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

* 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

Author: bigcat88

comfy_api_nodes/apinode_utils.py

@@ -50,44 +50,6 @@ class BFLFluxFillImageRequest(BaseModel):
     mask: str = Field(None, description='A Base64-encoded string representing the mask of the areas you with to modify.')
 
 
-class BFLFluxCannyImageRequest(BaseModel):
-    prompt: str = Field(..., description='Text prompt for image generation')
-    prompt_upsampling: Optional[bool] = Field(
-        None, description='Whether to perform upsampling on the prompt. If active, automatically modifies the prompt for more creative generation.'
-    )
-    canny_low_threshold: Optional[int] = Field(None, description='Low threshold for Canny edge detection')
-    canny_high_threshold: Optional[int] = Field(None, description='High threshold for Canny edge detection')
-    seed: Optional[int] = Field(None, description='The seed value for reproducibility.')
-    steps: conint(ge=15, le=50) = Field(..., description='Number of steps for the image generation process')
-    guidance: confloat(ge=1, le=100) = Field(..., description='Guidance strength for the image generation process')
-    safety_tolerance: Optional[conint(ge=0, le=6)] = Field(
-        6, description='Tolerance level for input and output moderation. Between 0 and 6, 0 being most strict, 6 being least strict. Defaults to 2.'
-    )
-    output_format: Optional[BFLOutputFormat] = Field(
-        BFLOutputFormat.png, description="Output format for the generated image. Can be 'jpeg' or 'png'.", examples=['png']
-    )
-    control_image: Optional[str] = Field(None, description='Base64 encoded image to use as control input if no preprocessed image is provided')
-    preprocessed_image: Optional[str] = Field(None, description='Optional pre-processed image that will bypass the control preprocessing step')
-
-
-class BFLFluxDepthImageRequest(BaseModel):
-    prompt: str = Field(..., description='Text prompt for image generation')
-    prompt_upsampling: Optional[bool] = Field(
-        None, description='Whether to perform upsampling on the prompt. If active, automatically modifies the prompt for more creative generation.'
-    )
-    seed: Optional[int] = Field(None, description='The seed value for reproducibility.')
-    steps: conint(ge=15, le=50) = Field(..., description='Number of steps for the image generation process')
-    guidance: confloat(ge=1, le=100) = Field(..., description='Guidance strength for the image generation process')
-    safety_tolerance: Optional[conint(ge=0, le=6)] = Field(
-        6, description='Tolerance level for input and output moderation. Between 0 and 6, 0 being most strict, 6 being least strict. Defaults to 2.'
-    )
-    output_format: Optional[BFLOutputFormat] = Field(
-        BFLOutputFormat.png, description="Output format for the generated image. Can be 'jpeg' or 'png'.", examples=['png']
-    )
-    control_image: Optional[str] = Field(None, description='Base64 encoded image to use as control input if no preprocessed image is provided')
-    preprocessed_image: Optional[str] = Field(None, description='Optional pre-processed image that will bypass the control preprocessing step')
-
-
 class BFLFluxProGenerateRequest(BaseModel):
     prompt: str = Field(..., description='The text prompt for image generation.')
     prompt_upsampling: Optional[bool] = Field(
@@ -160,15 +122,8 @@ class BFLStatus(str, Enum):
     error = "Error"
 
 
-class BFLFluxProStatusResponse(BaseModel):
+class BFLFluxStatusResponse(BaseModel):
     id: str = Field(..., description="The unique identifier for the generation task.")
     status: BFLStatus = Field(..., description="The status of the task.")
-    result: Optional[Dict[str, Any]] = Field(
-        None, description="The result of the task (null if not completed)."
-    )
-    progress: confloat(ge=0.0, le=1.0) = Field(
-        ..., description="The progress of the task (0.0 to 1.0)."
-    )
-    details: Optional[Dict[str, Any]] = Field(
-        None, description="Additional details about the task (null if not available)."
-    )
+    result: Optional[Dict[str, Any]] = Field(None, description="The result of the task (null if not completed).")
+    progress: Optional[float] = Field(None, description="The progress of the task (0.0 to 1.0).", ge=0.0, le=1.0)

comfy_api_nodes/apis/bfl_api.py

@@ -0,0 +1,111 @@
+from typing import Optional, Union
+from enum import Enum
+
+from pydantic import BaseModel, Field
+
+
+class Image2(BaseModel):
+    bytesBase64Encoded: str
+    gcsUri: Optional[str] = None
+    mimeType: Optional[str] = None
+
+
+class Image3(BaseModel):
+    bytesBase64Encoded: Optional[str] = None
+    gcsUri: str
+    mimeType: Optional[str] = None
+
+
+class Instance1(BaseModel):
+    image: Optional[Union[Image2, Image3]] = Field(
+        None, description='Optional image to guide video generation'
+    )
+    prompt: str = Field(..., description='Text description of the video')
+
+
+class PersonGeneration1(str, Enum):
+    ALLOW = 'ALLOW'
+    BLOCK = 'BLOCK'
+
+
+class Parameters1(BaseModel):
+    aspectRatio: Optional[str] = Field(None, examples=['16:9'])
+    durationSeconds: Optional[int] = None
+    enhancePrompt: Optional[bool] = None
+    generateAudio: Optional[bool] = Field(
+        None,
+        description='Generate audio for the video. Only supported by veo 3 models.',
+    )
+    negativePrompt: Optional[str] = None
+    personGeneration: Optional[PersonGeneration1] = None
+    sampleCount: Optional[int] = None
+    seed: Optional[int] = None
+    storageUri: Optional[str] = Field(
+        None, description='Optional Cloud Storage URI to upload the video'
+    )
+
+
+class VeoGenVidRequest(BaseModel):
+    instances: Optional[list[Instance1]] = None
+    parameters: Optional[Parameters1] = None
+
+
+class VeoGenVidResponse(BaseModel):
+    name: str = Field(
+        ...,
+        description='Operation resource name',
+        examples=[
+            'projects/PROJECT_ID/locations/us-central1/publishers/google/models/MODEL_ID/operations/a1b07c8e-7b5a-4aba-bb34-3e1ccb8afcc8'
+        ],
+    )
+
+
+class VeoGenVidPollRequest(BaseModel):
+    operationName: str = Field(
+        ...,
+        description='Full operation name (from predict response)',
+        examples=[
+            'projects/PROJECT_ID/locations/us-central1/publishers/google/models/MODEL_ID/operations/OPERATION_ID'
+        ],
+    )
+
+
+class Video(BaseModel):
+    bytesBase64Encoded: Optional[str] = Field(
+        None, description='Base64-encoded video content'
+    )
+    gcsUri: Optional[str] = Field(None, description='Cloud Storage URI of the video')
+    mimeType: Optional[str] = Field(None, description='Video MIME type')
+
+
+class Error1(BaseModel):
+    code: Optional[int] = Field(None, description='Error code')
+    message: Optional[str] = Field(None, description='Error message')
+
+
+class Response1(BaseModel):
+    field_type: Optional[str] = Field(
+        None,
+        alias='@type',
+        examples=[
+            'type.googleapis.com/cloud.ai.large_models.vision.GenerateVideoResponse'
+        ],
+    )
+    raiMediaFilteredCount: Optional[int] = Field(
+        None, description='Count of media filtered by responsible AI policies'
+    )
+    raiMediaFilteredReasons: Optional[list[str]] = Field(
+        None, description='Reasons why media was filtered by responsible AI policies'
+    )
+    videos: Optional[list[Video]] = None
+
+
+class VeoGenVidPollResponse(BaseModel):
+    done: Optional[bool] = None
+    error: Optional[Error1] = Field(
+        None, description='Error details if operation failed'
+    )
+    name: Optional[str] = None
+    response: Optional[Response1] = Field(
+        None, description='The actual prediction response if done is true'
+    )