runwayml/stable-diffusion-v1-5 cover image

runwayml/stable-diffusion-v1-5

Most widely used version of Stable Diffusion. Trained on 512x512 images, it can generate realistic images given text description

Most widely used version of Stable Diffusion. Trained on 512x512 images, it can generate realistic images given text description

Public

OpenAI-compatible HTTP API

This document provides an overview of the DeepInfra-compatible OpenAI image generation API. It allows users to generate AI-created images based on text prompts using DeepInfra models.

Image Generation

curl https://api.deepinfra.com/v1/openai/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $DEEPINFRA_TOKEN" \
  -d '{
    "prompt": "A photo of an astronaut riding a horse on Mars.",
    "size": "1024x1024",
    "model": "runwayml/stable-diffusion-v1-5",
    "n": 1
    }'

The API returns a JSON object containing the generated image(s).

Example Response

{
  "created": 1707000000,
  "data": [
    {
      "revised_prompt": "A photo of an astronaut riding a horse on Mars.",
      "b64_json": "/9j/4AAQS..."
    }
  ]
}

Input fields

modelstring

The model to use for image generation.


ninteger

The number of images to generate.

Default value: 1

Range: 1 ≤ n ≤ 4


response_formatstring

The format in which the generated images are returned. Currently only b64_json is supported.

Default value: "b64_json"

Allowed values: b64_json


sizestring

The size of the generated images. Available sizes depend on the model.

Default value: "1024x1024"


userstring

A unique identifier representing your end-user, which can help to monitor and detect abuse.


promptstring

A text description of desired image(s).


qualitystring

The quality of the image that will be generated.


stylestring

The style of the generated images.

Input Schema

Output Schema