diff --git a/comfy_api_nodes/apis/PixverseController.py b/comfy_api_nodes/apis/PixverseController.py index 949fce171..6f87c3d2c 100644 --- a/comfy_api_nodes/apis/PixverseController.py +++ b/comfy_api_nodes/apis/PixverseController.py @@ -1,6 +1,6 @@ # generated by datamodel-codegen: -# filename: filtered-openapi.yaml -# timestamp: 2025-04-24T22:16:48+00:00 +# filename: https://stagingapi.comfy.org/openapi +# timestamp: 2025-04-29T03:13:19+00:00 from __future__ import annotations diff --git a/comfy_api_nodes/apis/PixverseDto.py b/comfy_api_nodes/apis/PixverseDto.py index 3a2c95fbc..0b08fa2aa 100644 --- a/comfy_api_nodes/apis/PixverseDto.py +++ b/comfy_api_nodes/apis/PixverseDto.py @@ -1,6 +1,6 @@ # generated by datamodel-codegen: -# filename: filtered-openapi.yaml -# timestamp: 2025-04-24T22:16:48+00:00 +# filename: https://stagingapi.comfy.org/openapi +# timestamp: 2025-04-29T03:13:19+00:00 from __future__ import annotations diff --git a/comfy_api_nodes/apis/__init__.py b/comfy_api_nodes/apis/__init__.py index 4ca4d5ab9..562a7addb 100644 --- a/comfy_api_nodes/apis/__init__.py +++ b/comfy_api_nodes/apis/__init__.py @@ -1,39 +1,37 @@ # generated by datamodel-codegen: -# filename: filtered-openapi.yaml -# timestamp: 2025-04-25T03:57:04+00:00 +# filename: https://stagingapi.comfy.org/openapi +# timestamp: 2025-04-29T03:13:19+00:00 from __future__ import annotations from datetime import datetime from enum import Enum -from typing import Any, Dict, List, Optional +from typing import Any, Dict, List, Literal, Optional, Union +from uuid import UUID -from pydantic import BaseModel, Field, confloat, conint, constr - - -class OutputFormat(str, Enum): - png = 'png' - webp = 'webp' - jpeg = 'jpeg' +from pydantic import AnyUrl, BaseModel, Field, RootModel, confloat, conint, constr class BFLFluxProGenerateRequest(BaseModel): + guidance_scale: Optional[confloat(ge=1.0, le=20.0)] = Field( + None, description='The guidance scale for generation.' + ) + height: conint(ge=64, le=2048) = Field( + ..., description='The height of the image to generate.' + ) + negative_prompt: Optional[str] = Field( + None, description='The negative prompt for image generation.' + ) + num_images: Optional[conint(ge=1, le=4)] = Field( + None, description='The number of images to generate.' + ) + num_inference_steps: Optional[conint(ge=1, le=100)] = Field( + None, description='The number of inference steps.' + ) prompt: str = Field(..., description='The 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.') - aspect_ratio: Optional[str] = Field(None, description='Aspect ratio of the image between 21:9 and 9:21.') - 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[OutputFormat] = Field( - OutputFormat.png, description="Output format for the generated image. Can be 'jpeg' or 'png'.", examples=['png'] - ) - raw: Optional[bool] = Field(None, description='Generate less processed, more natural-looking images.') - image_prompt: Optional[str] = Field(None, description='Optional image to remix in base64 format') - image_prompt_strength: Optional[confloat(ge=0.0, le=1.0)] = Field( - None, description='Blend between the prompt and the image prompt.' + width: conint(ge=64, le=2048) = Field( + ..., description='The width of the image to generate.' ) @@ -42,11 +40,106 @@ class BFLFluxProGenerateResponse(BaseModel): polling_url: str = Field(..., description='URL to poll for the generation result.') +class ComfyNode(BaseModel): + category: Optional[str] = Field( + None, + description='UI category where the node is listed, used for grouping nodes.', + ) + comfy_node_name: Optional[str] = Field( + None, description='Unique identifier for the node' + ) + deprecated: Optional[bool] = Field( + None, + description='Indicates if the node is deprecated. Deprecated nodes are hidden in the UI.', + ) + description: Optional[str] = Field( + None, description="Brief description of the node's functionality or purpose." + ) + experimental: Optional[bool] = Field( + None, + description='Indicates if the node is experimental, subject to changes or removal.', + ) + function: Optional[str] = Field( + None, description='Name of the entry-point function to execute the node.' + ) + input_types: Optional[str] = Field(None, description='Defines input parameters') + output_is_list: Optional[List[bool]] = Field( + None, description='Boolean values indicating if each output is a list.' + ) + return_names: Optional[str] = Field( + None, description='Names of the outputs for clarity in workflows.' + ) + return_types: Optional[str] = Field( + None, description='Specifies the types of outputs produced by the node.' + ) + + +class ComfyNodeCloudBuildInfo(BaseModel): + build_id: Optional[str] = None + location: Optional[str] = None + project_id: Optional[str] = None + project_number: Optional[str] = None + + +class Customer(BaseModel): + createdAt: Optional[datetime] = Field( + None, description='The date and time the user was created' + ) + email: Optional[str] = Field(None, description='The email address for this user') + id: str = Field(..., description='The firebase UID of the user') + name: Optional[str] = Field(None, description='The name for this user') + updatedAt: Optional[datetime] = Field( + None, description='The date and time the user was last updated' + ) + + +class CustomerStorageResourceResponse(BaseModel): + download_url: Optional[str] = Field( + None, + description='The signed URL to use for downloading the file from the specified path', + ) + existing_file: Optional[bool] = Field( + None, description='Whether an existing file with the same hash was found' + ) + expires_at: Optional[datetime] = Field( + None, description='When the signed URL will expire' + ) + upload_url: Optional[str] = Field( + None, + description='The signed URL to use for uploading the file to the specified path', + ) + + +class Error(BaseModel): + details: Optional[List[str]] = Field( + None, + description='Optional detailed information about the error or hints for resolving it.', + ) + message: Optional[str] = Field( + None, description='A clear and concise description of the error.' + ) + + class ErrorResponse(BaseModel): error: str message: str +class GitCommitSummary(BaseModel): + author: Optional[str] = Field(None, description='The author of the commit') + branch_name: Optional[str] = Field( + None, description='The branch where the commit was made' + ) + commit_hash: Optional[str] = Field(None, description='The hash of the commit') + commit_name: Optional[str] = Field(None, description='The name of the commit') + status_summary: Optional[Dict[str, str]] = Field( + None, description='A map of operating system to status pairs' + ) + timestamp: Optional[datetime] = Field( + None, description='The timestamp when the commit was made' + ) + + class ImageRequest(BaseModel): aspect_ratio: Optional[str] = Field( None, @@ -117,24 +210,47 @@ class IdeogramGenerateResponse(BaseModel): ) -class Code(Enum): - int_1100 = 1100 - int_1101 = 1101 - int_1102 = 1102 - int_1103 = 1103 +class Duration(str, Enum): + field_5 = '5' + field_10 = '10' -class Code1(Enum): - int_1000 = 1000 - int_1001 = 1001 - int_1002 = 1002 - int_1003 = 1003 - int_1004 = 1004 +class Mode(str, Enum): + std = 'std' + pro = 'pro' + + +class ModelName(str, Enum): + kling_v1 = 'kling-v1' + kling_v1_5 = 'kling-v1-5' + kling_v1_6 = 'kling-v1-6' + + +class KlingDualCharacterEffectInput(BaseModel): + duration: Duration = Field( + ..., + description='Video Length in seconds. Both 5 and 10-second videos are supported.', + ) + images: List[str] = Field( + ..., + description='Reference Image Group. Must contain exactly 2 images. First image will be positioned on left side, second on right side of the composite. Each image follows the same requirements as single image effects.', + max_length=2, + min_length=2, + ) + mode: Optional[Mode] = Field( + 'std', + description='Video generation mode. std (Standard Mode) is cost-effective, pro (Professional Mode) generates videos with longer duration and higher quality.', + ) + model_name: Optional[ModelName] = Field( + 'kling-v1', + description='Model Name. Can be kling-v1, kling-v1-5, or kling-v1-6.', + ) class KlingErrorResponse(BaseModel): code: int = Field( - ..., description='Error code value as defined in the API documentation' + ..., + description='- 1000: Authentication failed\n- 1001: Authorization is empty\n- 1002: Authorization is invalid\n- 1003: Authorization is not yet valid\n- 1004: Authorization has expired\n- 1100: Account exception\n- 1101: Account in arrears (postpaid scenario)\n- 1102: Resource pack depleted or expired (prepaid scenario)\n- 1103: Unauthorized access to requested resource\n- 1200: Invalid request parameters\n- 1201: Invalid parameters\n- 1202: Invalid request method\n- 1203: Requested resource does not exist\n- 1300: Trigger platform strategy\n- 1301: Trigger content security policy\n- 1302: API request too frequent\n- 1303: Concurrency/QPS exceeds limit\n- 1304: Trigger IP whitelist policy\n- 5000: Internal server error\n- 5001: Service temporarily unavailable\n- 5002: Server internal timeout\n', ) message: str = Field(..., description='Human-readable error message') request_id: str = Field( @@ -142,45 +258,779 @@ class KlingErrorResponse(BaseModel): ) -class Code2(Enum): - int_1200 = 1200 - int_1201 = 1201 - int_1202 = 1202 - int_1203 = 1203 +class AspectRatio(str, Enum): + field_16_9 = '16:9' + field_9_16 = '9:16' + field_1_1 = '1:1' -class KlingRequestError(KlingErrorResponse): - code: Optional[Code2] = Field( +class Config(BaseModel): + horizontal: Optional[confloat(ge=-10.0, le=10.0)] = Field( None, - description='- 1200: Invalid request parameters\n- 1201: Invalid parameters\n- 1202: Invalid request method\n- 1203: Requested resource does not exist\n', + description="Controls camera's movement along horizontal axis (x-axis). Negative indicates left, positive indicates right.", + ) + pan: Optional[confloat(ge=-10.0, le=10.0)] = Field( + None, + description="Controls camera's rotation in vertical plane (x-axis). Negative indicates downward rotation, positive indicates upward rotation.", + ) + roll: Optional[confloat(ge=-10.0, le=10.0)] = Field( + None, + description="Controls camera's rolling amount (z-axis). Negative indicates counterclockwise, positive indicates clockwise.", + ) + tilt: Optional[confloat(ge=-10.0, le=10.0)] = Field( + None, + description="Controls camera's rotation in horizontal plane (y-axis). Negative indicates left rotation, positive indicates right rotation.", + ) + vertical: Optional[confloat(ge=-10.0, le=10.0)] = Field( + None, + description="Controls camera's movement along vertical axis (y-axis). Negative indicates downward, positive indicates upward.", + ) + zoom: Optional[confloat(ge=-10.0, le=10.0)] = Field( + None, + description="Controls change in camera's focal length. Negative indicates narrower field of view, positive indicates wider field of view.", ) -class Code3(Enum): - int_5000 = 5000 - int_5001 = 5001 - int_5002 = 5002 +class Type(str, Enum): + simple = 'simple' + down_back = 'down_back' + forward_up = 'forward_up' + right_turn_forward = 'right_turn_forward' + left_turn_forward = 'left_turn_forward' -class KlingServerError(KlingErrorResponse): - code: Optional[Code3] = Field( +class CameraControl(BaseModel): + config: Optional[Config] = None + type: Optional[Type] = Field( None, - description='- 5000: Internal server error\n- 5001: Service temporarily unavailable\n- 5002: Server internal timeout\n', + description='Predefined camera movements type. simple: Customizable camera movement. down_back: Camera descends and moves backward. forward_up: Camera moves forward and tilts up. right_turn_forward: Rotate right and move forward. left_turn_forward: Rotate left and move forward.', ) -class Code4(Enum): - int_1300 = 1300 - int_1301 = 1301 - int_1302 = 1302 - int_1303 = 1303 - int_1304 = 1304 - - -class KlingStrategyError(KlingErrorResponse): - code: Optional[Code4] = Field( +class Trajectory(BaseModel): + x: Optional[int] = Field( None, - description='- 1300: Trigger platform strategy\n- 1301: Trigger content security policy\n- 1302: API request too frequent\n- 1303: Concurrency/QPS exceeds limit\n- 1304: Trigger IP whitelist policy\n', + description='The horizontal coordinate of trajectory point. Based on bottom-left corner of image as origin (0,0).', + ) + y: Optional[int] = Field( + None, + description='The vertical coordinate of trajectory point. Based on bottom-left corner of image as origin (0,0).', + ) + + +class DynamicMask(BaseModel): + mask: Optional[AnyUrl] = Field( + None, + description='Dynamic Brush Application Area (Mask image created by users using the motion brush). The aspect ratio must match the input image.', + ) + trajectories: Optional[List[Trajectory]] = None + + +class KlingImage2VideoRequest(BaseModel): + aspect_ratio: Optional[AspectRatio] = '16:9' + callback_url: Optional[AnyUrl] = Field( + None, + description='The callback notification address. Server will notify when the task status changes.', + ) + camera_control: Optional[CameraControl] = None + cfg_scale: Optional[confloat(ge=0.0, le=1.0)] = Field( + 0.5, + description="Flexibility in video generation. The higher the value, the lower the model's degree of flexibility, and the stronger the relevance to the user's prompt.", + ) + duration: Optional[Duration] = Field(5, description='Video length in seconds') + dynamic_masks: Optional[List[DynamicMask]] = Field( + None, + description='Dynamic Brush Configuration List (up to 6 groups). For 5-second videos, trajectory length must not exceed 77 coordinates.', + ) + external_task_id: Optional[str] = Field( + None, + description='Customized Task ID. Must be unique within a single user account.', + ) + image: Optional[AnyUrl] = Field( + None, + description='Reference Image - URL or Base64 encoded string, cannot exceed 10MB, resolution not less than 300*300px, aspect ratio between 1:2.5 ~ 2.5:1. Base64 should not include data:image prefix.', + ) + image_tail: Optional[AnyUrl] = Field( + None, + description='Reference Image - End frame control. URL or Base64 encoded string, cannot exceed 10MB, resolution not less than 300*300px. Base64 should not include data:image prefix.', + ) + mode: Optional[Mode] = Field( + 'std', + description='Video generation mode. std: Standard Mode, which is cost-effective. pro: Professional Mode, generates videos with longer duration but higher quality output.', + ) + model_name: Optional[ModelName] = Field('kling-v1', description='Model Name') + negative_prompt: Optional[constr(max_length=2500)] = Field( + None, description='Negative text prompt' + ) + prompt: Optional[constr(max_length=2500)] = Field( + None, description='Positive text prompt' + ) + static_mask: Optional[AnyUrl] = Field( + None, + description='Static Brush Application Area (Mask image created by users using the motion brush). The aspect ratio must match the input image.', + ) + + +class TaskInfo(BaseModel): + external_task_id: Optional[str] = None + + +class Video(BaseModel): + duration: Optional[str] = Field(None, description='Total video duration') + id: Optional[str] = Field(None, description='Generated video ID') + url: Optional[AnyUrl] = Field(None, description='URL for generated video') + + +class TaskResult(BaseModel): + videos: Optional[List[Video]] = None + + +class TaskStatus(str, Enum): + submitted = 'submitted' + processing = 'processing' + succeed = 'succeed' + failed = 'failed' + + +class Data(BaseModel): + created_at: Optional[int] = Field(None, description='Task creation time') + task_id: Optional[str] = Field(None, description='Task ID') + task_info: Optional[TaskInfo] = None + task_result: Optional[TaskResult] = None + task_status: Optional[TaskStatus] = None + updated_at: Optional[int] = Field(None, description='Task update time') + + +class KlingImage2VideoResponse(BaseModel): + code: Optional[int] = Field(None, description='Error code') + data: Optional[Data] = None + message: Optional[str] = Field(None, description='Error message') + request_id: Optional[str] = Field(None, description='Request ID') + + +class AspectRatio1(str, Enum): + field_16_9 = '16:9' + field_9_16 = '9:16' + field_1_1 = '1:1' + field_4_3 = '4:3' + field_3_4 = '3:4' + field_3_2 = '3:2' + field_2_3 = '2:3' + field_21_9 = '21:9' + + +class ImageReference(str, Enum): + subject = 'subject' + face = 'face' + + +class ModelName2(str, Enum): + kling_v1 = 'kling-v1' + kling_v1_5 = 'kling-v1-5' + + +class KlingImageGenerationsRequest(BaseModel): + aspect_ratio: Optional[AspectRatio1] = Field( + '16:9', description='Aspect ratio of the generated images' + ) + callback_url: Optional[AnyUrl] = Field( + None, description='The callback notification address' + ) + human_fidelity: Optional[confloat(ge=0.0, le=1.0)] = Field( + 0.45, description='Subject reference similarity' + ) + image: Optional[str] = Field( + None, description='Reference Image - Base64 encoded string or image URL' + ) + image_fidelity: Optional[confloat(ge=0.0, le=1.0)] = Field( + 0.5, description='Reference intensity for user-uploaded images' + ) + image_reference: Optional[ImageReference] = Field( + None, description='Image reference type' + ) + model_name: Optional[ModelName2] = Field('kling-v1', description='Model Name') + n: Optional[conint(ge=1, le=9)] = Field(1, description='Number of generated images') + negative_prompt: Optional[constr(max_length=200)] = Field( + None, description='Negative text prompt' + ) + prompt: constr(max_length=500) = Field(..., description='Positive text prompt') + + +class Image(BaseModel): + index: Optional[int] = Field(None, description='Image Number (0-9)') + url: Optional[AnyUrl] = Field(None, description='URL for generated image') + + +class TaskResult1(BaseModel): + images: Optional[List[Image]] = None + + +class Data1(BaseModel): + created_at: Optional[int] = Field(None, description='Task creation time') + task_id: Optional[str] = Field(None, description='Task ID') + task_result: Optional[TaskResult1] = None + task_status: Optional[TaskStatus] = None + task_status_msg: Optional[str] = Field(None, description='Task status information') + updated_at: Optional[int] = Field(None, description='Task update time') + + +class KlingImageGenerationsResponse(BaseModel): + code: Optional[int] = Field(None, description='Error code') + data: Optional[Data1] = None + message: Optional[str] = Field(None, description='Error message') + request_id: Optional[str] = Field(None, description='Request ID') + + +class AudioType(str, Enum): + file = 'file' + url = 'url' + + +class Mode2(str, Enum): + text2video = 'text2video' + audio2video = 'audio2video' + + +class VoiceLanguage(str, Enum): + zh = 'zh' + en = 'en' + + +class Input(BaseModel): + audio_file: Optional[str] = Field( + None, + description='Local Path of Audio File. Supported formats: .mp3/.wav/.m4a/.aac, maximum file size of 5MB. Base64 code.', + ) + audio_type: Optional[AudioType] = Field( + None, + description='Method of Transmitting Audio Files for Lip-Sync. Required when mode is audio2video.', + ) + audio_url: Optional[AnyUrl] = Field( + None, + description='Audio File Download URL. Supported formats: .mp3/.wav/.m4a/.aac, maximum file size of 5MB.', + ) + mode: Mode2 = Field( + ..., + description='Video Generation Mode. text2video: Text-to-video generation mode; audio2video: Audio-to-video generation mode', + ) + text: Optional[str] = Field( + None, + description='Text Content for Lip-Sync Video Generation. Required when mode is text2video. Maximum length is 120 characters.', + ) + video_id: Optional[str] = Field( + None, + description='The ID of the video generated by Kling AI. Only supports 5-second and 10-second videos generated within the last 30 days.', + ) + video_url: Optional[AnyUrl] = Field( + None, + description='Get link for uploaded video. Video files support .mp4/.mov, file size does not exceed 100MB, video length between 2-10s.', + ) + voice_id: Optional[str] = Field( + None, + description='Voice ID. Required when mode is text2video. The system offers a variety of voice options to choose from.', + ) + voice_language: Optional[VoiceLanguage] = Field( + 'zh', description='The voice language corresponds to the Voice ID.' + ) + voice_speed: Optional[confloat(ge=0.8, le=2.0)] = Field( + 1, + description='Speech Rate. Valid range: 0.8~2.0, accurate to one decimal place.', + ) + + +class KlingLipSyncRequest(BaseModel): + callback_url: Optional[AnyUrl] = Field( + None, + description='The callback notification address. Server will notify when the task status changes.', + ) + input: Input + + +class TaskResult2(BaseModel): + videos: Optional[List[Video]] = None + + +class Data2(BaseModel): + created_at: Optional[int] = Field(None, description='Task creation time') + task_id: Optional[str] = Field(None, description='Task ID') + task_info: Optional[TaskInfo] = None + task_result: Optional[TaskResult2] = None + task_status: Optional[TaskStatus] = None + updated_at: Optional[int] = Field(None, description='Task update time') + + +class KlingLipSyncResponse(BaseModel): + code: Optional[int] = Field(None, description='Error code') + data: Optional[Data2] = None + message: Optional[str] = Field(None, description='Error message') + request_id: Optional[str] = Field(None, description='Request ID') + + +class ResourcePackType(str, Enum): + decreasing_total = 'decreasing_total' + constant_period = 'constant_period' + + +class Status(str, Enum): + toBeOnline = 'toBeOnline' + online = 'online' + expired = 'expired' + runOut = 'runOut' + + +class ResourcePackSubscribeInfo(BaseModel): + effective_time: Optional[int] = Field( + None, description='Effective time, Unix timestamp in ms' + ) + invalid_time: Optional[int] = Field( + None, description='Expiration time, Unix timestamp in ms' + ) + purchase_time: Optional[int] = Field( + None, description='Purchase time, Unix timestamp in ms' + ) + remaining_quantity: Optional[float] = Field( + None, description='Remaining quantity (updated with a 12-hour delay)' + ) + resource_pack_id: Optional[str] = Field(None, description='Resource package ID') + resource_pack_name: Optional[str] = Field(None, description='Resource package name') + resource_pack_type: Optional[ResourcePackType] = Field( + None, + description='Resource package type (decreasing_total=decreasing total, constant_period=constant periodicity)', + ) + status: Optional[Status] = Field(None, description='Resource Package Status') + total_quantity: Optional[float] = Field(None, description='Total quantity') + + +class Data3(BaseModel): + code: Optional[int] = Field(None, description='Error code; 0 indicates success') + msg: Optional[str] = Field(None, description='Error information') + resource_pack_subscribe_infos: Optional[List[ResourcePackSubscribeInfo]] = Field( + None, description='Resource package list' + ) + + +class KlingResourcePackageResponse(BaseModel): + code: Optional[int] = Field(None, description='Error code; 0 indicates success') + data: Optional[Data3] = None + message: Optional[str] = Field(None, description='Error information') + request_id: Optional[str] = Field( + None, + description='Request ID, generated by the system, used to track requests and troubleshoot problems', + ) + + +class Duration2(str, Enum): + field_5 = '5' + + +class ModelName3(str, Enum): + kling_v1_6 = 'kling-v1-6' + + +class KlingSingleImageEffectInput(BaseModel): + duration: Duration2 = Field( + ..., description='Video Length in seconds. Only 5-second videos are supported.' + ) + image: str = Field( + ..., + description='Reference Image. URL or Base64 encoded string (without data:image prefix). File size cannot exceed 10MB, resolution not less than 300*300px, aspect ratio between 1:2.5 ~ 2.5:1.', + ) + model_name: ModelName3 = Field( + ..., + description='Model Name. Only kling-v1-6 is supported for single image effects.', + ) + + +class AspectRatio2(str, Enum): + field_16_9 = '16:9' + field_9_16 = '9:16' + field_1_1 = '1:1' + + +class Config1(BaseModel): + horizontal: Optional[confloat(ge=-10.0, le=10.0)] = None + pan: Optional[confloat(ge=-10.0, le=10.0)] = None + roll: Optional[confloat(ge=-10.0, le=10.0)] = None + tilt: Optional[confloat(ge=-10.0, le=10.0)] = None + vertical: Optional[confloat(ge=-10.0, le=10.0)] = None + zoom: Optional[confloat(ge=-10.0, le=10.0)] = None + + +class CameraControl1(BaseModel): + config: Optional[Config1] = None + type: Optional[Type] = Field(None, description='Predefined camera movements type') + + +class Duration3(str, Enum): + field_5 = 5 + field_10 = 10 + + +class Mode3(str, Enum): + std = 'std' + pro = 'pro' + + +class ModelName4(str, Enum): + kling_v1 = 'kling-v1' + kling_v1_6 = 'kling-v1-6' + + +class KlingText2VideoRequest(BaseModel): + aspect_ratio: Optional[AspectRatio2] = '16:9' + callback_url: Optional[AnyUrl] = Field( + None, description='The callback notification address' + ) + camera_control: Optional[CameraControl1] = None + cfg_scale: Optional[confloat(ge=0.0, le=1.0)] = Field( + 0.5, description='Flexibility in video generation' + ) + duration: Optional[Duration3] = 5 + external_task_id: Optional[str] = Field(None, description='Customized Task ID') + mode: Optional[Mode3] = Field('std', description='Video generation mode') + model_name: Optional[ModelName4] = Field('kling-v1', description='Model Name') + negative_prompt: Optional[constr(max_length=2500)] = Field( + None, description='Negative text prompt' + ) + prompt: Optional[constr(max_length=2500)] = Field( + None, description='Positive text prompt' + ) + + +class TaskResult3(BaseModel): + videos: Optional[List[Video]] = None + + +class Data4(BaseModel): + created_at: Optional[int] = Field(None, description='Task creation time') + task_id: Optional[str] = Field(None, description='Task ID') + task_info: Optional[TaskInfo] = None + task_result: Optional[TaskResult3] = None + task_status: Optional[TaskStatus] = None + updated_at: Optional[int] = Field(None, description='Task update time') + + +class KlingText2VideoResponse(BaseModel): + code: Optional[int] = Field(None, description='Error code') + data: Optional[Data4] = None + message: Optional[str] = Field(None, description='Error message') + request_id: Optional[str] = Field(None, description='Request ID') + + +class KlingVideoEffectsInput( + RootModel[Union[KlingSingleImageEffectInput, KlingDualCharacterEffectInput]] +): + root: Union[KlingSingleImageEffectInput, KlingDualCharacterEffectInput] + + +class EffectScene(str, Enum): + bloombloom = 'bloombloom' + dizzydizzy = 'dizzydizzy' + fuzzyfuzzy = 'fuzzyfuzzy' + squish = 'squish' + expansion = 'expansion' + hug = 'hug' + kiss = 'kiss' + heart_gesture = 'heart_gesture' + + +class KlingVideoEffectsRequest(BaseModel): + callback_url: Optional[AnyUrl] = Field( + None, + description='The callback notification address for the result of this task.', + ) + effect_scene: EffectScene = Field( + ..., + description='Scene Name. Single Image Effects (bloombloom, dizzydizzy, fuzzyfuzzy, squish, expansion) or Dual-character Effects (hug, kiss, heart_gesture).', + ) + external_task_id: Optional[str] = Field( + None, + description='Customized Task ID. Must be unique within a single user account.', + ) + input: Optional[KlingVideoEffectsInput] = None + + +class TaskResult4(BaseModel): + videos: Optional[List[Video]] = None + + +class Data5(BaseModel): + created_at: Optional[int] = Field(None, description='Task creation time') + task_id: Optional[str] = Field(None, description='Task ID') + task_info: Optional[TaskInfo] = None + task_result: Optional[TaskResult4] = None + task_status: Optional[TaskStatus] = None + updated_at: Optional[int] = Field(None, description='Task update time') + + +class KlingVideoEffectsResponse(BaseModel): + code: Optional[int] = Field(None, description='Error code') + data: Optional[Data5] = None + message: Optional[str] = Field(None, description='Error message') + request_id: Optional[str] = Field(None, description='Request ID') + + +class KlingVideoExtendRequest(BaseModel): + callback_url: Optional[AnyUrl] = Field( + None, + description='The callback notification address. Server will notify when the task status changes.', + ) + cfg_scale: Optional[confloat(ge=0.0, le=1.0)] = Field( + 0.5, + description="Flexibility in video generation. The higher the value, the lower the model's flexibility and the stronger the relevance to the user's prompt.", + ) + negative_prompt: Optional[constr(max_length=2500)] = Field( + None, + description='Negative text prompt for elements to avoid in the extended video', + ) + prompt: Optional[constr(max_length=2500)] = Field( + None, description='Positive text prompt for guiding the video extension' + ) + video_id: Optional[str] = Field( + None, + description='The ID of the video to be extended. Supports videos generated by text-to-video, image-to-video, and previous video extension operations. Cannot exceed 3 minutes total duration after extension.', + ) + + +class TaskResult5(BaseModel): + videos: Optional[List[Video]] = None + + +class Data6(BaseModel): + created_at: Optional[int] = Field(None, description='Task creation time') + task_id: Optional[str] = Field(None, description='Task ID') + task_info: Optional[TaskInfo] = None + task_result: Optional[TaskResult5] = None + task_status: Optional[TaskStatus] = None + updated_at: Optional[int] = Field(None, description='Task update time') + + +class KlingVideoExtendResponse(BaseModel): + code: Optional[int] = Field(None, description='Error code') + data: Optional[Data6] = None + message: Optional[str] = Field(None, description='Error message') + request_id: Optional[str] = Field(None, description='Request ID') + + +class ModelName5(str, Enum): + kolors_virtual_try_on_v1 = 'kolors-virtual-try-on-v1' + kolors_virtual_try_on_v1_5 = 'kolors-virtual-try-on-v1-5' + + +class KlingVirtualTryOnRequest(BaseModel): + callback_url: Optional[AnyUrl] = Field( + None, description='The callback notification address' + ) + cloth_image: Optional[str] = Field( + None, + description='Reference clothing image - Base64 encoded string or image URL', + ) + human_image: str = Field( + ..., description='Reference human image - Base64 encoded string or image URL' + ) + model_name: Optional[ModelName5] = Field( + 'kolors-virtual-try-on-v1', description='Model Name' + ) + + +class Image1(BaseModel): + index: Optional[int] = Field(None, description='Image Number') + url: Optional[AnyUrl] = Field(None, description='URL for generated image') + + +class TaskResult6(BaseModel): + images: Optional[List[Image1]] = None + + +class Data7(BaseModel): + created_at: Optional[int] = Field(None, description='Task creation time') + task_id: Optional[str] = Field(None, description='Task ID') + task_result: Optional[TaskResult6] = None + task_status: Optional[TaskStatus] = None + task_status_msg: Optional[str] = Field(None, description='Task status information') + updated_at: Optional[int] = Field(None, description='Task update time') + + +class KlingVirtualTryOnResponse(BaseModel): + code: Optional[int] = Field(None, description='Error code') + data: Optional[Data7] = None + message: Optional[str] = Field(None, description='Error message') + request_id: Optional[str] = Field(None, description='Request ID') + + +class LumaAspectRatio(str, Enum): + field_1_1 = '1:1' + field_16_9 = '16:9' + field_9_16 = '9:16' + field_4_3 = '4:3' + field_3_4 = '3:4' + field_21_9 = '21:9' + field_9_21 = '9:21' + + +class LumaAssets(BaseModel): + image: Optional[AnyUrl] = Field(None, description='The URL of the image') + progress_video: Optional[AnyUrl] = Field( + None, description='The URL of the progress video' + ) + video: Optional[AnyUrl] = Field(None, description='The URL of the video') + + +class GenerationType(str, Enum): + add_audio = 'add_audio' + + +class LumaAudioGenerationRequest(BaseModel): + callback_url: Optional[AnyUrl] = Field( + None, description='The callback URL for the audio' + ) + generation_type: Optional[GenerationType] = 'add_audio' + negative_prompt: Optional[str] = Field( + None, description='The negative prompt of the audio' + ) + prompt: Optional[str] = Field(None, description='The prompt of the audio') + + +class LumaError(BaseModel): + detail: Optional[str] = Field(None, description='The error message') + + +class Type2(str, Enum): + generation = 'generation' + + +class LumaGenerationReference(BaseModel): + id: UUID = Field(..., description='The ID of the generation') + type: Literal['generation'] + + +class GenerationType1(str, Enum): + video = 'video' + + +class LumaGenerationType(str, Enum): + video = 'video' + image = 'image' + + +class GenerationType2(str, Enum): + image = 'image' + + +class LumaImageIdentity(BaseModel): + images: Optional[List[AnyUrl]] = Field( + None, description='The URLs of the image identity' + ) + + +class LumaImageModel(str, Enum): + photon_1 = 'photon-1' + photon_flash_1 = 'photon-flash-1' + + +class LumaImageRef(BaseModel): + url: Optional[AnyUrl] = Field(None, description='The URL of the image reference') + weight: Optional[float] = Field( + None, description='The weight of the image reference' + ) + + +class Type3(str, Enum): + image = 'image' + + +class LumaImageReference(BaseModel): + type: Literal['image'] + url: AnyUrl = Field(..., description='The URL of the image') + + +class LumaKeyframe(RootModel[Union[LumaGenerationReference, LumaImageReference]]): + root: Union[LumaGenerationReference, LumaImageReference] = Field( + ..., + description='A keyframe can be either a Generation reference, an Image, or a Video', + discriminator='type', + ) + + +class LumaKeyframes(BaseModel): + frame0: Optional[LumaKeyframe] = None + frame1: Optional[LumaKeyframe] = None + + +class LumaModifyImageRef(BaseModel): + url: Optional[AnyUrl] = Field(None, description='The URL of the image reference') + weight: Optional[float] = Field( + None, description='The weight of the modify image reference' + ) + + +class LumaState(str, Enum): + queued = 'queued' + dreaming = 'dreaming' + completed = 'completed' + failed = 'failed' + + +class GenerationType3(str, Enum): + upscale_video = 'upscale_video' + + +class LumaVideoModel(str, Enum): + ray_2 = 'ray-2' + ray_2_flash = 'ray-2-flash' + + +class LumaVideoModelOutputDuration1(str, Enum): + field_5s = '5s' + field_9s = '9s' + + +class LumaVideoModelOutputDuration( + RootModel[Union[LumaVideoModelOutputDuration1, str]] +): + root: Union[LumaVideoModelOutputDuration1, str] + + +class LumaVideoModelOutputResolution1(str, Enum): + field_540p = '540p' + field_720p = '720p' + field_1080p = '1080p' + field_4k = '4k' + + +class LumaVideoModelOutputResolution( + RootModel[Union[LumaVideoModelOutputResolution1, str]] +): + root: Union[LumaVideoModelOutputResolution1, str] + + +class MachineStats(BaseModel): + cpu_capacity: Optional[str] = Field(None, description='Total CPU on the machine.') + disk_capacity: Optional[str] = Field( + None, description='Total disk capacity on the machine.' + ) + gpu_type: Optional[str] = Field( + None, description='The GPU type. eg. NVIDIA Tesla K80' + ) + initial_cpu: Optional[str] = Field( + None, description='Initial CPU available before the job starts.' + ) + initial_disk: Optional[str] = Field( + None, description='Initial disk available before the job starts.' + ) + initial_ram: Optional[str] = Field( + None, description='Initial RAM available before the job starts.' + ) + machine_name: Optional[str] = Field(None, description='Name of the machine.') + memory_capacity: Optional[str] = Field( + None, description='Total memory on the machine.' + ) + os_version: Optional[str] = Field( + None, description='The operating system version. eg. Ubuntu Linux 20.04' + ) + pip_freeze: Optional[str] = Field(None, description='The pip freeze output') + vram_time_series: Optional[Dict[str, Any]] = Field( + None, description='Time series of VRAM usage.' ) @@ -212,7 +1062,7 @@ class MinimaxFileRetrieveResponse(BaseModel): file: File -class Status(str, Enum): +class Status1(str, Enum): Queueing = 'Queueing' Preparing = 'Preparing' Processing = 'Processing' @@ -226,7 +1076,7 @@ class MinimaxTaskResultResponse(BaseModel): None, description='After the task status changes to Success, this field returns the file ID corresponding to the generated video.', ) - status: Status = Field( + status: Status1 = Field( ..., description="Task status: 'Queueing' (in queue), 'Preparing' (task is preparing), 'Processing' (generating), 'Success' (task completed successfully), or 'Fail' (task failed).", ) @@ -286,11 +1136,40 @@ class MinimaxVideoGenerationResponse(BaseModel): ) +class NodeStatus(str, Enum): + NodeStatusActive = 'NodeStatusActive' + NodeStatusDeleted = 'NodeStatusDeleted' + NodeStatusBanned = 'NodeStatusBanned' + + +class NodeVersionStatus(str, Enum): + NodeVersionStatusActive = 'NodeVersionStatusActive' + NodeVersionStatusDeleted = 'NodeVersionStatusDeleted' + NodeVersionStatusBanned = 'NodeVersionStatusBanned' + NodeVersionStatusPending = 'NodeVersionStatusPending' + NodeVersionStatusFlagged = 'NodeVersionStatusFlagged' + + +class NodeVersionUpdateRequest(BaseModel): + changelog: Optional[str] = Field( + None, description='The changelog describing the version changes.' + ) + deprecated: Optional[bool] = Field( + None, description='Whether the version is deprecated.' + ) + + class Moderation(str, Enum): low = 'low' auto = 'auto' +class OutputFormat(str, Enum): + png = 'png' + webp = 'webp' + jpeg = 'jpeg' + + class OpenAIImageEditRequest(BaseModel): background: Optional[str] = Field( None, description='Background transparency', examples=['opaque'] @@ -404,19 +1283,730 @@ class Datum1(BaseModel): url: Optional[str] = Field(None, description='URL of the image') +class InputTokensDetails(BaseModel): + image_tokens: Optional[int] = None + text_tokens: Optional[int] = None + + +class Usage(BaseModel): + input_tokens: Optional[int] = None + input_tokens_details: Optional[InputTokensDetails] = None + output_tokens: Optional[int] = None + total_tokens: Optional[int] = None + + class OpenAIImageGenerationResponse(BaseModel): data: Optional[List[Datum1]] = None + usage: Optional[Usage] = None -class KlingAccountError(KlingErrorResponse): - code: Optional[Code] = Field( +class PersonalAccessToken(BaseModel): + createdAt: Optional[datetime] = Field( + None, description='[Output Only]The date and time the token was created.' + ) + description: Optional[str] = Field( None, - description='- 1100: Account exception\n- 1101: Account in arrears (postpaid scenario)\n- 1102: Resource pack depleted or expired (prepaid scenario)\n- 1103: Unauthorized access to requested resource\n', + description="Optional. A more detailed description of the token's intended use.", + ) + id: Optional[UUID] = Field(None, description='Unique identifier for the GitCommit') + name: Optional[str] = Field( + None, + description='Required. The name of the token. Can be a simple description.', + ) + token: Optional[str] = Field( + None, + description='[Output Only]. The personal access token. Only returned during creation.', ) -class KlingAuthenticationError(KlingErrorResponse): - code: Optional[Code1] = Field( - None, - description='- 1000: Authentication failed\n- 1001: Authorization is empty\n- 1002: Authorization is invalid\n- 1003: Authorization is not yet valid\n- 1004: Authorization has expired\n', +class PublisherStatus(str, Enum): + PublisherStatusActive = 'PublisherStatusActive' + PublisherStatusBanned = 'PublisherStatusBanned' + + +class PublisherUser(BaseModel): + email: Optional[str] = Field(None, description='The email address for this user.') + id: Optional[str] = Field(None, description='The unique id for this user.') + name: Optional[str] = Field(None, description='The name for this user.') + + +class RecraftImageGenerationRequest(BaseModel): + model: str = Field( + ..., description='The model to use for generation (e.g., "recraftv3")' ) + n: conint(ge=1, le=4) = Field(..., description='The number of images to generate') + prompt: str = Field( + ..., description='The text prompt describing the image to generate' + ) + size: str = Field( + ..., description='The size of the generated image (e.g., "1024x1024")' + ) + style: Optional[str] = Field( + None, + description='The style to apply to the generated image (e.g., "digital_illustration")', + ) + + +class Datum2(BaseModel): + image_id: Optional[str] = Field( + None, description='Unique identifier for the generated image' + ) + url: Optional[str] = Field(None, description='URL to access the generated image') + + +class RecraftImageGenerationResponse(BaseModel): + created: int = Field( + ..., description='Unix timestamp when the generation was created' + ) + credits: int = Field(..., description='Number of credits used for the generation') + data: List[Datum2] = Field(..., description='Array of generated image information') + + +class RunwayAspectRatioEnum(str, Enum): + field_1280_720 = '1280:720' + field_720_1280 = '720:1280' + field_1104_832 = '1104:832' + field_832_1104 = '832:1104' + field_960_960 = '960:960' + field_1584_672 = '1584:672' + field_1280_768 = '1280:768' + field_768_1280 = '768:1280' + + +class RunwayDurationEnum(int, Enum): + integer_5 = 5 + integer_10 = 10 + + +class RunwayImageToVideoResponse(BaseModel): + id: Optional[str] = Field(None, description='Task ID') + + +class RunwayModelEnum(str, Enum): + gen4_turbo = 'gen4_turbo' + gen3a_turbo = 'gen3a_turbo' + + +class Position(str, Enum): + first = 'first' + last = 'last' + + +class RunwayPromptImageDetailedObject(BaseModel): + position: Position = Field( + ..., + description="The position of the image in the output video. 'last' is currently supported for gen3a_turbo only.", + ) + uri: AnyUrl = Field( + ..., description='A HTTPS URL or data URI containing an encoded image.' + ) + + +class RunwayPromptImageObject( + RootModel[Union[AnyUrl, List[RunwayPromptImageDetailedObject]]] +): + root: Union[AnyUrl, List[RunwayPromptImageDetailedObject]] = Field( + ..., + description='Image(s) to use for the video generation. Can be a single URI or an array of image objects with positions.', + ) + + +class RunwayTaskStatusEnum(str, Enum): + SUCCEEDED = 'SUCCEEDED' + RUNNING = 'RUNNING' + FAILED = 'FAILED' + PENDING = 'PENDING' + CANCELLED = 'CANCELLED' + THROTTLED = 'THROTTLED' + + +class RunwayTaskStatusResponse(BaseModel): + createdAt: Optional[datetime] = Field(None, description='Task creation timestamp') + id: Optional[str] = Field(None, description='Task ID') + output: Optional[List[str]] = Field(None, description='Array of output video URLs') + status: Optional[RunwayTaskStatusEnum] = None + + +class StorageFile(BaseModel): + file_path: Optional[str] = Field(None, description='Path to the file in storage') + id: Optional[UUID] = Field( + None, description='Unique identifier for the storage file' + ) + public_url: Optional[str] = Field(None, description='Public URL') + + +class StripeAddress(BaseModel): + city: Optional[str] = None + country: Optional[str] = None + line1: Optional[str] = None + line2: Optional[str] = None + postal_code: Optional[str] = None + state: Optional[str] = None + + +class StripeAmountDetails(BaseModel): + tip: Optional[Dict[str, Any]] = None + + +class StripeBillingDetails(BaseModel): + address: Optional[StripeAddress] = None + email: Optional[str] = None + name: Optional[str] = None + phone: Optional[str] = None + tax_id: Optional[Any] = None + + +class Checks(BaseModel): + address_line1_check: Optional[Any] = None + address_postal_code_check: Optional[Any] = None + cvc_check: Optional[str] = None + + +class ExtendedAuthorization(BaseModel): + status: Optional[str] = None + + +class IncrementalAuthorization(BaseModel): + status: Optional[str] = None + + +class Multicapture(BaseModel): + status: Optional[str] = None + + +class NetworkToken(BaseModel): + used: Optional[bool] = None + + +class Overcapture(BaseModel): + maximum_amount_capturable: Optional[int] = None + status: Optional[str] = None + + +class StripeCardDetails(BaseModel): + amount_authorized: Optional[int] = None + authorization_code: Optional[Any] = None + brand: Optional[str] = None + checks: Optional[Checks] = None + country: Optional[str] = None + exp_month: Optional[int] = None + exp_year: Optional[int] = None + extended_authorization: Optional[ExtendedAuthorization] = None + fingerprint: Optional[str] = None + funding: Optional[str] = None + incremental_authorization: Optional[IncrementalAuthorization] = None + installments: Optional[Any] = None + last4: Optional[str] = None + mandate: Optional[Any] = None + multicapture: Optional[Multicapture] = None + network: Optional[str] = None + network_token: Optional[NetworkToken] = None + network_transaction_id: Optional[str] = None + overcapture: Optional[Overcapture] = None + regulated_status: Optional[str] = None + three_d_secure: Optional[Any] = None + wallet: Optional[Any] = None + + +class Object(str, Enum): + charge = 'charge' + + +class Object1(str, Enum): + event = 'event' + + +class Type4(str, Enum): + payment_intent_succeeded = 'payment_intent.succeeded' + + +class StripeOutcome(BaseModel): + advice_code: Optional[Any] = None + network_advice_code: Optional[Any] = None + network_decline_code: Optional[Any] = None + network_status: Optional[str] = None + reason: Optional[Any] = None + risk_level: Optional[str] = None + risk_score: Optional[int] = None + seller_message: Optional[str] = None + type: Optional[str] = None + + +class Object2(str, Enum): + payment_intent = 'payment_intent' + + +class StripePaymentMethodDetails(BaseModel): + card: Optional[StripeCardDetails] = None + type: Optional[str] = None + + +class Card(BaseModel): + installments: Optional[Any] = None + mandate_options: Optional[Any] = None + network: Optional[Any] = None + request_three_d_secure: Optional[str] = None + + +class StripePaymentMethodOptions(BaseModel): + card: Optional[Card] = None + + +class StripeRefundList(BaseModel): + data: Optional[List[Dict[str, Any]]] = None + has_more: Optional[bool] = None + object: Optional[str] = None + total_count: Optional[int] = None + url: Optional[str] = None + + +class StripeRequestInfo(BaseModel): + id: Optional[str] = None + idempotency_key: Optional[str] = None + + +class StripeShipping(BaseModel): + address: Optional[StripeAddress] = None + carrier: Optional[str] = None + name: Optional[str] = None + phone: Optional[str] = None + tracking_number: Optional[str] = None + + +class User(BaseModel): + email: Optional[str] = Field(None, description='The email address for this user.') + id: Optional[str] = Field(None, description='The unique id for this user.') + isAdmin: Optional[bool] = Field( + None, description='Indicates if the user has admin privileges.' + ) + isApproved: Optional[bool] = Field( + None, description='Indicates if the user is approved.' + ) + name: Optional[str] = Field(None, description='The name for this user.') + + +class Veo2GenVidPollRequest(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 Video5(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 Response(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' + ) + videos: Optional[List[Video5]] = None + + +class Veo2GenVidPollResponse(BaseModel): + done: Optional[bool] = None + name: Optional[str] = None + response: Optional[Response] = Field( + None, description='The actual prediction response if done is true' + ) + + +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 Instance(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 PersonGeneration(str, Enum): + ALLOW = 'ALLOW' + BLOCK = 'BLOCK' + + +class Parameters(BaseModel): + aspectRatio: Optional[str] = Field(None, examples=['16:9']) + durationSeconds: Optional[int] = None + enhancePrompt: Optional[bool] = None + negativePrompt: Optional[str] = None + personGeneration: Optional[PersonGeneration] = None + sampleCount: Optional[int] = None + seed: Optional[int] = None + storageUri: Optional[str] = Field( + None, description='Optional Cloud Storage URI to upload the video' + ) + + +class Veo2GenVidRequest(BaseModel): + instances: Optional[List[Instance]] = None + parameters: Optional[Parameters] = None + + +class Veo2GenVidResponse(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 WorkflowRunStatus(str, Enum): + WorkflowRunStatusStarted = 'WorkflowRunStatusStarted' + WorkflowRunStatusFailed = 'WorkflowRunStatusFailed' + WorkflowRunStatusCompleted = 'WorkflowRunStatusCompleted' + + +class ActionJobResult(BaseModel): + action_job_id: Optional[str] = Field( + None, description='Identifier of the job this result belongs to' + ) + action_run_id: Optional[str] = Field( + None, description='Identifier of the run this result belongs to' + ) + author: Optional[str] = Field(None, description='The author of the commit') + avg_vram: Optional[int] = Field( + None, description='The average VRAM used by the job' + ) + branch_name: Optional[str] = Field( + None, description='Name of the relevant git branch' + ) + comfy_run_flags: Optional[str] = Field( + None, description='The comfy run flags. E.g. `--low-vram`' + ) + commit_hash: Optional[str] = Field(None, description='The hash of the commit') + commit_id: Optional[str] = Field(None, description='The ID of the commit') + commit_message: Optional[str] = Field(None, description='The message of the commit') + commit_time: Optional[int] = Field( + None, description='The Unix timestamp when the commit was made' + ) + cuda_version: Optional[str] = Field(None, description='CUDA version used') + end_time: Optional[int] = Field( + None, description='The end time of the job as a Unix timestamp.' + ) + git_repo: Optional[str] = Field(None, description='The repository name') + id: Optional[UUID] = Field(None, description='Unique identifier for the job result') + job_trigger_user: Optional[str] = Field( + None, description='The user who triggered the job.' + ) + machine_stats: Optional[MachineStats] = None + operating_system: Optional[str] = Field(None, description='Operating system used') + peak_vram: Optional[int] = Field(None, description='The peak VRAM used by the job') + pr_number: Optional[str] = Field(None, description='The pull request number') + python_version: Optional[str] = Field(None, description='PyTorch version used') + pytorch_version: Optional[str] = Field(None, description='PyTorch version used') + start_time: Optional[int] = Field( + None, description='The start time of the job as a Unix timestamp.' + ) + status: Optional[WorkflowRunStatus] = None + storage_file: Optional[StorageFile] = None + workflow_name: Optional[str] = Field(None, description='Name of the workflow') + + +class LumaGenerationRequest(BaseModel): + aspect_ratio: LumaAspectRatio + callback_url: Optional[AnyUrl] = Field( + None, + description='The callback URL of the generation, a POST request with Generation object will be sent to the callback URL when the generation is dreaming, completed, or failed', + ) + duration: LumaVideoModelOutputDuration + generation_type: Optional[GenerationType1] = 'video' + keyframes: Optional[LumaKeyframes] = None + loop: Optional[bool] = Field(None, description='Whether to loop the video') + model: LumaVideoModel + prompt: str = Field(..., description='The prompt of the generation') + resolution: LumaVideoModelOutputResolution + + +class CharacterRef(BaseModel): + identity0: Optional[LumaImageIdentity] = None + + +class LumaImageGenerationRequest(BaseModel): + aspect_ratio: Optional[LumaAspectRatio] = '16:9' + callback_url: Optional[AnyUrl] = Field( + None, description='The callback URL for the generation' + ) + character_ref: Optional[CharacterRef] = None + generation_type: Optional[GenerationType2] = 'image' + image_ref: Optional[List[LumaImageRef]] = None + model: Optional[LumaImageModel] = 'photon-1' + modify_image_ref: Optional[LumaModifyImageRef] = None + prompt: Optional[str] = Field(None, description='The prompt of the generation') + style_ref: Optional[List[LumaImageRef]] = None + + +class LumaUpscaleVideoGenerationRequest(BaseModel): + callback_url: Optional[AnyUrl] = Field( + None, description='The callback URL for the upscale' + ) + generation_type: Optional[GenerationType3] = 'upscale_video' + resolution: Optional[LumaVideoModelOutputResolution] = None + + +class NodeVersion(BaseModel): + changelog: Optional[str] = Field( + None, description='Summary of changes made in this version' + ) + comfy_node_extract_status: Optional[str] = Field( + None, description='The status of comfy node extraction process.' + ) + createdAt: Optional[datetime] = Field( + None, description='The date and time the version was created.' + ) + dependencies: Optional[List[str]] = Field( + None, description='A list of pip dependencies required by the node.' + ) + deprecated: Optional[bool] = Field( + None, description='Indicates if this version is deprecated.' + ) + downloadUrl: Optional[str] = Field( + None, description='[Output Only] URL to download this version of the node' + ) + id: Optional[str] = None + node_id: Optional[str] = Field( + None, description='The unique identifier of the node.' + ) + status: Optional[NodeVersionStatus] = None + status_reason: Optional[str] = Field( + None, description='The reason for the status change.' + ) + version: Optional[str] = Field( + None, + description='The version identifier, following semantic versioning. Must be unique for the node.', + ) + + +class PublisherMember(BaseModel): + id: Optional[str] = Field( + None, description='The unique identifier for the publisher member.' + ) + role: Optional[str] = Field( + None, description='The role of the user in the publisher.' + ) + user: Optional[PublisherUser] = None + + +class RunwayImageToVideoRequest(BaseModel): + duration: RunwayDurationEnum + model: RunwayModelEnum + promptImage: RunwayPromptImageObject + promptText: Optional[constr(max_length=1000)] = Field( + None, description='Text prompt for the generation' + ) + ratio: RunwayAspectRatioEnum + seed: conint(ge=0, le=4294967295) = Field( + ..., description='Random seed for generation' + ) + + +class StripeCharge(BaseModel): + amount: Optional[int] = None + amount_captured: Optional[int] = None + amount_refunded: Optional[int] = None + application: Optional[str] = None + application_fee: Optional[str] = None + application_fee_amount: Optional[int] = None + balance_transaction: Optional[str] = None + billing_details: Optional[StripeBillingDetails] = None + calculated_statement_descriptor: Optional[str] = None + captured: Optional[bool] = None + created: Optional[int] = None + currency: Optional[str] = None + customer: Optional[str] = None + description: Optional[str] = None + destination: Optional[Any] = None + dispute: Optional[Any] = None + disputed: Optional[bool] = None + failure_balance_transaction: Optional[Any] = None + failure_code: Optional[Any] = None + failure_message: Optional[Any] = None + fraud_details: Optional[Dict[str, Any]] = None + id: Optional[str] = None + invoice: Optional[Any] = None + livemode: Optional[bool] = None + metadata: Optional[Dict[str, Any]] = None + object: Optional[Object] = None + on_behalf_of: Optional[Any] = None + order: Optional[Any] = None + outcome: Optional[StripeOutcome] = None + paid: Optional[bool] = None + payment_intent: Optional[str] = None + payment_method: Optional[str] = None + payment_method_details: Optional[StripePaymentMethodDetails] = None + radar_options: Optional[Dict[str, Any]] = None + receipt_email: Optional[str] = None + receipt_number: Optional[str] = None + receipt_url: Optional[str] = None + refunded: Optional[bool] = None + refunds: Optional[StripeRefundList] = None + review: Optional[Any] = None + shipping: Optional[StripeShipping] = None + source: Optional[Any] = None + source_transfer: Optional[Any] = None + statement_descriptor: Optional[Any] = None + statement_descriptor_suffix: Optional[Any] = None + status: Optional[str] = None + transfer_data: Optional[Any] = None + transfer_group: Optional[Any] = None + + +class StripeChargeList(BaseModel): + data: Optional[List[StripeCharge]] = None + has_more: Optional[bool] = None + object: Optional[str] = None + total_count: Optional[int] = None + url: Optional[str] = None + + +class StripePaymentIntent(BaseModel): + amount: Optional[int] = None + amount_capturable: Optional[int] = None + amount_details: Optional[StripeAmountDetails] = None + amount_received: Optional[int] = None + application: Optional[str] = None + application_fee_amount: Optional[int] = None + automatic_payment_methods: Optional[Any] = None + canceled_at: Optional[int] = None + cancellation_reason: Optional[str] = None + capture_method: Optional[str] = None + charges: Optional[StripeChargeList] = None + client_secret: Optional[str] = None + confirmation_method: Optional[str] = None + created: Optional[int] = None + currency: Optional[str] = None + customer: Optional[str] = None + description: Optional[str] = None + id: Optional[str] = None + invoice: Optional[str] = None + last_payment_error: Optional[Any] = None + latest_charge: Optional[str] = None + livemode: Optional[bool] = None + metadata: Optional[Dict[str, Any]] = None + next_action: Optional[Any] = None + object: Optional[Object2] = None + on_behalf_of: Optional[Any] = None + payment_method: Optional[str] = None + payment_method_configuration_details: Optional[Any] = None + payment_method_options: Optional[StripePaymentMethodOptions] = None + payment_method_types: Optional[List[str]] = None + processing: Optional[Any] = None + receipt_email: Optional[str] = None + review: Optional[Any] = None + setup_future_usage: Optional[Any] = None + shipping: Optional[StripeShipping] = None + source: Optional[Any] = None + statement_descriptor: Optional[Any] = None + statement_descriptor_suffix: Optional[Any] = None + status: Optional[str] = None + transfer_data: Optional[Any] = None + transfer_group: Optional[Any] = None + + +class LumaGeneration(BaseModel): + assets: Optional[LumaAssets] = None + created_at: Optional[datetime] = Field( + None, description='The date and time when the generation was created' + ) + failure_reason: Optional[str] = Field( + None, description='The reason for the state of the generation' + ) + generation_type: Optional[LumaGenerationType] = None + id: Optional[UUID] = Field(None, description='The ID of the generation') + model: Optional[str] = Field(None, description='The model used for the generation') + request: Optional[ + Union[ + LumaGenerationRequest, + LumaImageGenerationRequest, + LumaUpscaleVideoGenerationRequest, + LumaAudioGenerationRequest, + ] + ] = Field(None, description='The request of the generation') + state: Optional[LumaState] = None + + +class Publisher(BaseModel): + createdAt: Optional[datetime] = Field( + None, description='The date and time the publisher was created.' + ) + description: Optional[str] = None + id: Optional[str] = Field( + None, + description="The unique identifier for the publisher. It's akin to a username. Should be lowercase.", + ) + logo: Optional[str] = Field(None, description="URL to the publisher's logo.") + members: Optional[List[PublisherMember]] = Field( + None, description='A list of members in the publisher.' + ) + name: Optional[str] = None + source_code_repo: Optional[str] = None + status: Optional[PublisherStatus] = None + support: Optional[str] = None + website: Optional[str] = None + + +class Data8(BaseModel): + object: Optional[StripePaymentIntent] = None + + +class StripeEvent(BaseModel): + api_version: Optional[str] = None + created: Optional[int] = None + data: Data8 + id: str + livemode: Optional[bool] = None + object: Object1 + pending_webhooks: Optional[int] = None + request: Optional[StripeRequestInfo] = None + type: Type4 + + +class Node(BaseModel): + author: Optional[str] = None + category: Optional[str] = Field(None, description='The category of the node.') + description: Optional[str] = None + downloads: Optional[int] = Field( + None, description='The number of downloads of the node.' + ) + icon: Optional[str] = Field(None, description="URL to the node's icon.") + id: Optional[str] = Field(None, description='The unique identifier of the node.') + latest_version: Optional[NodeVersion] = None + license: Optional[str] = Field( + None, description="The path to the LICENSE file in the node's repository." + ) + name: Optional[str] = Field(None, description='The display name of the node.') + publisher: Optional[Publisher] = None + rating: Optional[float] = Field(None, description='The average rating of the node.') + repository: Optional[str] = Field(None, description="URL to the node's repository.") + status: Optional[NodeStatus] = None + status_detail: Optional[str] = Field( + None, description='The status detail of the node.' + ) + tags: Optional[List[str]] = None + translations: Optional[Dict[str, Dict[str, Any]]] = None diff --git a/comfy_api_nodes/nodes_veo2.py b/comfy_api_nodes/nodes_veo2.py new file mode 100644 index 000000000..c6defe00a --- /dev/null +++ b/comfy_api_nodes/nodes_veo2.py @@ -0,0 +1,274 @@ +import io +import logging +import base64 +import requests +import math +import torch +import numpy as np +from PIL import Image + +from comfy.comfy_types.node_typing import IO, ComfyNodeABC +from comfy.utils import common_upscale +from comfy_api.input_impl.video_types import VideoFromFile +from comfy_api_nodes.apis import ( + Veo2GenVidRequest, + Veo2GenVidResponse, + Veo2GenVidPollRequest, + Veo2GenVidPollResponse +) +from comfy_api_nodes.apis.client import ( + ApiEndpoint, + HttpMethod, + SynchronousOperation, +) + +def downscale_input(image, total_pixels=1536*1024): + samples = image.movedim(-1,1) + # Downscaling input images to roughly the same size as the outputs + total = int(total_pixels) + scale_by = math.sqrt(total / (samples.shape[3] * samples.shape[2])) + if scale_by >= 1: + return image + width = round(samples.shape[3] * scale_by) + height = round(samples.shape[2] * scale_by) + + s = common_upscale(samples, width, height, "lanczos", "disabled") + s = s.movedim(1,-1) + return s + +class VeoVideoGenerationNode(ComfyNodeABC): + """ + Generates videos from text prompts using Google's Veo API. + + This node can create videos from text descriptions and optional image inputs, + with control over parameters like aspect ratio, duration, and more. + """ + + @classmethod + def INPUT_TYPES(s): + return { + "required": { + "prompt": ( + IO.STRING, + { + "multiline": True, + "default": "", + "tooltip": "Text description of the video", + }, + ), + "aspect_ratio": ( + IO.COMBO, + { + "options": ["16:9", "9:16"], + "default": "16:9", + "tooltip": "Aspect ratio of the output video", + }, + ), + }, + "optional": { + "negative_prompt": ( + IO.STRING, + { + "multiline": True, + "default": "", + "tooltip": "Negative text prompt to guide what to avoid in the video", + }, + ), + "duration_seconds": ( + IO.INT, + { + "default": 5, + "min": 5, + "max": 8, + "step": 1, + "display": "number", + "tooltip": "Duration of the output video in seconds", + }, + ), + "enhance_prompt": ( + IO.BOOLEAN, + { + "default": True, + "tooltip": "Whether to enhance the prompt with AI assistance", + } + ), + "person_generation": ( + IO.COMBO, + { + "options": ["ALLOW", "BLOCK"], + "default": "ALLOW", + "tooltip": "Whether to allow generating people in the video", + }, + ), + "seed": ( + IO.INT, + { + "default": 0, + "min": 0, + "max": 0xFFFFFFFF, + "step": 1, + "display": "number", + "tooltip": "Seed for video generation (0 for random)", + }, + ), + "image": (IO.IMAGE, { + "default": None, + "tooltip": "Optional reference image to guide video generation", + }), + }, + "hidden": { + "auth_token": "AUTH_TOKEN_COMFY_ORG", + }, + } + + RETURN_TYPES = (IO.VIDEO,) + FUNCTION = "generate_video" + CATEGORY = "api node/video" + DESCRIPTION = "Generates videos from text prompts using Google's Veo API" + API_NODE = True + + def _convert_image_to_base64(self, image: torch.Tensor): + if image is None: + return None + + scaled_image = downscale_input(image, total_pixels=2048*2048) + + # Remove batch dimension if present + if len(scaled_image.shape) > 3: + scaled_image = scaled_image[0] + + # Convert to numpy array and then to PIL Image + image_np = (scaled_image.numpy() * 255).astype(np.uint8) + img = Image.fromarray(image_np) + + # Convert to base64 + buffer = io.BytesIO() + img.save(buffer, format="PNG") + return base64.b64encode(buffer.getvalue()).decode('utf-8') + + def generate_video( + self, + prompt, + aspect_ratio="16:9", + negative_prompt="", + duration_seconds=5, + enhance_prompt=True, + person_generation="ALLOW", + seed=0, + image=None, + auth_token=None, + ): + # Prepare the instances for the request + instances = [] + + instance = { + "prompt": prompt + } + + # Add image if provided + if image is not None: + image_base64 = self._convert_image_to_base64(image) + if image_base64: + instance["image"] = { + "bytesBase64Encoded": image_base64, + "mimeType": "image/png" + } + + instances.append(instance) + + # Create parameters dictionary + parameters = { + "aspectRatio": aspect_ratio, + "personGeneration": person_generation, + "durationSeconds": duration_seconds, + "enhancePrompt": enhance_prompt, + } + + # Add optional parameters if provided + if negative_prompt: + parameters["negativePrompt"] = negative_prompt + if seed > 0: + parameters["seed"] = seed + + # Initial request to start video generation + initial_operation = SynchronousOperation( + endpoint=ApiEndpoint( + path="/proxy/veo/generate", + method=HttpMethod.POST, + request_model=Veo2GenVidRequest, + response_model=Veo2GenVidResponse + ), + request=Veo2GenVidRequest( + instances=instances, + parameters=parameters + ), + auth_token=auth_token + ) + + initial_response = initial_operation.execute() + operation_name = initial_response.name + + logging.info(f"Veo generation started with operation name: {operation_name}") + + # Poll until operation is complete + video_data = None + while True: + poll_operation = SynchronousOperation( + endpoint=ApiEndpoint( + path="/proxy/veo/poll", + method=HttpMethod.POST, + request_model=Veo2GenVidPollRequest, + response_model=Veo2GenVidPollResponse + ), + request=Veo2GenVidPollRequest( + operationName=operation_name + ), + auth_token=auth_token + ) + + poll_response = poll_operation.execute() + + if poll_response.done: + if poll_response.response and poll_response.response.videos and len(poll_response.response.videos) > 0: + video = poll_response.response.videos[0] + + # Check if video is provided as base64 or URL + if hasattr(video, 'bytesBase64Encoded') and video.bytesBase64Encoded: + # Decode base64 string to bytes + video_data = base64.b64decode(video.bytesBase64Encoded) + break + elif hasattr(video, 'gcsUri') and video.gcsUri: + # Download from URL + video_url = video.gcsUri + video_response = requests.get(video_url) + video_data = video_response.content + break + else: + raise Exception("Video returned but no data or URL was provided") + else: + raise Exception("Video generation completed but no video was returned") + + # Wait before polling again + import time + time.sleep(5) + + if not video_data: + raise Exception("No video data was returned") + + logging.info("Video generation completed successfully") + + # Convert video data to BytesIO object + video_io = io.BytesIO(video_data) + + # Return VideoFromFile object + return (VideoFromFile(video_io),) + + +# Register the node +NODE_CLASS_MAPPINGS = { + "VeoVideoGenerationNode": VeoVideoGenerationNode, +} + +NODE_DISPLAY_NAME_MAPPINGS = { + "VeoVideoGenerationNode": "Google Veo2 Video Generation", +} diff --git a/nodes.py b/nodes.py index e25b840d8..db69fc685 100644 --- a/nodes.py +++ b/nodes.py @@ -2263,11 +2263,7 @@ def init_builtin_extra_nodes(): api_nodes_dir = os.path.join(os.path.dirname(os.path.realpath(__file__)), "comfy_api_nodes") api_nodes_files = [ "nodes_api.py", - ] - - api_nodes_dir = os.path.join(os.path.dirname(os.path.realpath(__file__)), "comfy_api_nodes") - api_nodes_files = [ - "nodes_api.py", + "nodes_veo2.py" ] import_failed = []