt: str = Field(...)
negative_prompt: Optional[str] = Field(None)
@@ -146,53 +142,7 @@ class VideoTaskStatusResponse(BaseModel):
request_id: str = Field(...)
RES_IN_PARENS = re.compile(r'\((\d+)\s*[x×]\s*(\d+)\)')
async def process_task(
auth_kwargs: dict[str, str],
url: str,
request_model: Type[T],
response_model: Type[R],
payload: Union[
Text2ImageTaskCreationRequest,
Image2ImageTaskCreationRequest,
Text2VideoTaskCreationRequest,
Image2VideoTaskCreationRequest,
],
node_id: str,
estimated_duration: int,
poll_interval: int,
) -> Type[R]:
initial_response = await SynchronousOperation(
endpoint=ApiEndpoint(
path=url,
method=HttpMethod.POST,
request_model=request_model,
response_model=TaskCreationResponse,
),
request=payload,
auth_kwargs=auth_kwargs,
).execute()
if not initial_response.output:
raise Exception(f"Unknown error occurred: {initial_response.code} - {initial_response.message}")
return await PollingOperation(
poll_endpoint=ApiEndpoint(
path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}",
method=HttpMethod.GET,
request_model=EmptyRequest,
response_model=response_model,
),
completed_statuses=["SUCCEEDED"],
failed_statuses=["FAILED", "CANCELED", "UNKNOWN"],
status_extractor=lambda x: x.output.task_status,
estimated_duration=estimated_duration,
poll_interval=poll_interval,
node_id=node_id,
auth_kwargs=auth_kwargs,
).execute()
RES_IN_PARENS = re.compile(r"\((\d+)\s*[x×]\s*(\d+)\)")
class WanTextToImageApi(IO.ComfyNode):
@@ -259,7 +209,7 @@ class WanTextToImageApi(IO.ComfyNode):
IO.Boolean.Input(
"watermark",
default=True,
tooltip="Whether to add an \"AI generated\" watermark to the result.",
tooltip='Whether to add an "AI generated" watermark to the result.',
optional=True,
),
],
@@ -286,26 +236,28 @@ class WanTextToImageApi(IO.ComfyNode):
prompt_extend: bool = True,
watermark: bool = True,
):
payload = Text2ImageTaskCreationRequest(
model=model,
input=Text2ImageInputField(prompt=prompt, negative_prompt=negative_prompt),
parameters=Txt2ImageParametersField(
size=f"{width}*{height}",
seed=seed,
prompt_extend=prompt_extend,
watermark=watermark,
initial_response = await sync_op(
cls,
ApiEndpoint(path="/proxy/wan/api/v1/services/aigc/text2image/image-synthesis", method="POST"),
response_model=TaskCreationResponse,
data=Text2ImageTaskCreationRequest(
model=model,
input=Text2ImageInputField(prompt=prompt, negative_prompt=negative_prompt),
parameters=Txt2ImageParametersField(
size=f"{width}*{height}",
seed=seed,
prompt_extend=prompt_extend,
watermark=watermark,
),
),
)
response = await process_task(
{
"auth_token": cls.hidden.auth_token_comfy_org,
"comfy_api_key": cls.hidden.api_key_comfy_org,
},
"/proxy/wan/api/v1/services/aigc/text2image/image-synthesis",
request_model=Text2ImageTaskCreationRequest,
if not initial_response.output:
raise Exception(f"Unknown error occurred: {initial_response.code} - {initial_response.message}")
response = await poll_op(
cls,
ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"),
response_model=ImageTaskStatusResponse,
payload=payload,
node_id=cls.hidden.unique_id,
status_extractor=lambda x: x.output.task_status,
estimated_duration=9,
poll_interval=3,
)
@@ -320,7 +272,7 @@ class WanImageToImageApi(IO.ComfyNode):
display_name="Wan Image to Image",
category="api node/image/Wan",
description="Generates an image from one or two input images and a text prompt. "
"The output image is currently fixed at 1.6 MP; its aspect ratio matches the input image(s).",
"The output image is currently fixed at 1.6 MP; its aspect ratio matches the input image(s).",
inputs=[
IO.Combo.Input(
"model",
@@ -376,7 +328,7 @@ class WanImageToImageApi(IO.ComfyNode):
IO.Boolean.Input(
"watermark",
default=True,
tooltip="Whether to add an \"AI generated\" watermark to the result.",
tooltip='Whether to add an "AI generated" watermark to the result.',
optional=True,
),
],
@@ -408,28 +360,30 @@ class WanImageToImageApi(IO.ComfyNode):
raise ValueError(f"Expected 1 or 2 input images, got {n_images}.")
images = []
for i in image:
images.append("data:image/png;base64," + tensor_to_base64_string(i, total_pixels=4096*4096))
payload = Image2ImageTaskCreationRequest(
model=model,
input=Image2ImageInputField(prompt=prompt, negative_prompt=negative_prompt, images=images),
parameters=Image2ImageParametersField(
# size=f"{width}*{height}",
seed=seed,
watermark=watermark,
images.append("data:image/png;base64," + tensor_to_base64_string(i, total_pixels=4096 * 4096))
initial_response = await sync_op(
cls,
ApiEndpoint(path="/proxy/wan/api/v1/services/aigc/image2image/image-synthesis", method="POST"),
response_model=TaskCreationResponse,
data=Image2ImageTaskCreationRequest(
model=model,
input=Image2ImageInputField(prompt=prompt, negative_prompt=negative_prompt, images=images),
parameters=Image2ImageParametersField(
# size=f"{width}*{height}",
seed=seed,
watermark=watermark,
),
),
)
response = await process_task(
{
"auth_token": cls.hidden.auth_token_comfy_org,
"comfy_api_key": cls.hidden.api_key_comfy_org,
},
"/proxy/wan/api/v1/services/aigc/image2image/image-synthesis",
request_model=Image2ImageTaskCreationRequest,
if not initial_response.output:
raise Exception(f"Unknown error occurred: {initial_response.code} - {initial_response.message}")
response = await poll_op(
cls,
ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"),
response_model=ImageTaskStatusResponse,
payload=payload,
node_id=cls.hidden.unique_id,
status_extractor=lambda x: x.output.task_status,
estimated_duration=42,
poll_interval=3,
poll_interval=4,
)
return IO.NodeOutput(await download_url_to_image_tensor(str(response.output.results[0].url)))
@@ -523,7 +477,7 @@ class WanTextToVideoApi(IO.ComfyNode):
IO.Boolean.Input(
"watermark",
default=True,
tooltip="Whether to add an \"AI generated\" watermark to the result.",
tooltip='Whether to add an "AI generated" watermark to the result.',
optional=True,
),
],
@@ -557,28 +511,31 @@ class WanTextToVideoApi(IO.ComfyNode):
if audio is not None:
validate_audio_duration(audio, 3.0, 29.0)
audio_url = "data:audio/mp3;base64," + audio_to_base64_string(audio, "mp3", "libmp3lame")
payload = Text2VideoTaskCreationRequest(
model=model,
input=Text2VideoInputField(prompt=prompt, negative_prompt=negative_prompt, audio_url=audio_url),
parameters=Text2VideoParametersField(
size=f"{width}*{height}",
duration=duration,
seed=seed,
audio=generate_audio,
prompt_extend=prompt_extend,
watermark=watermark,
initial_response = await sync_op(
cls,
ApiEndpoint(path="/proxy/wan/api/v1/services/aigc/video-generation/video-synthesis", method="POST"),
response_model=TaskCreationResponse,
data=Text2VideoTaskCreationRequest(
model=model,
input=Text2VideoInputField(prompt=prompt, negative_prompt=negative_prompt, audio_url=audio_url),
parameters=Text2VideoParametersField(
size=f"{width}*{height}",
duration=duration,
seed=seed,
audio=generate_audio,
prompt_extend=prompt_extend,
watermark=watermark,
),
),
)
response = await process_task(
{
"auth_token": cls.hidden.auth_token_comfy_org,
"comfy_api_key": cls.hidden.api_key_comfy_org,
},
"/proxy/wan/api/v1/services/aigc/video-generation/video-synthesis",
request_model=Text2VideoTaskCreationRequest,
if not initial_response.output:
raise Exception(f"Unknown error occurred: {initial_response.code} - {initial_response.message}")
response = await poll_op(
cls,
ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"),
response_model=VideoTaskStatusResponse,
payload=payload,
node_id=cls.hidden.unique_id,
status_extractor=lambda x: x.output.task_status,
estimated_duration=120 * int(duration / 5),
poll_interval=6,
)
@@ -667,7 +624,7 @@ class WanImageToVideoApi(IO.ComfyNode):
IO.Boolean.Input(
"watermark",
default=True,
tooltip="Whether to add an \"AI generated\" watermark to the result.",
tooltip='Whether to add an "AI generated" watermark to the result.',
optional=True,
),
],
@@ -699,35 +656,37 @@ class WanImageToVideoApi(IO.ComfyNode):
):
if get_number_of_images(image) != 1:
raise ValueError("Exactly one input image is required.")
image_url = "data:image/png;base64," + tensor_to_base64_string(image, total_pixels=2000*2000)
image_url = "data:image/png;base64," + tensor_to_base64_string(image, total_pixels=2000 * 2000)
audio_url = None
if audio is not None:
validate_audio_duration(audio, 3.0, 29.0)
audio_url = "data:audio/mp3;base64," + audio_to_base64_string(audio, "mp3", "libmp3lame")
payload = Image2VideoTaskCreationRequest(
model=model,
input=Image2VideoInputField(
prompt=prompt, negative_prompt=negative_prompt, img_url=image_url, audio_url=audio_url
),
parameters=Image2VideoParametersField(
resolution=resolution,
duration=duration,
seed=seed,
audio=generate_audio,
prompt_extend=prompt_extend,
watermark=watermark,
initial_response = await sync_op(
cls,
ApiEndpoint(path="/proxy/wan/api/v1/services/aigc/video-generation/video-synthesis", method="POST"),
response_model=TaskCreationResponse,
data=Image2VideoTaskCreationRequest(
model=model,
input=Image2VideoInputField(
prompt=prompt, negative_prompt=negative_prompt, img_url=image_url, audio_url=audio_url
),
parameters=Image2VideoParametersField(
resolution=resolution,
duration=duration,
seed=seed,
audio=generate_audio,
prompt_extend=prompt_extend,
watermark=watermark,
),
),
)
response = await process_task(
{
"auth_token": cls.hidden.auth_token_comfy_org,
"comfy_api_key": cls.hidden.api_key_comfy_org,
},
"/proxy/wan/api/v1/services/aigc/video-generation/video-synthesis",
request_model=Image2VideoTaskCreationRequest,
if not initial_response.output:
raise Exception(f"Unknown error occurred: {initial_response.code} - {initial_response.message}")
response = await poll_op(
cls,
ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"),
response_model=VideoTaskStatusResponse,
payload=payload,
node_id=cls.hidden.unique_id,
status_extractor=lambda x: x.output.task_status,
estimated_duration=120 * int(duration / 5),
poll_interval=6,
)