openapi: 3.1.0
info:
  title: Livepeer AI Runner
  description: An application to run AI pipelines
  version: v0.3.0
servers:
- url: https://dream-gateway.livepeer.cloud
  description: Livepeer Cloud Community Gateway
- url: https://livepeer.studio/api/beta/generate
  description: Livepeer Studio Gateway
paths:
  /text-to-image:
    post:
      tags:
      - generate
      summary: Text To Image
      description: Generate images from text prompts.
      operationId: genTextToImage
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/TextToImageParams'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ImageResponse'
                x-speakeasy-name-override: data
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPError'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPError'
        '500':
          description: Internal Server Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPError'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
      - HTTPBearer: []
      x-speakeasy-name-override: textToImage
      x-speakeasy-retries:
        strategy: backoff
        statusCodes:
        - '503'
  /image-to-image:
    post:
      tags:
      - generate
      summary: Image To Image
      description: Apply image transformations to a provided image.
      operationId: genImageToImage
      requestBody:
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/Body_genImageToImage'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ImageResponse'
                x-speakeasy-name-override: data
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPError'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPError'
        '500':
          description: Internal Server Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPError'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
      - HTTPBearer: []
      x-speakeasy-name-override: imageToImage
      x-speakeasy-retries:
        strategy: backoff
        statusCodes:
        - '503'
  /image-to-video:
    post:
      tags:
      - generate
      summary: Image To Video
      description: Generate a video from a provided image.
      operationId: genImageToVideo
      requestBody:
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/Body_genImageToVideo'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VideoResponse'
                x-speakeasy-name-override: data
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPError'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPError'
        '500':
          description: Internal Server Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPError'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
      - HTTPBearer: []
      x-speakeasy-name-override: imageToVideo
      x-speakeasy-retries:
        strategy: backoff
        statusCodes:
        - '503'
  /upscale:
    post:
      tags:
      - generate
      summary: Upscale
      description: Upscale an image by increasing its resolution.
      operationId: genUpscale
      requestBody:
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/Body_genUpscale'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ImageResponse'
                x-speakeasy-name-override: data
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPError'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPError'
        '500':
          description: Internal Server Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPError'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
      - HTTPBearer: []
      x-speakeasy-name-override: upscale
      x-speakeasy-retries:
        strategy: backoff
        statusCodes:
        - '503'
  /audio-to-text:
    post:
      tags:
      - generate
      summary: Audio To Text
      description: Transcribe audio files to text.
      operationId: genAudioToText
      requestBody:
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/Body_genAudioToText'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TextResponse'
                x-speakeasy-name-override: data
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPError'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPError'
        '413':
          description: Request Entity Too Large
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPError'
        '500':
          description: Internal Server Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPError'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
      - HTTPBearer: []
      x-speakeasy-name-override: audioToText
      x-speakeasy-retries:
        strategy: backoff
        statusCodes:
        - '503'
  /segment-anything-2:
    post:
      tags:
      - generate
      summary: Segment Anything 2
      description: Segment objects in an image.
      operationId: genSegmentAnything2
      requestBody:
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/Body_genSegmentAnything2'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/MasksResponse'
                x-speakeasy-name-override: data
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPError'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPError'
        '500':
          description: Internal Server Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPError'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
      - HTTPBearer: []
      x-speakeasy-name-override: segmentAnything2
      x-speakeasy-retries:
        strategy: backoff
        statusCodes:
        - '503'
components:
  schemas:
    APIError:
      properties:
        msg:
          type: string
          title: Msg
          description: The error message.
      type: object
      required:
      - msg
      title: APIError
      description: API error response model.
    Body_genAudioToText:
      properties:
        audio:
          type: string
          format: binary
          title: Audio
          description: Uploaded audio file to be transcribed.
        model_id:
          type: string
          title: Model Id
          description: Hugging Face model ID used for transcription.
          default: ''
      type: object
      required:
      - audio
      - model_id
      title: Body_genAudioToText
    Body_genImageToImage:
      properties:
        prompt:
          type: string
          title: Prompt
          description: Text prompt(s) to guide image generation.
        image:
          type: string
          format: binary
          title: Image
          description: Uploaded image to modify with the pipeline.
        model_id:
          type: string
          title: Model Id
          description: Hugging Face model ID used for image generation.
          default: ''
        strength:
          type: number
          title: Strength
          description: Degree of transformation applied to the reference image (0
            to 1).
          default: 0.8
        guidance_scale:
          type: number
          title: Guidance Scale
          description: Encourages model to generate images closely linked to the text
            prompt (higher values may reduce image quality).
          default: 7.5
        image_guidance_scale:
          type: number
          title: Image Guidance Scale
          description: Degree to which the generated image is pushed towards the initial
            image.
          default: 1.5
        negative_prompt:
          type: string
          title: Negative Prompt
          description: Text prompt(s) to guide what to exclude from image generation.
            Ignored if guidance_scale < 1.
          default: ''
        safety_check:
          type: boolean
          title: Safety Check
          description: Perform a safety check to estimate if generated images could
            be offensive or harmful.
          default: true
        seed:
          type: integer
          title: Seed
          description: Seed for random number generation.
        num_inference_steps:
          type: integer
          title: Num Inference Steps
          description: Number of denoising steps. More steps usually lead to higher
            quality images but slower inference. Modulated by strength.
          default: 100
        num_images_per_prompt:
          type: integer
          title: Num Images Per Prompt
          description: Number of images to generate per prompt.
          default: 1
      type: object
      required:
      - prompt
      - image
      - model_id
      title: Body_genImageToImage
    Body_genImageToVideo:
      properties:
        image:
          type: string
          format: binary
          title: Image
          description: Uploaded image to generate a video from.
        model_id:
          type: string
          title: Model Id
          description: Hugging Face model ID used for video generation.
          default: ''
        height:
          type: integer
          title: Height
          description: The height in pixels of the generated video.
          default: 576
        width:
          type: integer
          title: Width
          description: The width in pixels of the generated video.
          default: 1024
        fps:
          type: integer
          title: Fps
          description: The frames per second of the generated video.
          default: 6
        motion_bucket_id:
          type: integer
          title: Motion Bucket Id
          description: Used for conditioning the amount of motion for the generation.
            The higher the number the more motion will be in the video.
          default: 127
        noise_aug_strength:
          type: number
          title: Noise Aug Strength
          description: Amount of noise added to the conditioning image. Higher values
            reduce resemblance to the conditioning image and increase motion.
          default: 0.02
        safety_check:
          type: boolean
          title: Safety Check
          description: Perform a safety check to estimate if generated images could
            be offensive or harmful.
          default: true
        seed:
          type: integer
          title: Seed
          description: Seed for random number generation.
        num_inference_steps:
          type: integer
          title: Num Inference Steps
          description: Number of denoising steps. More steps usually lead to higher
            quality images but slower inference. Modulated by strength.
          default: 25
      type: object
      required:
      - image
      - model_id
      title: Body_genImageToVideo
    Body_genSegmentAnything2:
      properties:
        image:
          type: string
          format: binary
          title: Image
          description: Image to segment.
        model_id:
          type: string
          title: Model Id
          description: Hugging Face model ID used for image generation.
          default: ''
        point_coords:
          type: string
          title: Point Coords
          description: Nx2 array of point prompts to the model, where each point is
            in (X,Y) in pixels.
        point_labels:
          type: string
          title: Point Labels
          description: Labels for the point prompts, where 1 indicates a foreground
            point and 0 indicates a background point.
        box:
          type: string
          title: Box
          description: A length 4 array given as a box prompt to the model, in XYXY
            format.
        mask_input:
          type: string
          title: Mask Input
          description: A low-resolution mask input to the model, typically from a
            previous prediction iteration, with the form 1xHxW (H=W=256 for SAM).
        multimask_output:
          type: boolean
          title: Multimask Output
          description: If true, the model will return three masks for ambiguous input
            prompts, often producing better masks than a single prediction.
          default: true
        return_logits:
          type: boolean
          title: Return Logits
          description: If true, returns un-thresholded mask logits instead of a binary
            mask.
          default: true
        normalize_coords:
          type: boolean
          title: Normalize Coords
          description: If true, the point coordinates will be normalized to the range
            [0,1], with point_coords expected to be with respect to image dimensions.
          default: true
      type: object
      required:
      - image
      - model_id
      title: Body_genSegmentAnything2
    Body_genUpscale:
      properties:
        prompt:
          type: string
          title: Prompt
          description: Text prompt(s) to guide upscaled image generation.
        image:
          type: string
          format: binary
          title: Image
          description: Uploaded image to modify with the pipeline.
        model_id:
          type: string
          title: Model Id
          description: Hugging Face model ID used for upscaled image generation.
          default: ''
        safety_check:
          type: boolean
          title: Safety Check
          description: Perform a safety check to estimate if generated images could
            be offensive or harmful.
          default: true
        seed:
          type: integer
          title: Seed
          description: Seed for random number generation.
        num_inference_steps:
          type: integer
          title: Num Inference Steps
          description: Number of denoising steps. More steps usually lead to higher
            quality images but slower inference. Modulated by strength.
          default: 75
      type: object
      required:
      - prompt
      - image
      - model_id
      title: Body_genUpscale
    HTTPError:
      properties:
        detail:
          allOf:
          - $ref: '#/components/schemas/APIError'
          description: Detailed error information.
      type: object
      required:
      - detail
      title: HTTPError
      description: HTTP error response model.
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ImageResponse:
      properties:
        images:
          items:
            $ref: '#/components/schemas/Media'
          type: array
          title: Images
          description: The generated images.
      type: object
      required:
      - images
      title: ImageResponse
      description: Response model for image generation.
    MasksResponse:
      properties:
        masks:
          type: string
          title: Masks
          description: The generated masks.
        scores:
          type: string
          title: Scores
          description: The model's confidence scores for each generated mask.
        logits:
          type: string
          title: Logits
          description: The raw, unnormalized predictions (logits) for the masks.
      type: object
      required:
      - masks
      - scores
      - logits
      title: MasksResponse
      description: Response model for object segmentation.
    Media:
      properties:
        url:
          type: string
          title: Url
          description: The URL where the media can be accessed.
        seed:
          type: integer
          title: Seed
          description: The seed used to generate the media.
        nsfw:
          type: boolean
          title: Nsfw
          description: Whether the media was flagged as NSFW.
      type: object
      required:
      - url
      - seed
      - nsfw
      title: Media
      description: A media object containing information about the generated media.
    TextResponse:
      properties:
        text:
          type: string
          title: Text
          description: The generated text.
        chunks:
          items:
            $ref: '#/components/schemas/chunk'
          type: array
          title: Chunks
          description: The generated text chunks.
      type: object
      required:
      - text
      - chunks
      title: TextResponse
      description: Response model for text generation.
    TextToImageParams:
      properties:
        model_id:
          type: string
          title: Model Id
          description: Hugging Face model ID used for image generation.
          default: ''
        prompt:
          type: string
          title: Prompt
          description: Text prompt(s) to guide image generation. Separate multiple
            prompts with '|' if supported by the model.
        height:
          type: integer
          title: Height
          description: The height in pixels of the generated image.
          default: 576
        width:
          type: integer
          title: Width
          description: The width in pixels of the generated image.
          default: 1024
        guidance_scale:
          type: number
          title: Guidance Scale
          description: Encourages model to generate images closely linked to the text
            prompt (higher values may reduce image quality).
          default: 7.5
        negative_prompt:
          type: string
          title: Negative Prompt
          description: Text prompt(s) to guide what to exclude from image generation.
            Ignored if guidance_scale < 1.
          default: ''
        safety_check:
          type: boolean
          title: Safety Check
          description: Perform a safety check to estimate if generated images could
            be offensive or harmful.
          default: true
        seed:
          type: integer
          title: Seed
          description: Seed for random number generation.
        num_inference_steps:
          type: integer
          title: Num Inference Steps
          description: Number of denoising steps. More steps usually lead to higher
            quality images but slower inference. Modulated by strength.
          default: 50
        num_images_per_prompt:
          type: integer
          title: Num Images Per Prompt
          description: Number of images to generate per prompt.
          default: 1
      type: object
      required:
      - prompt
      - model_id
      title: TextToImageParams
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
    VideoResponse:
      properties:
        images:
          items:
            $ref: '#/components/schemas/Media'
          type: array
          title: Images
          description: The generated images.
      type: object
      required:
      - images
      title: VideoResponse
      description: Response model for image generation.
    chunk:
      properties:
        timestamp:
          items: {}
          type: array
          title: Timestamp
          description: The timestamp of the chunk.
        text:
          type: string
          title: Text
          description: The text of the chunk.
      type: object
      required:
      - timestamp
      - text
      title: chunk
      description: A chunk of text with a timestamp.
  securitySchemes:
    HTTPBearer:
      type: http
      scheme: bearer