diff --git a/comfy_api_nodes/apis/__init__.py b/comfy_api_nodes/apis/__init__.py index 274489c23..393753048 100644 --- a/comfy_api_nodes/apis/__init__.py +++ b/comfy_api_nodes/apis/__init__.py @@ -1,6 +1,6 @@ # generated by datamodel-codegen: -# filename: https://stagingapi.comfy.org/openapi -# timestamp: 2025-05-01T00:26:01+00:00 +# filename: filtered-openapi.yaml +# timestamp: 2025-05-01T00:49:31+00:00 from __future__ import annotations @@ -9,115 +9,61 @@ from enum import Enum from typing import Any, Dict, List, Literal, Optional, Union from uuid import UUID -from pydantic import AnyUrl, BaseModel, Field, RootModel, confloat, conint, constr +from pydantic import AnyUrl, BaseModel, Field, RootModel -bytes_aliased=bytes -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.') - seed: Optional[int] = Field(None, description='The seed value for reproducibility.') - width: conint(ge=64, le=2048) = Field( - ..., description='The width of the image to generate.' - ) +bytes_aliased = bytes -class BFLFluxProGenerateResponse(BaseModel): - id: str = Field(..., description='The unique identifier for the generation task.') - polling_url: str = Field(..., description='URL to poll for the generation result.') - - -class ComfyNode(BaseModel): - category: Optional[str] = Field( +class PersonalAccessToken(BaseModel): + id: Optional[UUID] = Field(None, description="Unique identifier for the GitCommit") + name: 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="Required. The name of the token. Can be a simple description.", ) 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.', + description="Optional. A more detailed description of the token's intended use.", ) - 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' + None, description="[Output Only]The date and time the token 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( + token: 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', + description="[Output Only]. The personal access token. Only returned during creation.", ) -class Error(BaseModel): - details: Optional[List[str]] = Field( - None, - description='Optional detailed information about the error or hints for resolving it.', +class GitCommitSummary(BaseModel): + commit_hash: Optional[str] = Field(None, description="The hash of the commit") + commit_name: Optional[str] = Field(None, description="The name of the commit") + branch_name: Optional[str] = Field( + None, description="The branch where the commit was made" ) - message: Optional[str] = Field( - None, description='A clear and concise description of the error.' + author: Optional[str] = Field(None, description="The author of the commit") + timestamp: Optional[datetime] = Field( + None, description="The timestamp when the commit was made" ) + status_summary: Optional[Dict[str, str]] = Field( + None, description="A map of operating system to status pairs" + ) + + +class User(BaseModel): + id: Optional[str] = Field(None, description="The unique id for this user.") + email: Optional[str] = Field(None, description="The email address for this user.") + name: Optional[str] = Field(None, description="The name for this user.") + isApproved: Optional[bool] = Field( + None, description="Indicates if the user is approved." + ) + isAdmin: Optional[bool] = Field( + None, description="Indicates if the user has admin privileges." + ) + + +class PublisherUser(BaseModel): + id: Optional[str] = Field(None, description="The unique id for this user.") + email: Optional[str] = Field(None, description="The email address for this user.") + name: Optional[str] = Field(None, description="The name for this user.") class ErrorResponse(BaseModel): @@ -125,37 +71,186 @@ class ErrorResponse(BaseModel): 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' +class StorageFile(BaseModel): + id: Optional[UUID] = Field( + None, description="Unique identifier for the storage file" ) - 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' + file_path: Optional[str] = Field(None, description="Path to the file in storage") + public_url: Optional[str] = Field(None, description="Public URL") + + +class PublisherMember(BaseModel): + id: Optional[str] = Field( + None, description="The unique identifier for the publisher member." ) - timestamp: Optional[datetime] = Field( - None, description='The timestamp when the commit was made' + user: Optional[PublisherUser] = Field( + None, description="The user associated with this publisher member." ) + role: Optional[str] = Field( + None, description="The role of the user in the publisher." + ) + + +class ComfyNode(BaseModel): + comfy_node_name: Optional[str] = Field( + None, description="Unique identifier for the node" + ) + category: Optional[str] = Field( + None, + description="UI category where the node is listed, used for grouping nodes.", + ) + description: Optional[str] = Field( + None, description="Brief description of the node's functionality or purpose." + ) + input_types: Optional[str] = Field(None, description="Defines input parameters") + deprecated: Optional[bool] = Field( + None, + description="Indicates if the node is deprecated. Deprecated nodes are hidden in the UI.", + ) + experimental: Optional[bool] = Field( + None, + description="Indicates if the node is experimental, subject to changes or removal.", + ) + 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." + ) + function: Optional[str] = Field( + None, description="Name of the entry-point function to execute the node." + ) + + +class ComfyNodeCloudBuildInfo(BaseModel): + project_id: Optional[str] = None + project_number: Optional[str] = None + location: Optional[str] = None + build_id: Optional[str] = None + + +class Error(BaseModel): + message: Optional[str] = Field( + None, description="A clear and concise description of the error." + ) + details: Optional[List[str]] = Field( + None, + description="Optional detailed information about the error or hints for resolving it.", + ) + + +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 NodeStatus(str, Enum): + NodeStatusActive = "NodeStatusActive" + NodeStatusDeleted = "NodeStatusDeleted" + NodeStatusBanned = "NodeStatusBanned" + + +class NodeVersionStatus(str, Enum): + NodeVersionStatusActive = "NodeVersionStatusActive" + NodeVersionStatusDeleted = "NodeVersionStatusDeleted" + NodeVersionStatusBanned = "NodeVersionStatusBanned" + NodeVersionStatusPending = "NodeVersionStatusPending" + NodeVersionStatusFlagged = "NodeVersionStatusFlagged" + + +class PublisherStatus(str, Enum): + PublisherStatusActive = "PublisherStatusActive" + PublisherStatusBanned = "PublisherStatusBanned" + + +class WorkflowRunStatus(str, Enum): + WorkflowRunStatusStarted = "WorkflowRunStatusStarted" + WorkflowRunStatusFailed = "WorkflowRunStatusFailed" + WorkflowRunStatusCompleted = "WorkflowRunStatusCompleted" + + +class MachineStats(BaseModel): + machine_name: Optional[str] = Field(None, description="Name of the machine.") + os_version: Optional[str] = Field( + None, description="The operating system version. eg. Ubuntu Linux 20.04" + ) + gpu_type: Optional[str] = Field( + None, description="The GPU type. eg. NVIDIA Tesla K80" + ) + cpu_capacity: Optional[str] = Field(None, description="Total CPU on the machine.") + initial_cpu: Optional[str] = Field( + None, description="Initial CPU available before the job starts." + ) + memory_capacity: Optional[str] = Field( + None, description="Total memory on the machine." + ) + initial_ram: Optional[str] = Field( + None, description="Initial RAM available before the job starts." + ) + vram_time_series: Optional[Dict[str, Any]] = Field( + None, description="Time series of VRAM usage." + ) + disk_capacity: Optional[str] = Field( + None, description="Total disk capacity on the machine." + ) + initial_disk: Optional[str] = Field( + None, description="Initial disk available before the job starts." + ) + pip_freeze: Optional[str] = Field(None, description="The pip freeze output") + + +class Customer(BaseModel): + id: str = Field(..., description="The firebase UID of the user") + email: Optional[str] = Field(None, description="The email address for this user") + name: Optional[str] = Field(None, description="The name for this user") + createdAt: Optional[datetime] = Field( + None, description="The date and time the user was created" + ) + updatedAt: Optional[datetime] = Field( + None, description="The date and time the user was last updated" + ) + + +class MagicPrompt(str, Enum): + ON = "ON" + OFF = "OFF" + + +class ColorPalette(BaseModel): + name: str = Field(..., description="Name of the color palette", examples=["PASTEL"]) + + +class StyleCode(RootModel[str]): + root: str = Field(..., pattern="^[0-9A-Fa-f]{8}$") + + +class StyleType(str, Enum): + GENERAL = "GENERAL" class IdeogramColorPalette1(BaseModel): - name: str = Field(..., description='Name of the preset color palette') + name: str = Field(..., description="Name of the preset color palette") class Member(BaseModel): - color: Optional[constr(pattern=r'^#[0-9A-Fa-f]{6}$')] = Field( - None, description='Hexadecimal color code' + color: Optional[str] = Field( + None, description="Hexadecimal color code", pattern="^#[0-9A-Fa-f]{6}$" ) - weight: Optional[confloat(ge=0.0, le=1.0)] = Field( - None, description='Optional weight for the color (0-1)' + weight: Optional[float] = Field( + None, description="Optional weight for the color (0-1)", ge=0.0, le=1.0 ) class IdeogramColorPalette2(BaseModel): members: List[Member] = Field( - ..., description='Array of color definitions with optional weights' + ..., description="Array of color definitions with optional weights" ) @@ -164,232 +259,156 @@ class IdeogramColorPalette( ): root: Union[IdeogramColorPalette1, IdeogramColorPalette2] = Field( ..., - description='A color palette specification that can either use a preset name or explicit color definitions with weights', + description="A color palette specification that can either use a preset name or explicit color definitions with weights", ) class ImageRequest(BaseModel): + prompt: str = Field( + ..., description="Required. The prompt to use to generate the image." + ) aspect_ratio: Optional[str] = Field( None, description="Optional. The aspect ratio (e.g., 'ASPECT_16_9', 'ASPECT_1_1'). Cannot be used with resolution. Defaults to 'ASPECT_1_1' if unspecified.", ) - color_palette: Optional[Dict[str, Any]] = Field( - None, description='Optional. Color palette object. Only for V_2, V_2_TURBO.' - ) + model: str = Field(..., description="The model used (e.g., 'V_2', 'V_2A_TURBO')") magic_prompt_option: Optional[str] = Field( None, description="Optional. MagicPrompt usage ('AUTO', 'ON', 'OFF')." ) - model: str = Field(..., description="The model used (e.g., 'V_2', 'V_2A_TURBO')") - negative_prompt: Optional[str] = Field( + seed: Optional[int] = Field( None, - description='Optional. Description of what to exclude. Only for V_1, V_1_TURBO, V_2, V_2_TURBO.', - ) - num_images: Optional[conint(ge=1, le=8)] = Field( - 1, description='Optional. Number of images to generate (1-8). Defaults to 1.' - ) - prompt: str = Field( - ..., description='Required. The prompt to use to generate the image.' - ) - resolution: Optional[str] = Field( - None, - description="Optional. Resolution (e.g., 'RESOLUTION_1024_1024'). Only for model V_2. Cannot be used with aspect_ratio.", - ) - seed: Optional[conint(ge=0, le=2147483647)] = Field( - None, description='Optional. A number between 0 and 2147483647.' + description="Optional. A number between 0 and 2147483647.", + ge=0, + le=2147483647, ) style_type: Optional[str] = Field( None, description="Optional. Style type ('AUTO', 'GENERAL', 'REALISTIC', 'DESIGN', 'RENDER_3D', 'ANIME'). Only for models V_2 and above.", ) + negative_prompt: Optional[str] = Field( + None, + description="Optional. Description of what to exclude. Only for V_1, V_1_TURBO, V_2, V_2_TURBO.", + ) + num_images: Optional[int] = Field( + 1, + description="Optional. Number of images to generate (1-8). Defaults to 1.", + ge=1, + le=8, + ) + resolution: Optional[str] = Field( + None, + description="Optional. Resolution (e.g., 'RESOLUTION_1024_1024'). Only for model V_2. Cannot be used with aspect_ratio.", + ) + color_palette: Optional[Dict[str, Any]] = Field( + None, description="Optional. Color palette object. Only for V_2, V_2_TURBO." + ) class IdeogramGenerateRequest(BaseModel): image_request: ImageRequest = Field( - ..., description='The image generation request parameters.' + ..., description="The image generation request parameters." ) class Datum(BaseModel): - is_image_safe: Optional[bool] = Field( - None, description='Indicates whether the image is considered safe.' - ) prompt: Optional[str] = Field( - None, description='The prompt used to generate this image.' + None, description="The prompt used to generate this image." ) resolution: Optional[str] = Field( None, description="The resolution of the generated image (e.g., '1024x1024')." ) - seed: Optional[int] = Field( - None, description='The seed value used for this generation.' + is_image_safe: Optional[bool] = Field( + None, description="Indicates whether the image is considered safe." ) + seed: Optional[int] = Field( + None, description="The seed value used for this generation." + ) + url: Optional[str] = Field(None, description="URL to the generated image.") style_type: Optional[str] = Field( None, description="The style type used for generation (e.g., 'REALISTIC', 'ANIME').", ) - url: Optional[str] = Field(None, description='URL to the generated image.') class IdeogramGenerateResponse(BaseModel): created: Optional[datetime] = Field( - None, description='Timestamp when the generation was created.' + None, description="Timestamp when the generation was created." ) data: Optional[List[Datum]] = Field( - None, description='Array of generated image information.' + None, description="Array of generated image information." ) -class ColorPalette(BaseModel): - name: str = Field(..., description='Name of the color palette', examples=['PASTEL']) - - -class MagicPrompt(str, Enum): - ON = 'ON' - OFF = 'OFF' - - -class StyleType(str, Enum): - GENERAL = 'GENERAL' - - -class KlingErrorResponse(BaseModel): - code: int = Field( - ..., - 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( - ..., description='Request ID for tracking and troubleshooting' - ) - - -class AspectRatio(str, Enum): - field_16_9 = '16:9' - field_9_16 = '9:16' - field_1_1 = '1:1' - - -class Config(BaseModel): - horizontal: Optional[confloat(ge=-10.0, le=10.0)] = Field( - None, - 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 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 CameraControl(BaseModel): - config: Optional[Config] = None - type: Optional[Type] = Field( - None, - 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 Duration(str, Enum): - field_5 = '5' - field_10 = '10' - - -class Trajectory(BaseModel): - x: Optional[int] = Field( - None, - 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 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' - kling_v2_master = 'kling-v2-master' + kling_v1 = "kling-v1" + kling_v1_6 = "kling-v1-6" + kling_v2_master = "kling-v2-master" -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.', +class Mode(str, Enum): + std = "std" + pro = "pro" + + +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 Config(BaseModel): + horizontal: Optional[float] = Field(None, ge=-10.0, le=10.0) + vertical: Optional[float] = Field(None, ge=-10.0, le=10.0) + pan: Optional[float] = Field(None, ge=-10.0, le=10.0) + tilt: Optional[float] = Field(None, ge=-10.0, le=10.0) + roll: Optional[float] = Field(None, ge=-10.0, le=10.0) + zoom: Optional[float] = Field(None, ge=-10.0, le=10.0) + + +class CameraControl(BaseModel): + type: Optional[Type] = Field(None, description="Predefined camera movements type") + config: Optional[Config] = None + + +class AspectRatio(str, Enum): + field_16_9 = "16:9" + field_9_16 = "9:16" + field_1_1 = "1:1" + + +class Duration(str, Enum): + field_5 = "5" + field_10 = "10" + + +class KlingText2VideoRequest(BaseModel): + model_name: Optional[ModelName] = Field("kling-v1", description="Model Name") + prompt: Optional[str] = Field( + None, description="Positive text prompt", max_length=2500 ) + negative_prompt: Optional[str] = Field( + None, description="Negative text prompt", max_length=2500 + ) + cfg_scale: Optional[float] = Field( + 0.5, description="Flexibility in video generation", ge=0.0, le=1.0 + ) + mode: Optional[Mode] = Field("std", description="Video generation mode") 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[str] = 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[str] = 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.', + aspect_ratio: Optional[AspectRatio] = "16:9" + duration: Optional[Duration] = "5" + callback_url: Optional[AnyUrl] = Field( + None, description="The callback notification address" ) + external_task_id: Optional[str] = Field(None, description="Customized Task ID") + + +class TaskStatus(str, Enum): + submitted = "submitted" + processing = "processing" + succeed = "succeed" + failed = "failed" class TaskInfo(BaseModel): @@ -397,76 +416,148 @@ class TaskInfo(BaseModel): 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') + id: Optional[str] = Field(None, description="Generated video ID") + url: Optional[AnyUrl] = Field(None, description="URL for generated video") + duration: Optional[str] = Field(None, description="Total video duration") 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_id: Optional[str] = Field(None, description="Task ID") task_status: Optional[TaskStatus] = None - updated_at: Optional[int] = Field(None, description='Task update time') + task_info: Optional[TaskInfo] = None + created_at: Optional[int] = Field(None, description="Task creation time") + updated_at: Optional[int] = Field(None, description="Task update time") + task_result: Optional[TaskResult] = None -class KlingImage2VideoResponse(BaseModel): - code: Optional[int] = Field(None, description='Error code') +class KlingText2VideoResponse(BaseModel): + code: Optional[int] = Field(None, description="Error code") + message: Optional[str] = Field(None, description="Error message") + request_id: Optional[str] = Field(None, description="Request ID") data: Optional[Data] = None - message: Optional[str] = Field(None, description='Error message') - request_id: Optional[str] = Field(None, description='Request ID') - - -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 ModelName1(str, Enum): - kling_v1 = 'kling-v1' - kling_v1_6 = 'kling-v1-6' - kling_v2_master = 'kling-v2-master' + kling_v1 = "kling-v1" + kling_v1_5 = "kling-v1-5" + kling_v1_6 = "kling-v1-6" + kling_v2_master = "kling-v2-master" -class KlingText2VideoRequest(BaseModel): - aspect_ratio: Optional[AspectRatio] = '16:9' - callback_url: Optional[AnyUrl] = Field( - None, description='The callback notification address' +class Trajectory(BaseModel): + x: Optional[int] = Field( + None, + 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 Config1(BaseModel): + horizontal: Optional[float] = Field( + None, + description="Controls camera's movement along horizontal axis (x-axis). Negative indicates left, positive indicates right.", + ge=-10.0, + le=10.0, + ) + vertical: Optional[float] = Field( + None, + description="Controls camera's movement along vertical axis (y-axis). Negative indicates downward, positive indicates upward.", + ge=-10.0, + le=10.0, + ) + pan: Optional[float] = Field( + None, + description="Controls camera's rotation in vertical plane (x-axis). Negative indicates downward rotation, positive indicates upward rotation.", + ge=-10.0, + le=10.0, + ) + tilt: Optional[float] = Field( + None, + description="Controls camera's rotation in horizontal plane (y-axis). Negative indicates left rotation, positive indicates right rotation.", + ge=-10.0, + le=10.0, + ) + roll: Optional[float] = Field( + None, + description="Controls camera's rolling amount (z-axis). Negative indicates counterclockwise, positive indicates clockwise.", + ge=-10.0, + le=10.0, + ) + zoom: Optional[float] = Field( + None, + description="Controls change in camera's focal length. Negative indicates narrower field of view, positive indicates wider field of view.", + ge=-10.0, + le=10.0, + ) + + +class CameraControl1(BaseModel): + type: Optional[Type] = Field( + None, + 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.", + ) + config: Optional[Config1] = None + + +class KlingImage2VideoRequest(BaseModel): + model_name: Optional[ModelName1] = Field("kling-v1", description="Model Name") + image: Optional[str] = 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[str] = 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.", + ) + prompt: Optional[str] = Field( + None, description="Positive text prompt", max_length=2500 + ) + negative_prompt: Optional[str] = Field( + None, description="Negative text prompt", max_length=2500 + ) + cfg_scale: Optional[float] = 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.", + ge=0.0, + le=1.0, + ) + 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.", + ) + 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.", + ) + 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.", ) camera_control: Optional[CameraControl1] = None - cfg_scale: Optional[confloat(ge=0.0, le=1.0)] = Field( - 0.5, description='Flexibility in video generation' + aspect_ratio: Optional[AspectRatio] = "16:9" + duration: Optional[Duration] = Field("5", description="Video length in seconds") + callback_url: Optional[AnyUrl] = Field( + None, + description="The callback notification address. Server will notify when the task status changes.", ) - duration: Optional[Duration] = '5' - external_task_id: Optional[str] = Field(None, description='Customized Task ID') - mode: Optional[Mode] = Field('std', description='Video generation mode') - model_name: Optional[ModelName1] = 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' + external_task_id: Optional[str] = Field( + None, + description="Customized Task ID. Must be unique within a single user account.", ) @@ -475,875 +566,44 @@ class TaskResult1(BaseModel): class Data1(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[TaskResult1] = None + task_id: Optional[str] = Field(None, description="Task ID") task_status: Optional[TaskStatus] = None - updated_at: Optional[int] = Field(None, description='Task update time') + task_info: Optional[TaskInfo] = None + created_at: Optional[int] = Field(None, description="Task creation time") + updated_at: Optional[int] = Field(None, description="Task update time") + task_result: Optional[TaskResult1] = None -class KlingText2VideoResponse(BaseModel): - code: Optional[int] = Field(None, description='Error code') +class KlingImage2VideoResponse(BaseModel): + code: Optional[int] = Field(None, description="Error code") + message: Optional[str] = Field(None, description="Error message") + request_id: Optional[str] = Field(None, description="Request ID") data: Optional[Data1] = 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 Object(str, Enum): + event = "event" class Type2(str, Enum): - generation = 'generation' + payment_intent_succeeded = "payment_intent.succeeded" -class LumaGenerationReference(BaseModel): - id: UUID = Field(..., description='The ID of the generation') - type: Literal['generation'] +class StripeRequestInfo(BaseModel): + id: Optional[str] = None + idempotency_key: Optional[str] = None -class GenerationType1(str, Enum): - video = 'video' +class Object1(str, Enum): + payment_intent = "payment_intent" -class LumaGenerationType(str, Enum): - video = 'video' - image = 'image' +class StripeAmountDetails(BaseModel): + tip: Optional[Dict[str, Any]] = None -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_flash_2 = 'ray-flash-2' - ray_1_6 = 'ray-1-6' - - -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.' - ) - - -class MinimaxBaseResponse(BaseModel): - status_code: int = Field( - ..., - description='Status code. 0 indicates success, other values indicate errors.', - ) - status_msg: str = Field( - ..., description='Specific error details or success message.' - ) - - -class File(BaseModel): - bytes: Optional[int] = Field(None, description='File size in bytes') - created_at: Optional[int] = Field( - None, description='Unix timestamp when the file was created, in seconds' - ) - download_url: Optional[str] = Field( - None, description='The URL to download the video' - ) - file_id: Optional[int] = Field(None, description='Unique identifier for the file') - filename: Optional[str] = Field(None, description='The name of the file') - purpose: Optional[str] = Field(None, description='The purpose of using the file') - - -class MinimaxFileRetrieveResponse(BaseModel): - base_resp: MinimaxBaseResponse - file: File - - -class Status(str, Enum): - Queueing = 'Queueing' - Preparing = 'Preparing' - Processing = 'Processing' - Success = 'Success' - Fail = 'Fail' - - -class MinimaxTaskResultResponse(BaseModel): - base_resp: MinimaxBaseResponse - file_id: Optional[str] = Field( - None, - description='After the task status changes to Success, this field returns the file ID corresponding to the generated video.', - ) - status: Status = Field( - ..., - description="Task status: 'Queueing' (in queue), 'Preparing' (task is preparing), 'Processing' (generating), 'Success' (task completed successfully), or 'Fail' (task failed).", - ) - task_id: str = Field(..., description='The task ID being queried.') - - -class Model(str, Enum): - T2V_01_Director = 'T2V-01-Director' - I2V_01_Director = 'I2V-01-Director' - S2V_01 = 'S2V-01' - I2V_01 = 'I2V-01' - I2V_01_live = 'I2V-01-live' - T2V_01 = 'T2V-01' - - -class SubjectReferenceItem(BaseModel): - image: Optional[str] = Field( - None, description='URL or base64 encoding of the subject reference image.' - ) - mask: Optional[str] = Field( - None, - description='URL or base64 encoding of the mask for the subject reference image.', - ) - - -class MinimaxVideoGenerationRequest(BaseModel): - callback_url: Optional[str] = Field( - None, - description='Optional. URL to receive real-time status updates about the video generation task.', - ) - first_frame_image: Optional[str] = Field( - None, - description='URL or base64 encoding of the first frame image. Required when model is I2V-01, I2V-01-Director, or I2V-01-live.', - ) - model: Model = Field( - ..., - description='Required. ID of model. Options: T2V-01-Director, I2V-01-Director, S2V-01, I2V-01, I2V-01-live, T2V-01', - ) - prompt: Optional[constr(max_length=2000)] = Field( - None, - description='Description of the video. Should be less than 2000 characters. Supports camera movement instructions in [brackets].', - ) - prompt_optimizer: Optional[bool] = Field( - True, - description='If true (default), the model will automatically optimize the prompt. Set to false for more precise control.', - ) - subject_reference: Optional[List[SubjectReferenceItem]] = Field( - None, - description='Only available when model is S2V-01. The model will generate a video based on the subject uploaded through this parameter.', - ) - - -class MinimaxVideoGenerationResponse(BaseModel): - base_resp: MinimaxBaseResponse - task_id: str = Field( - ..., description='The task ID for the asynchronous video generation task.' - ) - - -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'] - ) - model: str = Field( - ..., description='The model to use for image editing', examples=['gpt-image-1'] - ) - moderation: Optional[Moderation] = Field( - None, description='Content moderation setting', examples=['auto'] - ) - n: Optional[int] = Field( - None, description='The number of images to generate', examples=[1] - ) - output_compression: Optional[int] = Field( - None, description='Compression level for JPEG or WebP (0-100)', examples=[100] - ) - output_format: Optional[OutputFormat] = Field( - None, description='Format of the output image', examples=['png'] - ) - prompt: str = Field( - ..., - description='A text description of the desired edit', - examples=['Give the rocketship rainbow coloring'], - ) - quality: Optional[str] = Field( - None, description='The quality of the edited image', examples=['low'] - ) - size: Optional[str] = Field( - None, description='Size of the output image', examples=['1024x1024'] - ) - user: Optional[str] = Field( - None, - description='A unique identifier for end-user monitoring', - examples=['user-1234'], - ) - - -class Background(str, Enum): - transparent = 'transparent' - opaque = 'opaque' - - -class Quality(str, Enum): - low = 'low' - medium = 'medium' - high = 'high' - standard = 'standard' - hd = 'hd' - - -class ResponseFormat(str, Enum): - url = 'url' - b64_json = 'b64_json' - - -class Style(str, Enum): - vivid = 'vivid' - natural = 'natural' - - -class OpenAIImageGenerationRequest(BaseModel): - background: Optional[Background] = Field( - None, description='Background transparency', examples=['opaque'] - ) - model: Optional[str] = Field( - None, description='The model to use for image generation', examples=['dall-e-3'] - ) - moderation: Optional[Moderation] = Field( - None, description='Content moderation setting', examples=['auto'] - ) - n: Optional[int] = Field( - None, - description='The number of images to generate (1-10). Only 1 supported for dall-e-3.', - examples=[1], - ) - output_compression: Optional[int] = Field( - None, description='Compression level for JPEG or WebP (0-100)', examples=[100] - ) - output_format: Optional[OutputFormat] = Field( - None, description='Format of the output image', examples=['png'] - ) - prompt: str = Field( - ..., - description='A text description of the desired image', - examples=['Draw a rocket in front of a blackhole in deep space'], - ) - quality: Optional[Quality] = Field( - None, description='The quality of the generated image', examples=['high'] - ) - response_format: Optional[ResponseFormat] = Field( - None, description='Response format of image data', examples=['b64_json'] - ) - size: Optional[str] = Field( - None, - description='Size of the image (e.g., 1024x1024, 1536x1024, auto)', - examples=['1024x1536'], - ) - style: Optional[Style] = Field( - None, description='Style of the image (only for dall-e-3)', examples=['vivid'] - ) - user: Optional[str] = Field( - None, - description='A unique identifier for end-user monitoring', - examples=['user-1234'], - ) - - -class Datum1(BaseModel): - b64_json: Optional[str] = Field(None, description='Base64 encoded image data') - revised_prompt: Optional[str] = Field(None, description='Revised prompt') - 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 PersonalAccessToken(BaseModel): - createdAt: Optional[datetime] = Field( - None, description='[Output Only]The date and time the token was created.' - ) - description: Optional[str] = Field( - None, - 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 IngredientsMode(str, Enum): - creative = 'creative' - precise = 'precise' - - -class PikaBodyGenerate22C2vGenerate22PikascenesPost(BaseModel): - aspectRatio: Optional[confloat(ge=0.4, le=2.5)] = Field( - None, description='Aspect ratio (width / height)', title='Aspectratio' - ) - duration: Optional[int] = Field(5, title='Duration') - images: List[bytes_aliased] = Field( - ..., description='Array of images to process', title='Images' - ) - ingredientsMode: IngredientsMode = Field(..., title='Ingredientsmode') - negativePrompt: Optional[str] = Field(None, title='Negativeprompt') - promptText: Optional[str] = Field(None, title='Prompttext') - resolution: Optional[str] = Field('1080p', title='Resolution') - seed: Optional[int] = Field(None, title='Seed') - - -class PikaBodyGenerate22I2vGenerate22I2vPost(BaseModel): - duration: Optional[int] = Field(5, title='Duration') - image: bytes_aliased = Field(..., title='Image') - negativePrompt: Optional[str] = Field(None, title='Negativeprompt') - promptText: Optional[str] = Field(None, title='Prompttext') - resolution: Optional[str] = Field('1080p', title='Resolution') - seed: Optional[int] = Field(None, title='Seed') - - -class PikaBodyGenerate22KeyframeGenerate22PikaframesPost(BaseModel): - duration: Optional[int] = Field(5, title='Duration') - keyFrames: List[bytes_aliased] = Field( - ..., description='Array of keyframe images', title='Keyframes' - ) - negativePrompt: Optional[str] = Field(None, title='Negativeprompt') - promptText: str = Field(..., title='Prompttext') - resolution: Optional[str] = Field('1080p', title='Resolution') - seed: Optional[int] = Field(None, title='Seed') - - -class PikaBodyGenerate22T2vGenerate22T2vPost(BaseModel): - aspectRatio: Optional[confloat(ge=0.4, le=2.5)] = Field( - None, description='Aspect ratio (width / height)', title='Aspectratio' - ) - duration: Optional[int] = Field(5, title='Duration') - negativePrompt: Optional[str] = Field(None, title='Negativeprompt') - promptText: str = Field(..., title='Prompttext') - resolution: Optional[str] = Field('1080p', title='Resolution') - seed: Optional[int] = Field(None, title='Seed') - - -class PikaGenerateResponse(BaseModel): - video_id: str = Field(..., title='Video Id') - - -class PikaValidationError(BaseModel): - loc: List[Union[str, int]] = Field(..., title='Location') - msg: str = Field(..., title='Message') - type: str = Field(..., title='Error Type') - - -class PikaVideoResponse(BaseModel): - id: str = Field(..., title='Id') - progress: int = Field(..., title='Progress') - status: str = Field(..., title='Status') - url: str = Field(..., title='Url') - - -class Resp(BaseModel): - img_id: Optional[int] = None - - -class PixverseImageUploadResponse(BaseModel): - ErrCode: Optional[int] = None - ErrMsg: Optional[str] = None - Resp_1: Optional[Resp] = Field(None, alias='Resp') - - -class Duration2(int, Enum): - integer_5 = 5 - integer_8 = 8 - - -class Model1(str, Enum): - v3_5 = 'v3.5' - - -class MotionMode(str, Enum): - normal = 'normal' - fast = 'fast' - - -class Quality1(str, Enum): - field_360p = '360p' - field_540p = '540p' - field_720p = '720p' - field_1080p = '1080p' - - -class Style1(str, Enum): - anime = 'anime' - field_3d_animation = '3d_animation' - clay = 'clay' - comic = 'comic' - cyberpunk = 'cyberpunk' - - -class PixverseImageVideoRequest(BaseModel): - duration: Duration2 - img_id: int - model: Model1 - motion_mode: Optional[MotionMode] = None - prompt: str - quality: Quality1 - seed: Optional[int] = None - style: Optional[Style1] = None - template_id: Optional[int] = None - water_mark: Optional[bool] = None - - -class AspectRatio2(str, Enum): - field_16_9 = '16:9' - field_4_3 = '4:3' - field_1_1 = '1:1' - field_3_4 = '3:4' - field_9_16 = '9:16' - - -class PixverseTextVideoRequest(BaseModel): - aspect_ratio: AspectRatio2 - duration: Duration2 - model: Model1 - motion_mode: Optional[MotionMode] = None - negative_prompt: Optional[str] = None - prompt: str - quality: Quality1 - seed: Optional[int] = None - style: Optional[Style1] = None - template_id: Optional[int] = None - water_mark: Optional[bool] = None - - -class PixverseTransitionVideoRequest(BaseModel): - duration: Duration2 - first_frame_img: int - last_frame_img: int - model: Model1 - motion_mode: MotionMode - prompt: str - quality: Quality1 - seed: int - style: Optional[Style1] = None - template_id: Optional[int] = None - water_mark: Optional[bool] = None - - -class Resp1(BaseModel): - video_id: Optional[int] = None - - -class PixverseVideoResponse(BaseModel): - ErrCode: Optional[int] = None - ErrMsg: Optional[str] = None - Resp: Optional[Resp1] = None - - -class Status1(int, Enum): - integer_1 = 1 - integer_5 = 5 - integer_6 = 6 - integer_7 = 7 - integer_8 = 8 - - -class Resp2(BaseModel): - create_time: Optional[str] = None - id: Optional[int] = None - modify_time: Optional[str] = None - negative_prompt: Optional[str] = None - outputHeight: Optional[int] = None - outputWidth: Optional[int] = None - prompt: Optional[str] = None - resolution_ratio: Optional[int] = None - seed: Optional[int] = None - size: Optional[int] = None - status: Optional[Status1] = Field( - None, - description='Video generation status codes:\n* 1 - Generation successful\n* 5 - Generating\n* 6 - Deleted\n* 7 - Contents moderation failed\n* 8 - Generation failed\n', - ) - style: Optional[str] = None - url: Optional[str] = None - - -class PixverseVideoResultResponse(BaseModel): - ErrCode: Optional[int] = None - ErrMsg: Optional[str] = None - Resp: Optional[Resp2] = None - - -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 RgbItem(RootModel[conint(ge=0, le=255)]): - root: conint(ge=0, le=255) - - -class RGBColor(BaseModel): - rgb: List[RgbItem] = Field(..., max_length=3, min_length=3) - - -class Controls(BaseModel): - artistic_level: Optional[conint(ge=0, le=5)] = Field( - None, - description='Defines artistic tone of your image. At a simple level, the person looks straight at the camera in a static and clean style. Dynamic and eccentric levels introduce movement and creativity.', - ) - background_color: Optional[RGBColor] = None - colors: Optional[List[RGBColor]] = Field( - None, description='An array of preferable colors' - ) - no_text: Optional[bool] = Field(None, description='Do not embed text layouts') - - -class RecraftImageGenerationRequest(BaseModel): - controls: Optional[Controls] = Field( - None, description='The controls for the generated image' - ) - 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")', - ) - style_id: Optional[str] = Field( - None, - description='The style ID to apply to the generated image (e.g., "123e4567-e89b-12d3-a456-426614174000"). If style_id is provided, style should not be provided.', - ) - - -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 RenderingSpeed(str, Enum): - BALANCED = 'BALANCED' - TURBO = 'TURBO' - QUALITY = 'QUALITY' - - -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 Name(str, Enum): - content_moderation = 'content_moderation' - - -class StabilityContentModerationResponse(BaseModel): - errors: List[str] = Field( - ..., - description='One or more error messages indicating what went wrong.', - examples=[['some-field: is required']], - min_length=1, - ) - id: constr(min_length=1) = Field( - ..., - description='A unique identifier associated with this error. Please include this in any [support tickets](https://kb.stability.ai/knowledge-base/kb-tickets/new) you file, as it will greatly assist us in diagnosing the root cause of the problem.', - examples=['a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4'], - ) - name: Name = Field( - ..., - description='Our content moderation system has flagged some part of your request and subsequently denied it. You were not charged for this request. While this may at times be frustrating, it is necessary to maintain the integrity of our platform and ensure a safe experience for all users. If you would like to provide feedback, please use the [Support Form](https://kb.stability.ai/knowledge-base/kb-tickets/new).', - ) - - -class StabilityStabilityClientID(RootModel[constr(max_length=256)]): - root: constr(max_length=256) = Field( - ..., - description='The name of your application, used to help us communicate app-specific debugging or moderation issues to you.', - examples=['my-awesome-app'], - ) - - -class StabilityStabilityClientUserID(RootModel[constr(max_length=256)]): - root: constr(max_length=256) = Field( - ..., - description='A unique identifier for your end user. Used to help us communicate user-specific debugging or moderation issues to you. Feel free to obfuscate this value to protect user privacy.', - examples=['DiscordUser#9999'], - ) - - -class StabilityStabilityClientVersion(RootModel[constr(max_length=256)]): - root: constr(max_length=256) = Field( - ..., - description='The version of your application, used to help us communicate version-specific debugging or moderation issues to you.', - examples=['1.2.1'], - ) - - -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 Object2(str, Enum): + charge = "charge" class StripeAddress(BaseModel): @@ -1355,16 +615,16 @@ class StripeAddress(BaseModel): 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 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 Checks(BaseModel): @@ -1419,37 +679,12 @@ class StripeCardDetails(BaseModel): 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 StripeRefundList(BaseModel): + object: Optional[str] = None + data: Optional[List[Dict[str, Any]]] = None + has_more: Optional[bool] = None + total_count: Optional[int] = None + url: Optional[str] = None class Card(BaseModel): @@ -1463,19 +698,6 @@ 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 @@ -1484,67 +706,460 @@ class StripeShipping(BaseModel): 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.' +class Model(str, Enum): + T2V_01_Director = "T2V-01-Director" + I2V_01_Director = "I2V-01-Director" + S2V_01 = "S2V-01" + I2V_01 = "I2V-01" + I2V_01_live = "I2V-01-live" + T2V_01 = "T2V-01" + + +class SubjectReferenceItem(BaseModel): + image: Optional[str] = Field( + None, description="URL or base64 encoding of the subject reference image." ) - 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 Error1(BaseModel): - code: Optional[int] = Field(None, description='Error code') - message: Optional[str] = Field(None, description='Error message') - - -class Video2(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( + mask: Optional[str] = Field( None, - alias='@type', - examples=[ - 'type.googleapis.com/cloud.ai.large_models.vision.GenerateVideoResponse' - ], + description="URL or base64 encoding of the mask for the subject reference image.", ) - 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[Video2]] = None -class Veo2GenVidPollResponse(BaseModel): - done: Optional[bool] = None - error: Optional[Error1] = Field( - None, description='Error details if operation failed' +class MinimaxVideoGenerationRequest(BaseModel): + model: Model = Field( + ..., + description="Required. ID of model. Options: T2V-01-Director, I2V-01-Director, S2V-01, I2V-01, I2V-01-live, T2V-01", ) - name: Optional[str] = None - response: Optional[Response] = Field( - None, description='The actual prediction response if done is true' + prompt: Optional[str] = Field( + None, + description="Description of the video. Should be less than 2000 characters. Supports camera movement instructions in [brackets].", + max_length=2000, ) + prompt_optimizer: Optional[bool] = Field( + True, + description="If true (default), the model will automatically optimize the prompt. Set to false for more precise control.", + ) + first_frame_image: Optional[str] = Field( + None, + description="URL or base64 encoding of the first frame image. Required when model is I2V-01, I2V-01-Director, or I2V-01-live.", + ) + subject_reference: Optional[List[SubjectReferenceItem]] = Field( + None, + description="Only available when model is S2V-01. The model will generate a video based on the subject uploaded through this parameter.", + ) + callback_url: Optional[str] = Field( + None, + description="Optional. URL to receive real-time status updates about the video generation task.", + ) + + +class MinimaxBaseResponse(BaseModel): + status_code: int = Field( + ..., + description="Status code. 0 indicates success, other values indicate errors.", + ) + status_msg: str = Field( + ..., description="Specific error details or success message." + ) + + +class MinimaxVideoGenerationResponse(BaseModel): + task_id: str = Field( + ..., description="The task ID for the asynchronous video generation task." + ) + base_resp: MinimaxBaseResponse + + +class File(BaseModel): + file_id: Optional[int] = Field(None, description="Unique identifier for the file") + bytes: Optional[int] = Field(None, description="File size in bytes") + created_at: Optional[int] = Field( + None, description="Unix timestamp when the file was created, in seconds" + ) + filename: Optional[str] = Field(None, description="The name of the file") + purpose: Optional[str] = Field(None, description="The purpose of using the file") + download_url: Optional[str] = Field( + None, description="The URL to download the video" + ) + + +class MinimaxFileRetrieveResponse(BaseModel): + file: File + base_resp: MinimaxBaseResponse + + +class Status(str, Enum): + Queueing = "Queueing" + Preparing = "Preparing" + Processing = "Processing" + Success = "Success" + Fail = "Fail" + + +class MinimaxTaskResultResponse(BaseModel): + task_id: str = Field(..., description="The task ID being queried.") + status: Status = Field( + ..., + description="Task status: 'Queueing' (in queue), 'Preparing' (task is preparing), 'Processing' (generating), 'Success' (task completed successfully), or 'Fail' (task failed).", + ) + file_id: Optional[str] = Field( + None, + description="After the task status changes to Success, this field returns the file ID corresponding to the generated video.", + ) + base_resp: MinimaxBaseResponse + + +class BFLFluxProGenerateRequest(BaseModel): + prompt: str = Field(..., description="The text prompt for image generation.") + negative_prompt: Optional[str] = Field( + None, description="The negative prompt for image generation." + ) + width: int = Field( + ..., description="The width of the image to generate.", ge=64, le=2048 + ) + height: int = Field( + ..., description="The height of the image to generate.", ge=64, le=2048 + ) + num_inference_steps: Optional[int] = Field( + None, description="The number of inference steps.", ge=1, le=100 + ) + guidance_scale: Optional[float] = Field( + None, description="The guidance scale for generation.", ge=1.0, le=20.0 + ) + seed: Optional[int] = Field(None, description="The seed value for reproducibility.") + num_images: Optional[int] = Field( + None, description="The number of images to generate.", ge=1, le=4 + ) + + +class BFLFluxProGenerateResponse(BaseModel): + id: str = Field(..., description="The unique identifier for the generation task.") + polling_url: str = Field(..., description="URL to poll for the generation result.") + + +class Datum1(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[Datum1] = Field(..., description="Array of generated image information") + + +class KlingErrorResponse(BaseModel): + code: int = Field( + ..., + 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( + ..., description="Request ID for tracking and troubleshooting" + ) + + +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 LumaVideoModel(str, Enum): + ray_2 = "ray-2" + ray_flash_2 = "ray-flash-2" + ray_1_6 = "ray-1-6" + + +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 LumaVideoModelOutputDuration1(str, Enum): + field_5s = "5s" + field_9s = "9s" + + +class LumaVideoModelOutputDuration( + RootModel[Union[LumaVideoModelOutputDuration1, str]] +): + root: Union[LumaVideoModelOutputDuration1, str] + + +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 LumaImageIdentity(BaseModel): + images: Optional[List[AnyUrl]] = Field( + None, description="The URLs of the image identity" + ) + + +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 Type3(str, Enum): + generation = "generation" + + +class LumaGenerationReference(BaseModel): + type: Literal["generation"] + id: UUID = Field(..., description="The ID of the generation") + + +class Type4(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 LumaGenerationType(str, Enum): + video = "video" + image = "image" + + +class LumaState(str, Enum): + queued = "queued" + dreaming = "dreaming" + completed = "completed" + failed = "failed" + + +class LumaAssets(BaseModel): + video: Optional[AnyUrl] = Field(None, description="The URL of the video") + image: Optional[AnyUrl] = Field(None, description="The URL of the image") + progress_video: Optional[AnyUrl] = Field( + None, description="The URL of the progress video" + ) + + +class GenerationType(str, Enum): + video = "video" + + +class GenerationType1(str, Enum): + image = "image" + + +class CharacterRef(BaseModel): + identity0: Optional[LumaImageIdentity] = None + + +class LumaImageGenerationRequest(BaseModel): + generation_type: Optional[GenerationType1] = "image" + model: Optional[LumaImageModel] = "photon-1" + prompt: Optional[str] = Field(None, description="The prompt of the generation") + aspect_ratio: Optional[LumaAspectRatio] = "16:9" + callback_url: Optional[AnyUrl] = Field( + None, description="The callback URL for the generation" + ) + image_ref: Optional[List[LumaImageRef]] = None + style_ref: Optional[List[LumaImageRef]] = None + character_ref: Optional[CharacterRef] = None + modify_image_ref: Optional[LumaModifyImageRef] = None + + +class GenerationType2(str, Enum): + upscale_video = "upscale_video" + + +class LumaUpscaleVideoGenerationRequest(BaseModel): + generation_type: Optional[GenerationType2] = "upscale_video" + resolution: Optional[LumaVideoModelOutputResolution] = None + callback_url: Optional[AnyUrl] = Field( + None, description="The callback URL for the upscale" + ) + + +class GenerationType3(str, Enum): + add_audio = "add_audio" + + +class LumaAudioGenerationRequest(BaseModel): + generation_type: Optional[GenerationType3] = "add_audio" + prompt: Optional[str] = Field(None, description="The prompt of the audio") + negative_prompt: Optional[str] = Field( + None, description="The negative prompt of the audio" + ) + callback_url: Optional[AnyUrl] = Field( + None, description="The callback URL for the audio" + ) + + +class LumaError(BaseModel): + detail: Optional[str] = Field(None, description="The error message") + + +class AspectRatio2(str, Enum): + field_16_9 = "16:9" + field_4_3 = "4:3" + field_1_1 = "1:1" + field_3_4 = "3:4" + field_9_16 = "9:16" + + +class Duration2(int, Enum): + integer_5 = 5 + integer_8 = 8 + + +class Model1(str, Enum): + v3_5 = "v3.5" + + +class MotionMode(str, Enum): + normal = "normal" + fast = "fast" + + +class Quality(str, Enum): + field_360p = "360p" + field_540p = "540p" + field_720p = "720p" + field_1080p = "1080p" + + +class Style(str, Enum): + anime = "anime" + field_3d_animation = "3d_animation" + clay = "clay" + comic = "comic" + cyberpunk = "cyberpunk" + + +class PixverseTextVideoRequest(BaseModel): + aspect_ratio: AspectRatio2 + duration: Duration2 + model: Model1 + motion_mode: Optional[MotionMode] = None + negative_prompt: Optional[str] = None + prompt: str + quality: Quality + seed: Optional[int] = None + style: Optional[Style] = None + template_id: Optional[int] = None + water_mark: Optional[bool] = None + + +class Resp(BaseModel): + video_id: Optional[int] = None + + +class PixverseVideoResponse(BaseModel): + ErrCode: Optional[int] = None + ErrMsg: Optional[str] = None + Resp_1: Optional[Resp] = Field(None, alias="Resp") + + +class Resp1(BaseModel): + img_id: Optional[int] = None + + +class PixverseImageUploadResponse(BaseModel): + ErrCode: Optional[int] = None + ErrMsg: Optional[str] = None + Resp: Optional[Resp1] = None + + +class PixverseImageVideoRequest(BaseModel): + img_id: int + model: Model1 + prompt: str + duration: Duration2 + quality: Quality + motion_mode: Optional[MotionMode] = None + seed: Optional[int] = None + style: Optional[Style] = None + template_id: Optional[int] = None + water_mark: Optional[bool] = None + + +class PixverseTransitionVideoRequest(BaseModel): + first_frame_img: int + last_frame_img: int + model: Model1 + duration: Duration2 + quality: Quality + motion_mode: MotionMode + seed: int + prompt: str + style: Optional[Style] = None + template_id: Optional[int] = None + water_mark: Optional[bool] = None + + +class Status1(int, Enum): + integer_1 = 1 + integer_5 = 5 + integer_6 = 6 + integer_7 = 7 + integer_8 = 8 + + +class Resp2(BaseModel): + create_time: Optional[str] = None + id: Optional[int] = None + modify_time: Optional[str] = None + negative_prompt: Optional[str] = None + outputHeight: Optional[int] = None + outputWidth: Optional[int] = None + prompt: Optional[str] = None + resolution_ratio: Optional[int] = None + seed: Optional[int] = None + size: Optional[int] = None + status: Optional[Status1] = Field( + None, + description="Video generation status codes:\n* 1 - Generation successful\n* 5 - Generating\n* 6 - Deleted\n* 7 - Contents moderation failed\n* 8 - Generation failed\n", + ) + style: Optional[str] = None + url: Optional[str] = None + + +class PixverseVideoResultResponse(BaseModel): + ErrCode: Optional[int] = None + ErrMsg: Optional[str] = None + Resp: Optional[Resp2] = None class Image(BaseModel): @@ -1560,28 +1175,28 @@ class Image1(BaseModel): class Instance(BaseModel): + prompt: str = Field(..., description="Text description of the video") image: Optional[Union[Image, Image1]] = Field( - None, description='Optional image to guide video generation' + 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' + ALLOW = "ALLOW" + BLOCK = "BLOCK" class Parameters(BaseModel): - aspectRatio: Optional[str] = Field(None, examples=['16:9']) - durationSeconds: Optional[int] = None - enhancePrompt: Optional[bool] = None + aspectRatio: Optional[str] = Field(None, examples=["16:9"]) 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' + None, description="Optional Cloud Storage URI to upload the video" ) + durationSeconds: Optional[int] = None + enhancePrompt: Optional[bool] = None class Veo2GenVidRequest(BaseModel): @@ -1592,234 +1207,771 @@ class Veo2GenVidRequest(BaseModel): class Veo2GenVidResponse(BaseModel): name: str = Field( ..., - description='Operation resource name', + description="Operation resource name", examples=[ - 'projects/PROJECT_ID/locations/us-central1/publishers/google/models/MODEL_ID/operations/a1b07c8e-7b5a-4aba-bb34-3e1ccb8afcc8' + "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 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 Video2(BaseModel): + gcsUri: Optional[str] = Field(None, description="Cloud Storage URI of the video") + bytesBase64Encoded: Optional[str] = Field( + None, description="Base64-encoded video content" + ) + 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" + ) + raiMediaFilteredReasons: Optional[List[str]] = Field( + None, description="Reasons why media was filtered by responsible AI policies" + ) + videos: Optional[List[Video2]] = None + + +class Error1(BaseModel): + code: Optional[int] = Field(None, description="Error code") + message: Optional[str] = Field(None, description="Error message") + + +class Veo2GenVidPollResponse(BaseModel): + name: Optional[str] = None + done: Optional[bool] = None + response: Optional[Response] = Field( + None, description="The actual prediction response if done is true" + ) + error: Optional[Error1] = Field( + None, description="Error details if operation failed" + ) + + +class RunwayImageToVideoResponse(BaseModel): + id: Optional[str] = Field(None, description="Task ID") + + +class RunwayTaskStatusEnum(str, Enum): + SUCCEEDED = "SUCCEEDED" + RUNNING = "RUNNING" + FAILED = "FAILED" + PENDING = "PENDING" + CANCELLED = "CANCELLED" + THROTTLED = "THROTTLED" + + +class RunwayModelEnum(str, Enum): + gen4_turbo = "gen4_turbo" + gen3a_turbo = "gen3a_turbo" + + +class Position(str, Enum): + first = "first" + last = "last" + + +class RunwayPromptImageDetailedObject(BaseModel): + uri: AnyUrl = Field( + ..., description="A HTTPS URL or data URI containing an encoded image." + ) + position: Position = Field( + ..., + description="The position of the image in the output video. 'last' is currently supported for gen3a_turbo only.", + ) + + +class RunwayDurationEnum(int, Enum): + integer_5 = 5 + integer_10 = 10 + + +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 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 Datum2(BaseModel): + b64_json: Optional[str] = Field(None, description="Base64 encoded image data") + url: Optional[str] = Field(None, description="URL of the image") + revised_prompt: Optional[str] = Field(None, description="Revised prompt") + + +class InputTokensDetails(BaseModel): + text_tokens: Optional[int] = None + image_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[Datum2]] = None + usage: Optional[Usage] = None + + +class Quality3(str, Enum): + low = "low" + medium = "medium" + high = "high" + standard = "standard" + hd = "hd" + + +class OutputFormat(str, Enum): + png = "png" + webp = "webp" + jpeg = "jpeg" + + +class Moderation(str, Enum): + low = "low" + auto = "auto" + + +class Background(str, Enum): + transparent = "transparent" + opaque = "opaque" + + +class ResponseFormat(str, Enum): + url = "url" + b64_json = "b64_json" + + +class Style3(str, Enum): + vivid = "vivid" + natural = "natural" + + +class OpenAIImageGenerationRequest(BaseModel): + model: Optional[str] = Field( + None, description="The model to use for image generation", examples=["dall-e-3"] + ) + prompt: str = Field( + ..., + description="A text description of the desired image", + examples=["Draw a rocket in front of a blackhole in deep space"], + ) + n: Optional[int] = Field( + None, + description="The number of images to generate (1-10). Only 1 supported for dall-e-3.", + examples=[1], + ) + quality: Optional[Quality3] = Field( + None, description="The quality of the generated image", examples=["high"] + ) + size: Optional[str] = Field( + None, + description="Size of the image (e.g., 1024x1024, 1536x1024, auto)", + examples=["1024x1536"], + ) + output_format: Optional[OutputFormat] = Field( + None, description="Format of the output image", examples=["png"] + ) + output_compression: Optional[int] = Field( + None, description="Compression level for JPEG or WebP (0-100)", examples=[100] + ) + moderation: Optional[Moderation] = Field( + None, description="Content moderation setting", examples=["auto"] + ) + background: Optional[Background] = Field( + None, description="Background transparency", examples=["opaque"] + ) + response_format: Optional[ResponseFormat] = Field( + None, description="Response format of image data", examples=["b64_json"] + ) + style: Optional[Style3] = Field( + None, description="Style of the image (only for dall-e-3)", examples=["vivid"] + ) + user: Optional[str] = Field( + None, + description="A unique identifier for end-user monitoring", + examples=["user-1234"], + ) + + +class OpenAIImageEditRequest(BaseModel): + model: str = Field( + ..., description="The model to use for image editing", examples=["gpt-image-1"] + ) + prompt: str = Field( + ..., + description="A text description of the desired edit", + examples=["Give the rocketship rainbow coloring"], + ) + n: Optional[int] = Field( + None, description="The number of images to generate", examples=[1] + ) + quality: Optional[str] = Field( + None, description="The quality of the edited image", examples=["low"] + ) + size: Optional[str] = Field( + None, description="Size of the output image", examples=["1024x1024"] + ) + output_format: Optional[OutputFormat] = Field( + None, description="Format of the output image", examples=["png"] + ) + output_compression: Optional[int] = Field( + None, description="Compression level for JPEG or WebP (0-100)", examples=[100] + ) + moderation: Optional[Moderation] = Field( + None, description="Content moderation setting", examples=["auto"] + ) + background: Optional[str] = Field( + None, description="Background transparency", examples=["opaque"] + ) + user: Optional[str] = Field( + None, + description="A unique identifier for end-user monitoring", + examples=["user-1234"], + ) + + +class CustomerStorageResourceResponse(BaseModel): + download_url: Optional[str] = Field( + None, + description="The signed URL to use for downloading the file from the specified path", + ) + upload_url: Optional[str] = Field( + None, + description="The signed URL to use for uploading the file to the specified path", + ) + expires_at: Optional[datetime] = Field( + None, description="When the signed URL will expire" + ) + existing_file: Optional[bool] = Field( + None, description="Whether an existing file with the same hash was found" + ) + + +class PikaBodyGenerate22T2vGenerate22T2vPost(BaseModel): + promptText: str = Field(..., title="Prompttext") + negativePrompt: Optional[str] = Field(None, title="Negativeprompt") + seed: Optional[int] = Field(None, title="Seed") + resolution: Optional[str] = Field("1080p", title="Resolution") + duration: Optional[int] = Field(5, title="Duration") + aspectRatio: Optional[float] = Field( + 1.7777777777777777, + description="Aspect ratio (width / height)", + ge=0.4, + le=2.5, + title="Aspectratio", + ) + + +class PikaGenerateResponse(BaseModel): + video_id: str = Field(..., title="Video Id") + + +class PikaBodyGenerate22I2vGenerate22I2vPost(BaseModel): + image: Optional[str] = Field(None, title="Image") + promptText: Optional[str] = Field(None, title="Prompttext") + negativePrompt: Optional[str] = Field(None, title="Negativeprompt") + seed: Optional[int] = Field(None, title="Seed") + resolution: Optional[str] = Field("1080p", title="Resolution") + duration: Optional[int] = Field(5, title="Duration") + + +class IngredientsMode(str, Enum): + creative = "creative" + precise = "precise" + + +class AspectRatio3(RootModel[float]): + root: float = Field( + ..., + description="Aspect ratio (width / height)", + ge=0.4, + le=2.5, + title="Aspectratio", + ) + + +class PikaBodyGenerate22C2vGenerate22PikascenesPost(BaseModel): + images: Optional[List[bytes_aliased]] = Field( + None, description="Array of images to process", title="Images" + ) + ingredientsMode: IngredientsMode = Field(..., title="Ingredientsmode") + promptText: Optional[str] = Field(None, title="Prompttext") + negativePrompt: Optional[str] = Field(None, title="Negativeprompt") + seed: Optional[int] = Field(None, title="Seed") + resolution: Optional[str] = Field("1080p", title="Resolution") + duration: Optional[int] = Field(5, title="Duration") + aspectRatio: Optional[AspectRatio3] = Field( + None, description="Aspect ratio (width / height)", title="Aspectratio" + ) + + +class PikaBodyGenerate22KeyframeGenerate22PikaframesPost(BaseModel): + keyFrames: List[bytes_aliased] = Field( + ..., description="Array of keyframe images", title="Keyframes" + ) + promptText: str = Field(..., title="Prompttext") + negativePrompt: Optional[str] = Field(None, title="Negativeprompt") + seed: Optional[int] = Field(None, title="Seed") + resolution: Optional[str] = Field("1080p", title="Resolution") + duration: Optional[int] = Field(5, title="Duration") + + +class PikaStatusEnum(str, Enum): + queued = "queued" + started = "started" + finished = "finished" + + +class PikaValidationError(BaseModel): + loc: List[Union[str, int]] = Field(..., title="Location") + msg: str = Field(..., title="Message") + type: str = Field(..., title="Error Type") + + +class RgbItem(RootModel[int]): + root: int = Field(..., ge=0, le=255) + + +class RGBColor(BaseModel): + rgb: List[RgbItem] = Field(..., max_length=3, min_length=3) + + +class StabilityStabilityClientID(RootModel[str]): + root: str = Field( + ..., + description="The name of your application, used to help us communicate app-specific debugging or moderation issues to you.", + examples=["my-awesome-app"], + max_length=256, + ) + + +class StabilityStabilityClientUserID(RootModel[str]): + root: str = Field( + ..., + description="A unique identifier for your end user. Used to help us communicate user-specific debugging or moderation issues to you. Feel free to obfuscate this value to protect user privacy.", + examples=["DiscordUser#9999"], + max_length=256, + ) + + +class StabilityStabilityClientVersion(RootModel[str]): + root: str = Field( + ..., + description="The version of your application, used to help us communicate version-specific debugging or moderation issues to you.", + examples=["1.2.1"], + max_length=256, + ) + + +class Name(str, Enum): + content_moderation = "content_moderation" + + +class StabilityContentModerationResponse(BaseModel): + id: str = Field( + ..., + description="A unique identifier associated with this error. Please include this in any [support tickets](https://kb.stability.ai/knowledge-base/kb-tickets/new) you file, as it will greatly assist us in diagnosing the root cause of the problem.", + examples=["a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4"], + min_length=1, + ) + name: Name = Field( + ..., + description="Our content moderation system has flagged some part of your request and subsequently denied it. You were not charged for this request. While this may at times be frustrating, it is necessary to maintain the integrity of our platform and ensure a safe experience for all users. If you would like to provide feedback, please use the [Support Form](https://kb.stability.ai/knowledge-base/kb-tickets/new).", + ) + errors: List[str] = Field( + ..., + description="One or more error messages indicating what went wrong.", + examples=[["some-field: is required"]], + min_length=1, + ) + + +class RenderingSpeed(str, Enum): + BALANCED = "BALANCED" + TURBO = "TURBO" + QUALITY = "QUALITY" class ActionJobResult(BaseModel): - action_job_id: Optional[str] = Field( - None, description='Identifier of the job this result belongs to' - ) + id: Optional[UUID] = Field(None, description="Unique identifier for the job result") + workflow_name: Optional[str] = Field(None, description="Name of the workflow") + operating_system: Optional[str] = Field(None, description="Operating system used") + python_version: Optional[str] = Field(None, description="PyTorch version used") + pytorch_version: Optional[str] = Field(None, description="PyTorch version used") action_run_id: Optional[str] = Field( - None, description='Identifier of the run this result belongs to' + 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' + action_job_id: Optional[str] = Field( + None, description="Identifier of the job this result belongs to" ) + cuda_version: Optional[str] = Field(None, description="CUDA version used") branch_name: Optional[str] = Field( - None, description='Name of the relevant git branch' + 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_hash: Optional[str] = Field(None, description="The hash of the commit") + commit_id: Optional[str] = Field(None, description="The ID of the commit") commit_time: Optional[int] = Field( - None, description='The Unix timestamp when the commit was made' + 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.' + commit_message: Optional[str] = Field(None, description="The message of the commit") + comfy_run_flags: Optional[str] = Field( + None, description="The comfy run flags. E.g. `--low-vram`" ) - 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') + git_repo: Optional[str] = Field(None, description="The repository name") + pr_number: Optional[str] = Field(None, description="The pull request number") start_time: Optional[int] = Field( - None, description='The start time of the job as a Unix timestamp.' + None, description="The start time of the job as a Unix timestamp." ) + end_time: Optional[int] = Field( + None, description="The end time of the job as a Unix timestamp." + ) + avg_vram: Optional[int] = Field( + None, description="The average VRAM used by the job" + ) + peak_vram: Optional[int] = Field(None, description="The peak VRAM used by the job") + job_trigger_user: Optional[str] = Field( + None, description="The user who triggered the job." + ) + author: Optional[str] = Field(None, description="The author of the commit") + machine_stats: Optional[MachineStats] = None status: Optional[WorkflowRunStatus] = None storage_file: Optional[StorageFile] = None - workflow_name: Optional[str] = Field(None, description='Name of the workflow') -class IdeogramV3EditRequest(BaseModel): - color_palette: Optional[IdeogramColorPalette] = None - image: Optional[bytes_aliased] = Field( +class Publisher(BaseModel): + name: Optional[str] = None + id: Optional[str] = Field( None, - description='The image being edited (max size 10MB); only JPEG, WebP and PNG formats are supported at this time.', + description="The unique identifier for the publisher. It's akin to a username. Should be lowercase.", ) - magic_prompt: Optional[str] = Field( + description: Optional[str] = None + website: Optional[str] = None + support: Optional[str] = None + source_code_repo: Optional[str] = None + logo: Optional[str] = Field(None, description="URL to the publisher's logo.") + createdAt: Optional[datetime] = Field( + None, description="The date and time the publisher was created." + ) + members: Optional[List[PublisherMember]] = Field( + None, description="A list of members in the publisher." + ) + status: Optional[PublisherStatus] = Field( + None, description="The status of the publisher." + ) + + +class NodeVersion(BaseModel): + id: Optional[str] = None + version: Optional[str] = Field( None, - description='Determine if MagicPrompt should be used in generating the request or not.', + description="The version identifier, following semantic versioning. Must be unique for the node.", ) - mask: Optional[bytes_aliased] = Field( - None, - description='A black and white image of the same size as the image being edited (max size 10MB). Black regions in the mask should match up with the regions of the image that you would like to edit; only JPEG, WebP and PNG formats are supported at this time.', + createdAt: Optional[datetime] = Field( + None, description="The date and time the version was created." ) - num_images: Optional[int] = Field( - None, description='The number of images to generate.' + changelog: Optional[str] = Field( + None, description="Summary of changes made in this version" ) - prompt: str = Field( - ..., description='The prompt used to describe the edited result.' + dependencies: Optional[List[str]] = Field( + None, description="A list of pip dependencies required by the node." ) - rendering_speed: RenderingSpeed - seed: Optional[int] = Field( - None, description='Random seed. Set for reproducible generation.' + downloadUrl: Optional[str] = Field( + None, description="[Output Only] URL to download this version of the node" ) - style_codes: Optional[List[constr(pattern=r'^[0-9A-Fa-f]{8}$')]] = Field( - None, - description='A list of 8 character hexadecimal codes representing the style of the image. Cannot be used in conjunction with style_reference_images or style_type.', + deprecated: Optional[bool] = Field( + None, description="Indicates if this version is deprecated." ) - style_reference_images: Optional[List[bytes_aliased]] = Field( - None, - description='A set of images to use as style references (maximum total size 10MB across all style references). The images should be in JPEG, PNG or WebP format.', + status: Optional[NodeVersionStatus] = Field( + None, description="The status of the node version." + ) + status_reason: Optional[str] = Field( + None, description="The reason for the status change." + ) + node_id: Optional[str] = Field( + None, description="The unique identifier of the node." + ) + comfy_node_extract_status: Optional[str] = Field( + None, description="The status of comfy node extraction process." ) class IdeogramV3Request(BaseModel): - aspect_ratio: Optional[str] = Field( - None, description='Aspect ratio in format WxH', examples=['1x3'] + prompt: str = Field(..., description="The text prompt for image generation") + seed: Optional[int] = Field( + None, description="Seed value for reproducible generation" ) - color_palette: Optional[ColorPalette] = None + resolution: Optional[str] = Field( + None, description="Image resolution in format WxH", examples=["1280x800"] + ) + aspect_ratio: Optional[str] = Field( + None, description="Aspect ratio in format WxH", examples=["1x3"] + ) + rendering_speed: RenderingSpeed magic_prompt: Optional[MagicPrompt] = Field( - None, description='Whether to enable magic prompt enhancement' + None, description="Whether to enable magic prompt enhancement" ) negative_prompt: Optional[str] = Field( - None, description='Text prompt specifying what to avoid in the generation' + None, description="Text prompt specifying what to avoid in the generation" ) - num_images: Optional[conint(ge=1)] = Field( - None, description='Number of images to generate' + num_images: Optional[int] = Field( + None, description="Number of images to generate", ge=1 ) - prompt: str = Field(..., description='The text prompt for image generation') - rendering_speed: RenderingSpeed - resolution: Optional[str] = Field( - None, description='Image resolution in format WxH', examples=['1280x800'] - ) - seed: Optional[int] = Field( - None, description='Seed value for reproducible generation' - ) - style_codes: Optional[List[constr(pattern=r'^[0-9A-Fa-f]{8}$')]] = Field( - None, description='Array of style codes in hexadecimal format' - ) - style_reference_images: Optional[List[str]] = Field( - None, description='Array of reference image URLs or identifiers' + color_palette: Optional[ColorPalette] = None + style_codes: Optional[List[StyleCode]] = Field( + None, description="Array of style codes in hexadecimal format" ) style_type: Optional[StyleType] = Field( - None, description='The type of style to apply' + None, description="The type of style to apply" ) + style_reference_images: Optional[List[str]] = Field( + None, description="Array of reference image URLs or identifiers" + ) + + +class IdeogramV3EditRequest(BaseModel): + image: Optional[bytes_aliased] = Field( + None, + description="The image being edited (max size 10MB); only JPEG, WebP and PNG formats are supported at this time.", + ) + mask: Optional[bytes_aliased] = Field( + None, + description="A black and white image of the same size as the image being edited (max size 10MB). Black regions in the mask should match up with the regions of the image that you would like to edit; only JPEG, WebP and PNG formats are supported at this time.", + ) + prompt: str = Field( + ..., description="The prompt used to describe the edited result." + ) + magic_prompt: Optional[str] = Field( + None, + description="Determine if MagicPrompt should be used in generating the request or not.", + ) + num_images: Optional[int] = Field( + None, description="The number of images to generate." + ) + seed: Optional[int] = Field( + None, description="Random seed. Set for reproducible generation." + ) + rendering_speed: RenderingSpeed + color_palette: Optional[IdeogramColorPalette] = Field( + None, + description="A color palette for generation, must EITHER be specified via one of the presets (name) or explicitly via hexadecimal representations of the color with optional weights (members). Not supported by V_1, V_1_TURBO, V_2A and V_2A_TURBO models.", + ) + style_codes: Optional[List[StyleCode]] = Field( + None, + description="A list of 8 character hexadecimal codes representing the style of the image. Cannot be used in conjunction with style_reference_images or style_type.", + ) + style_reference_images: Optional[List[bytes_aliased]] = Field( + None, + description="A set of images to use as style references (maximum total size 10MB across all style references). The images should be in JPEG, PNG or WebP format.", + ) + + +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 StripePaymentMethodDetails(BaseModel): + card: Optional[StripeCardDetails] = None + type: Optional[str] = None + + +class Controls(BaseModel): + artistic_level: Optional[int] = Field( + None, + description="Defines artistic tone of your image. At a simple level, the person looks straight at the camera in a static and clean style. Dynamic and eccentric levels introduce movement and creativity.", + ge=0, + le=5, + ) + colors: Optional[List[RGBColor]] = Field( + None, description="An array of preferable colors" + ) + background_color: Optional[RGBColor] = Field( + None, description="Use given color as a desired background color" + ) + no_text: Optional[bool] = Field(None, description="Do not embed text layouts") + + +class RecraftImageGenerationRequest(BaseModel): + prompt: str = Field( + ..., description="The text prompt describing the image to generate" + ) + model: str = Field( + ..., description='The model to use for generation (e.g., "recraftv3")' + ) + style: Optional[str] = Field( + None, + description='The style to apply to the generated image (e.g., "digital_illustration")', + ) + style_id: Optional[str] = Field( + None, + description='The style ID to apply to the generated image (e.g., "123e4567-e89b-12d3-a456-426614174000"). If style_id is provided, style should not be provided.', + ) + size: str = Field( + ..., description='The size of the generated image (e.g., "1024x1024")' + ) + controls: Optional[Controls] = Field( + None, description="The controls for the generated image" + ) + n: int = Field(..., description="The number of images to generate", ge=1, le=4) + + +class LumaKeyframes(BaseModel): + frame0: Optional[LumaKeyframe] = None + frame1: Optional[LumaKeyframe] = None class LumaGenerationRequest(BaseModel): + generation_type: Optional[GenerationType] = "video" + prompt: str = Field(..., description="The prompt of the generation") 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' + loop: Optional[bool] = Field(None, description="Whether to loop the 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.', + 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", ) + model: LumaVideoModel + resolution: LumaVideoModelOutputResolution + duration: LumaVideoModelOutputDuration -class PikaHTTPValidationError(BaseModel): - detail: Optional[List[PikaValidationError]] = Field(None, title='Detail') +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 PublisherMember(BaseModel): - id: Optional[str] = Field( - None, description='The unique identifier for the publisher member.' +class LumaGeneration(BaseModel): + id: Optional[UUID] = Field(None, description="The ID of the generation") + generation_type: Optional[LumaGenerationType] = None + state: Optional[LumaState] = None + failure_reason: Optional[str] = Field( + None, description="The reason for the state of the generation" ) - role: Optional[str] = Field( - None, description='The role of the user in the publisher.' + created_at: Optional[datetime] = Field( + None, description="The date and time when the generation was created" ) - user: Optional[PublisherUser] = None + assets: Optional[LumaAssets] = None + 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") class RunwayImageToVideoRequest(BaseModel): - duration: RunwayDurationEnum - model: RunwayModelEnum promptImage: RunwayPromptImageObject - promptText: Optional[constr(max_length=1000)] = Field( - None, description='Text prompt for the generation' + seed: int = Field( + ..., description="Random seed for generation", ge=0, le=4294967295 ) - ratio: RunwayAspectRatioEnum - seed: conint(ge=0, le=4294967295) = Field( - ..., description='Random seed for generation' + model: RunwayModelEnum = Field(..., description="Model to use for generation") + promptText: Optional[str] = Field( + None, description="Text prompt for the generation", max_length=1000 ) + duration: RunwayDurationEnum = Field( + ..., description="The number of seconds of duration for the output video." + ) + ratio: RunwayAspectRatioEnum = Field( + ..., + description="The resolution (aspect ratio) of the output video. Allowable values depend on the selected model. 1280:768 and 768:1280 are only supported for gen3a_turbo.", + ) + + +class RunwayTaskStatusResponse(BaseModel): + id: Optional[str] = Field(None, description="Task ID") + status: Optional[RunwayTaskStatusEnum] = Field(None, description="Task status") + createdAt: Optional[datetime] = Field(None, description="Task creation timestamp") + output: Optional[List[str]] = Field(None, description="Array of output video URLs") + + +class PikaHTTPValidationError(BaseModel): + detail: Optional[List[PikaValidationError]] = Field(None, title="Detail") + + +class PikaVideoResponse(BaseModel): + id: str = Field(..., title="Id") + status: PikaStatusEnum = Field( + ..., description="The status of the video", title="Status" + ) + url: Optional[str] = Field(None, title="Url") + progress: Optional[int] = Field(None, title="Progress") + + +class Node(BaseModel): + id: Optional[str] = Field(None, description="The unique identifier of the node.") + name: Optional[str] = Field(None, description="The display name of the node.") + category: Optional[str] = Field(None, description="The category of the node.") + description: Optional[str] = None + author: Optional[str] = None + license: Optional[str] = Field( + None, description="The path to the LICENSE file in the node's repository." + ) + icon: Optional[str] = Field(None, description="URL to the node's icon.") + repository: Optional[str] = Field(None, description="URL to the node's repository.") + tags: Optional[List[str]] = None + latest_version: Optional[NodeVersion] = Field( + None, description="The latest version of the node." + ) + rating: Optional[float] = Field(None, description="The average rating of the node.") + downloads: Optional[int] = Field( + None, description="The number of downloads of the node." + ) + publisher: Optional[Publisher] = Field( + None, description="The publisher of the node." + ) + status: Optional[NodeStatus] = Field(None, description="The status of the node.") + status_detail: Optional[str] = Field( + None, description="The status detail of the node." + ) + translations: Optional[Dict[str, Dict[str, Any]]] = None class StripeCharge(BaseModel): + id: Optional[str] = None + object: Optional[Object2] = None amount: Optional[int] = None amount_captured: Optional[int] = None amount_refunded: Optional[int] = None @@ -1841,11 +1993,9 @@ class StripeCharge(BaseModel): 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 @@ -1870,15 +2020,9 @@ class StripeCharge(BaseModel): 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): + id: Optional[str] = None + object: Optional[Object1] = None amount: Optional[int] = None amount_capturable: Optional[int] = None amount_details: Optional[StripeAmountDetails] = None @@ -1896,14 +2040,12 @@ class StripePaymentIntent(BaseModel): 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 @@ -1922,84 +2064,17 @@ class StripePaymentIntent(BaseModel): 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 Data2(BaseModel): object: Optional[StripePaymentIntent] = None class StripeEvent(BaseModel): + id: str + object: Object api_version: Optional[str] = None created: Optional[int] = None data: Data2 - 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 + type: Type2 diff --git a/comfy_api_nodes/apis/client.py b/comfy_api_nodes/apis/client.py index b376aafe6..e9c68bf5b 100644 --- a/comfy_api_nodes/apis/client.py +++ b/comfy_api_nodes/apis/client.py @@ -411,7 +411,6 @@ class SynchronousOperation(Generic[T, R]): self.verify_ssl = verify_ssl self.files = files self.content_type = content_type - def execute(self, client: Optional[ApiClient] = None) -> R: """Execute the API operation using the provided client or create one""" try: @@ -430,6 +429,10 @@ class SynchronousOperation(Generic[T, R]): if isinstance(self.request, EmptyRequest) else self.request.model_dump(exclude_none=True) ) + if request_dict: + for key, value in request_dict.items(): + if isinstance(value, Enum): + request_dict[key] = value.value if request_dict: for key, value in request_dict.items(): diff --git a/comfy_api_nodes/nodes_pika.py b/comfy_api_nodes/nodes_pika.py new file mode 100644 index 000000000..230af9669 --- /dev/null +++ b/comfy_api_nodes/nodes_pika.py @@ -0,0 +1,397 @@ +"""Pika API docs: https://pika-827374fb.mintlify.app/api-reference""" + +from typing import Optional, TypeVar +import logging +import torch +from comfy_api_nodes.apis import ( + PikaBodyGenerate22T2vGenerate22T2vPost, + PikaGenerateResponse, + PikaBodyGenerate22I2vGenerate22I2vPost, + PikaVideoResponse, + PikaBodyGenerate22C2vGenerate22PikascenesPost, + IngredientsMode, +) +from comfy_api_nodes.apis.client import ( + ApiEndpoint, + HttpMethod, + SynchronousOperation, + PollingOperation, + EmptyRequest, +) +from comfy_api_nodes.apinode_utils import ( + tensor_to_bytesio, + download_url_to_video_output, +) +from comfy_api_nodes.mapper_utils import model_field_to_node_input +from comfy.comfy_types.node_typing import IO, ComfyNodeABC, InputTypeOptions +from comfy_api.input_impl import VideoFromFile + +R = TypeVar("R") + +PIKA_API_VERSION = "2.2" +PATH_TEXT_TO_VIDEO = f"/proxy/pika/generate/{PIKA_API_VERSION}/t2v" +PATH_IMAGE_TO_VIDEO = f"/proxy/pika/generate/{PIKA_API_VERSION}/i2v" +PATH_PIKAFRAMES = f"/proxy/pika/generate/{PIKA_API_VERSION}/pikaframes" +PATH_PIKASCENES = f"/proxy/pika/generate/{PIKA_API_VERSION}/pikascenes" +PATH_VIDEO_GET = "/proxy/pika/videos" + + +class PikaApiError(Exception): + """Exception for Pika API errors.""" + + pass + + +def is_valid_video_response(response: PikaVideoResponse) -> bool: + """Check if the video response is valid.""" + return hasattr(response, "url") and response.url is not None + + +def is_valid_initial_response(response: PikaGenerateResponse) -> bool: + """Check if the initial response is valid.""" + return hasattr(response, "video_id") and response.video_id is not None + + +class PikaNodeBase(ComfyNodeABC): + """Base class for Pika nodes.""" + + @classmethod + def get_base_inputs_types( + cls, request_model + ) -> dict[str, tuple[IO, InputTypeOptions]]: + """Get the base required inputs types common to all Pika nodes.""" + return { + "prompt_text": model_field_to_node_input( + IO.STRING, + request_model, + "promptText", + multiline=True, + ), + "negative_prompt": model_field_to_node_input( + IO.STRING, + request_model, + "negativePrompt", + multiline=True, + ), + "seed": model_field_to_node_input( + IO.INT, + request_model, + "seed", + min=0, + max=0xFFFFFFFF, + control_after_generate=True, + ), + "resolution": model_field_to_node_input( + IO.STRING, + request_model, + "resolution", + ), + "duration": model_field_to_node_input( + IO.INT, + request_model, + "duration", + ), + } + + CATEGORY = "api node/video/Pika" + API_NODE = True + FUNCTION = "api_call" + + def poll_for_task_status( + self, task_id: str, auth_token: str + ) -> PikaGenerateResponse: + """Polls the Pika API endpoint until the task reaches a terminal state.""" + polling_operation = PollingOperation( + poll_endpoint=ApiEndpoint( + path=f"{PATH_VIDEO_GET}/{task_id}", + method=HttpMethod.GET, + request_model=EmptyRequest, + response_model=PikaVideoResponse, + ), + completed_statuses=[ + "finished", + ], + failed_statuses=["failed", "cancelled"], + status_extractor=lambda response: ( + response.status.value if response.status else None + ), + progress_extractor=lambda response: ( + response.progress if hasattr(response, "progress") else None + ), + auth_token=auth_token, + ) + return polling_operation.execute() + + def execute_task( + self, + initial_operation: SynchronousOperation[R, PikaGenerateResponse], + auth_token: Optional[str] = None, + ) -> tuple[VideoFromFile]: + """Executes the initial operation then polls for the task status until it is completed. + + Args: + initial_operation: The initial operation to execute. + auth_token: The authentication token to use for the API call. + + Returns: + A tuple containing the video file as a VIDEO output. + """ + initial_response = initial_operation.execute() + if not is_valid_initial_response(initial_response): + error_msg = f"Pika initial request failed. Code: {initial_response.code}, Message: {initial_response.message}, Data: {initial_response.data}" + logging.error(error_msg) + raise PikaApiError(error_msg) + + task_id = initial_response.video_id + final_response = self.poll_for_task_status(task_id, auth_token) + if not is_valid_video_response(final_response): + error_msg = ( + f"Pika task {task_id} succeeded but no video data found in response." + ) + logging.error(error_msg) + raise PikaApiError(error_msg) + + video_url = str(final_response.url) + logging.debug("Pika task %s succeeded. Video URL: %s", task_id, video_url) + + return download_url_to_video_output(video_url) + + +class PikaImageToVideoV2_2(PikaNodeBase): + """Pika 2.2 Image to Video Node.""" + + @classmethod + def INPUT_TYPES(cls): + return { + "required": { + "image": ( + IO.IMAGE, + {"tooltip": "The image to convert to video"}, + ), + **cls.get_base_inputs_types(PikaBodyGenerate22I2vGenerate22I2vPost), + }, + "hidden": { + "auth_token": "AUTH_TOKEN_COMFY_ORG", + }, + } + + DESCRIPTION = "Sends an image and prompt to the Pika API v2.2 to generate a video." + RETURN_TYPES = ("VIDEO",) + + def api_call( + self, + image: torch.Tensor, + prompt_text: str, + negative_prompt: str, + seed: int, + resolution: str, + duration: int, + auth_token: Optional[str] = None, + ) -> tuple[VideoFromFile]: + """API call for Pika 2.2 Image to Video.""" + # Convert image to BytesIO + image_bytes_io = tensor_to_bytesio(image) + image_bytes_io.seek(0) # Reset stream position + + # Prepare file data for multipart upload + pika_files = {"image": ("image.png", image_bytes_io, "image/png")} + + # Prepare non-file data using the Pydantic model + pika_request_data = PikaBodyGenerate22I2vGenerate22I2vPost( + promptText=prompt_text, + negativePrompt=negative_prompt, + seed=seed, + resolution=resolution, + duration=duration, + ) + + initial_operation = SynchronousOperation( + endpoint=ApiEndpoint( + path=PATH_IMAGE_TO_VIDEO, + method=HttpMethod.POST, + request_model=PikaBodyGenerate22I2vGenerate22I2vPost, + response_model=PikaGenerateResponse, + ), + request=pika_request_data, + files=pika_files, + content_type="multipart/form-data", + auth_token=auth_token, + ) + + return self.execute_task(initial_operation, auth_token) + + +class PikaTextToVideoNodeV2_2(PikaNodeBase): + """Pika 2.2 Text to Video Node.""" + + @classmethod + def INPUT_TYPES(cls): + return { + "required": { + **cls.get_base_inputs_types(PikaBodyGenerate22T2vGenerate22T2vPost), + "aspect_ratio": model_field_to_node_input( + IO.FLOAT, + PikaBodyGenerate22T2vGenerate22T2vPost, + "aspectRatio", + step=0.001, + ), + }, + "hidden": { + "auth_token": "AUTH_TOKEN_COMFY_ORG", + }, + } + + RETURN_TYPES = ("VIDEO",) + DESCRIPTION = "Sends a text prompt to the Pika API v2.2 to generate a video." + + def api_call( + self, + prompt_text: str, + negative_prompt: str, + seed: int, + resolution: str, + duration: int, + aspect_ratio: float, + auth_token: Optional[str] = None, + ) -> tuple[VideoFromFile]: + """API call for Pika 2.2 Text to Video.""" + initial_operation = SynchronousOperation( + endpoint=ApiEndpoint( + path=PATH_TEXT_TO_VIDEO, + method=HttpMethod.POST, + request_model=PikaBodyGenerate22T2vGenerate22T2vPost, + response_model=PikaGenerateResponse, + ), + request=PikaBodyGenerate22T2vGenerate22T2vPost( + promptText=prompt_text, + negativePrompt=negative_prompt, + seed=seed, + resolution=resolution, + duration=duration, + aspectRatio=aspect_ratio, + ), + auth_token=auth_token, + content_type="application/x-www-form-urlencoded", + ) + + return self.execute_task(initial_operation, auth_token) + + +class PikaScenesV2_2(PikaNodeBase): + """Pika 2.2 Scenes Node.""" + + @classmethod + def INPUT_TYPES(cls): + image_ingredient_input = ( + IO.IMAGE, + {"tooltip": "Image that will be used as ingredient to create a video."}, + ) + return { + "required": { + **cls.get_base_inputs_types( + PikaBodyGenerate22C2vGenerate22PikascenesPost, + ), + "ingredients_mode": model_field_to_node_input( + IO.COMBO, + PikaBodyGenerate22C2vGenerate22PikascenesPost, + "ingredientsMode", + enum_type=IngredientsMode, + default="creative", + ), + "aspect_ratio": model_field_to_node_input( + IO.FLOAT, + PikaBodyGenerate22C2vGenerate22PikascenesPost, + "aspectRatio", + step=0.001, + default=1.7777777777777777, + ), + }, + "optional": { + "image_ingredient_1": image_ingredient_input, + "image_ingredient_2": image_ingredient_input, + "image_ingredient_3": image_ingredient_input, + "image_ingredient_4": image_ingredient_input, + "image_ingredient_5": image_ingredient_input, + }, + "hidden": { + "auth_token": "AUTH_TOKEN_COMFY_ORG", + }, + } + + DESCRIPTION = "Combine your images to create a video with the objects in them. Upload multiple images as ingredients and generate a high-quality video that incorporates all of them." + RETURN_TYPES = ("VIDEO",) + + def api_call( + self, + prompt_text: str, + negative_prompt: str, + seed: int, + resolution: str, + duration: int, + ingredients_mode: str, + aspect_ratio: float, + image_ingredient_1: Optional[torch.Tensor] = None, + image_ingredient_2: Optional[torch.Tensor] = None, + image_ingredient_3: Optional[torch.Tensor] = None, + image_ingredient_4: Optional[torch.Tensor] = None, + image_ingredient_5: Optional[torch.Tensor] = None, + auth_token: Optional[str] = None, + ) -> tuple[VideoFromFile]: + """API call for Pika Scenes 2.2.""" + all_image_bytes_io = [] + for image in [ + image_ingredient_1, + image_ingredient_2, + image_ingredient_3, + image_ingredient_4, + image_ingredient_5, + ]: + if image is not None: + image_bytes_io = tensor_to_bytesio(image) + image_bytes_io.seek(0) + all_image_bytes_io.append(image_bytes_io) + + # Prepare files data for multipart upload + pika_files = [ + ("images", (f"image_{i}.png", image_bytes_io, "image/png")) + for i, image_bytes_io in enumerate(all_image_bytes_io) + ] + + # Prepare non-file data using the Pydantic model + pika_request_data = PikaBodyGenerate22C2vGenerate22PikascenesPost( + ingredientsMode=ingredients_mode, + promptText=prompt_text, + negativePrompt=negative_prompt, + seed=seed, + resolution=resolution, + duration=duration, + aspectRatio=aspect_ratio, + ) + + initial_operation = SynchronousOperation( + endpoint=ApiEndpoint( + path=PATH_PIKASCENES, + method=HttpMethod.POST, + request_model=PikaBodyGenerate22C2vGenerate22PikascenesPost, + response_model=PikaGenerateResponse, + ), + request=pika_request_data, + files=pika_files, + content_type="multipart/form-data", + auth_token=auth_token, + ) + + return self.execute_task(initial_operation, auth_token) + + +NODE_CLASS_MAPPINGS = { + "PikaImageToVideoNode2_2": PikaImageToVideoV2_2, + "PikaTextToVideoNode2_2": PikaTextToVideoNodeV2_2, + "PikaScenesV2_2": PikaScenesV2_2, +} + +NODE_DISPLAY_NAME_MAPPINGS = { + "PikaImageToVideoNode2_2": "Pika 2.2 Image to Video", + "PikaTextToVideoNode2_2": "Pika 2.2 Text to Video", + "PikaScenesV2_2": "Pika 2.2 Scenes", +} diff --git a/nodes.py b/nodes.py index 0534edc8c..fe148c68f 100644 --- a/nodes.py +++ b/nodes.py @@ -2272,6 +2272,7 @@ def init_builtin_extra_nodes(): "nodes_luma.py", "nodes_recraft.py", "nodes_pixverse.py", + "nodes_pika.py", ] import_failed = []