Text To Image

Generate images from text prompts.

POST /text-to-image

Text To Image

cURL

curl --request POST \
  --url https://dream-gateway.livepeer.cloud/text-to-image \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "<string>",
  "model_id": "",
  "loras": "",
  "height": 576,
  "width": 1024,
  "guidance_scale": 7.5,
  "negative_prompt": "",
  "safety_check": true,
  "seed": 123,
  "num_inference_steps": 50,
  "num_images_per_prompt": 1
}
'

200

{
  "images": [
    {
      "url": "<string>",
      "seed": 123,
      "nsfw": true
    }
  ]
}

The default Gateway used in this guide is the public Livepeer.cloud Gateway. It is free to use but not intended for production-ready applications. For production-ready applications, consider using the Livepeer Studio Gateway, which requires an API token. Alternatively, you can set up your own Gateway node or partner with one via the ai-video channel on Discord.

Please note that the exact parameters, default values, and responses may vary between models. For more information on model-specific parameters, please refer to the respective model documentation available in the text pipeline. Not all parameters might be available for a given model.

Authorizations

Authorization · string · header · required

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

Body

application/json

prompt · string · required

Text prompt(s) to guide image generation. Separate multiple prompts with '|' if supported by the model.

model_id · string · default: ""

Hugging Face model ID used for image generation.

loras · string · default: ""

A LoRA (Low-Rank Adaptation) model and its corresponding weight for image generation. Example: { "latent-consistency/lcm-lora-sdxl": 1.0, "nerijs/pixel-art-xl": 1.2}.

height · integer · default: 576

The height in pixels of the generated image.

width · integer · default: 1024

The width in pixels of the generated image.

guidance_scale · number · default: 7.5

Encourages model to generate images closely linked to the text prompt (higher values may reduce image quality).

negative_prompt · string · default: ""

Text prompt(s) to guide what to exclude from image generation. Ignored if guidance_scale < 1.

safety_check · boolean · default: true

Perform a safety check to estimate if generated images could be offensive or harmful.

seed · integer

Seed for random number generation.

num_inference_steps · integer · default: 50

Number of denoising steps. More steps usually lead to higher quality images but slower inference. Modulated by strength.

num_images_per_prompt · integer · default: 1

Number of images to generate per prompt.

Response

200

application/json

Successful Response

Response model for image generation.

images · Media · object[] · required

The generated images.

Show child attributes