stable-diffusion-v1-5-img2img
Beta
Terminal window
Model ID: @cf/runwayml/stable-diffusion-v1-5-img2img
Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images. Img2img generate a new image from an input image with Stable Diffusion.
Properties
Task Type: Text-to-Image
Code Examples
Workers - Typescript
export interface Env { AI: Ai;}
export default { async fetch(request, env): Promise<Response> {
// Picture of a dog const exampleInputImage = await fetch( "https://pub-1fb693cb11cc46b2b2f656f51e015a2c.r2.dev/dog.png" );
const inputs = { prompt: "Change to a lion", image: [...new Uint8Array(await exampleInputImage.arrayBuffer())], };
const response = await env.AI.run( "@cf/runwayml/stable-diffusion-v1-5-img2img", inputs );
return new Response(response, { headers: { "content-type": "image/png", }, }); },} satisfies ExportedHandler<Env>;
curl
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run/@cf/runwayml/stable-diffusion-v1-5-img2img \ -X POST \ -H "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \ -d '{ "prompt": "cyberpunk cat" }'
Response
The response is a binary PNG file.
API Schema
The following schema is based on JSON Schema
Input JSON Schema
{ "type": "object", "properties": { "prompt": { "type": "string", "minLength": 1 }, "negative_prompt": { "type": "string" }, "height": { "type": "integer", "maximum": 1024 }, "width": { "type": "integer", "maximum": 1024 }, "image": { "type": "array", "items": { "type": "number" } }, "image_b64": { "type": "string" }, "mask": { "type": "array", "items": { "type": "number" } }, "num_steps": { "type": "integer", "default": 20, "maximum": 20 }, "strength": { "type": "number", "default": 1 }, "guidance": { "type": "number", "default": 7.5 }, "seed": { "type": "integer" } }, "required": [ "prompt" ]}
Output JSON Schema
{ "type": "string", "contentType": "image/png", "format": "binary"}