Stable Diffusion is a latent text-to-image diffusion model. Generate realistic images given text description

You can use cURL or any other http client to run inferences:

```bash
curl -X POST \
    -H "Authorization: bearer $(deepctl auth token)"  \
    -F 'prompt=A photo of an astronaut riding a horse on Mars.'  \
    'https://api.deepinfra.com/v1/inference/stabilityai/stable-diffusion-2-1'
```

which will give you back something similar to:

```json
{
  "images": [
    "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAIAAACQd1PeAAAADElEQVQI12PQz3wAAAJDAXkkWn+MAAAAAElFTkSuQmCC"
  ],
  "nsfw_content_detected": [
    false
  ],
  "seed": 42,
  "request_id": null,
  "inference_status": {
    "status": "unknown",
    "runtime_ms": 0,
    "cost": 0.0,
    "tokens_generated": 0,
    "tokens_input": 0
  }
}

```


You can use our command-line tool [deepctl](/docs/getting-started) to run
inferences:

```bash
deepctl infer \
    -m 'stabilityai/stable-diffusion-2-1'  \
    -i 'prompt=A photo of an astronaut riding a horse on Mars.'
```

which will give you back something similar to:

```json
{
  "images": [
    "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAIAAACQd1PeAAAADElEQVQI12PQz3wAAAJDAXkkWn+MAAAAAElFTkSuQmCC"
  ],
  "nsfw_content_detected": [
    false
  ],
  "seed": 42,
  "request_id": null,
  "inference_status": {
    "status": "unknown",
    "runtime_ms": 0,
    "cost": 0.0,
    "tokens_generated": 0,
    "tokens_input": 0
  }
}

```


prompt

negative_prompt

image

num_images

num_inference_steps

classifier-free guidance, higher means follow prompt more closely

guidance_scale

how much to follow the input image. 1 means ignore the image, 0 means follow the image exactly

strength

width

height

seed

use_compel

The webhook to call when inference is done, by default you will get the output in the response of your inference request

webhook

Guidance Scale

Height

Image

Negative Prompt

Num Images

Num Inference Steps

Prompt

Seed

Strength

Use Compel

Webhook

Width

TextToImageIn

estimated cost billed for the request in USD

Cost

Runtime Ms

Status

Tokens Generated

Tokens Input

a list of images, encoded in data-URL (png) format

Images

Object containing the status of the inference request

Inference Status

a list of booleans indicating whether NSFW content was detected in the corresponding image

stabilityai/stable-diffusion-2-1

HTTP/cURL API

Input fields

`prompt`string

`negative_prompt`string

`image`string

`num_images`integer

`num_inference_steps`integer

`guidance_scale`number

`strength`number

`width`integer

`height`integer

`seed`integer

`use_compel`boolean

`webhook`file

Input Schema

Output Schema

stabilityai/stable-diffusion-2-1

HTTP/cURL API

Input fields

promptstring

negative_promptstring

imagestring

num_imagesinteger

num_inference_stepsinteger

guidance_scalenumber

strengthnumber

widthinteger

heightinteger

seedinteger

use_compelboolean

webhookfile