Cloudflare Docs
Workers AI
Cloudflare Docs
Workers AI
GitHub icon
Visit Workers AI on GitHub
Set theme to dark (⇧+D)
  1. Products
  2. Workers AI
  3. Models
  4. Text-to-Image

Text-to-Image

  • Task type: text-to-image
  • TypeScript class: AiTextToImage

​​ Available Embedding Models

List of available models in for this task type:

Model IDDescription
@cf/stabilityai/stable-diffusion-xl-base-1.0Diffusion-based text-to-image generative model by Stability AI. Generates and modify images based on text prompts.
More information
Terms and license

​​ Examples


import { Ai } from '@cloudflare/ai'



export interface Env {
  AI: any;

}



export default {
  async fetch(request: Request, env: Env) {
    const ai = new Ai(env.AI);


    const inputs = {
        prompt: "cyberpunk cat",
    };


    const response = await ai.run("@cf/stabilityai/stable-diffusion-xl-base-1.0", inputs);


    return new Response(response, {
        headers: {
            "content-type": "image/png",
        },
    });


  }

}


$ curl https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/run/@cf/stabilityai/stable-diffusion-xl-base-1.0 \
  -X POST \
  -H "Authorization: Bearer {API_TOKEN}" \
  -d '{ "prompt": "cyberpunk cat" }'

Example Workers AI response

The response is a Uint8Array binary with a PNG image.

​​ API schema

The following schema is based on JSON Schema

​​ Input


{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string"
    },
    "num_steps": {
      "type": "integer",
      "default": 20,
      "maximum": 20
    }
  },
  "required": [
    "prompt"
  ]

}

TypeScript class: AiTextToImageInput

​​ Output


{
  "type": "string",
  "contentType": "image/png",
  "format": "binary"

}

TypeScript class: AiTextToImageOutput