Create Image

Use an image model to generate an image for a given prompt.

POST /images/generations

Create image

cURL

curl --request POST \
  --url https://api.together.xyz/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "cat floating in space, cinematic",
  "model": "black-forest-labs/FLUX.1-schnell",
  "steps": 20,
  "image_url": "<string>",
  "seed": 123,
  "n": 1,
  "height": 1024,
  "width": 1024,
  "negative_prompt": "<string>",
  "guidance": 3.5,
  "output_format": "jpeg",
  "image_loras": [
    {
      "path": "<string>",
      "scale": 123
    }
  ]
}
'

200

{
  "id": "<string>",
  "model": "<string>",
  "object": "list",
  "data": [
    {
      "index": 123,
      "b64_json": "<string>",
      "url": "<string>"
    }
  ]
}

Authorizations

Authorization · string · header · default: default · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

prompt · string · required

A description of the desired images. Maximum length varies by model.

Example:

"cat floating in space, cinematic"

model · enum<string> string · required

The model to use for image generation.

See all of Together AI's image models

Available options: black-forest-labs/FLUX.1-schnell-Free, black-forest-labs/FLUX.1-schnell, black-forest-labs/FLUX.1.1-pro

Example:

"black-forest-labs/FLUX.1-schnell"

steps · integer · default: 20

Number of generation steps.

image_url · string

URL of an image to use for image models that support it.

seed · integer

Seed used for generation. Can be used to reproduce image generations.

n · integer · default: 1

Number of image results to generate.

height · integer · default: 1024

Height of the image to generate in number of pixels.

width · integer · default: 1024

Width of the image to generate in number of pixels.

negative_prompt · string

The prompt or prompts not to guide the image generation.

response_format · enum<string>

Format of the image response. Can be either a base64 string or a URL.

Available options: base64, url

guidance · number · default: 3.5

Adjusts the alignment of the generated image with the input prompt. Higher values (e.g., 8-10) make the output more faithful to the prompt, while lower values (e.g., 1-5) encourage more creative freedom.

output_format · enum<string> · default: jpeg

The format of the image response. Can be either be jpeg or png. Defaults to jpeg.

Available options: jpeg, png

image_loras · object[]

An array of objects that define LoRAs (Low-Rank Adaptations) to influence the generated image.

Show child attributes

Response

200 - application/json

Image generated successfully

id · string · required

model · string · required

object · enum<string> · required

Available options: list

Example:

"list"

data · object[] · required

Option 1

Option 2

Show child attributes