Hugging Face Multimodal API

openapi: 3.2.0
info:
  title: Hugging Face Inference Multimodal API
  description: Run inference on 200,000+ machine learning models hosted on the Hugging Face Hub with a simple HTTP request. Supports text generation, image classification, object detection, speech recognition, and many more tasks.
  version: 1.0.0
  termsOfService: https://huggingface.co/terms-of-service
  contact:
    name: Hugging Face Support
    url: https://huggingface.co/support
  license:
    name: Apache 2.0
    url: https://www.apache.org/licenses/LICENSE-2.0
servers:
- url: https://api-inference.huggingface.co
  description: Hugging Face Inference API production server
security:
- bearerAuth: []
tags:
- name: Multimodal
  description: Tasks involving multiple modalities
paths:
  /models/{model_id}/text-to-image:
    post:
      summary: Text to Image Generation
      description: Generate an image from a text prompt using a diffusion model.
      operationId: textToImage
      tags:
      - Multimodal
      parameters:
      - name: model_id
        in: path
        required: true
        schema:
          type: string
        example: stabilityai/stable-diffusion-xl-base-1.0
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/TextToImageRequest'
            examples:
              TexttoimageRequestExample:
                summary: Default textToImage request
                x-microcks-default: true
                value:
                  inputs: example_value
                  parameters:
                    negative_prompt: example_value
                    height: 10
                    width: 10
                    num_inference_steps: 10
                    guidance_scale: 42.5
      responses:
        '200':
          description: Generated image
          content:
            image/png:
              schema:
                type: string
                format: binary
              examples:
                Texttoimage200Example:
                  summary: Default textToImage 200 response
                  x-microcks-default: true
                  value: example_value
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
components:
  schemas:
    TextToImageRequest:
      type: object
      required:
      - inputs
      properties:
        inputs:
          type: string
          description: The text prompt to generate an image from
          example: A beautiful sunset over mountains
        parameters:
          type: object
          properties:
            negative_prompt:
              type: string
              description: Text describing what to avoid in the image
            height:
              type: integer
              description: Height of the generated image in pixels
            width:
              type: integer
              description: Width of the generated image in pixels
            num_inference_steps:
              type: integer
              description: Number of denoising steps
            guidance_scale:
              type: number
              format: float
              description: Classifier-free guidance scale
          example: example_value
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: HF Token
      description: Hugging Face API token. Generate one from https://huggingface.co/settings/tokens