Image Generation

Generate images from a text prompt using various AI models on Subnet 23.

POSTv1/23/text-to-image

Generate an image

Generate images from text descriptions using various models.

Required attributes

Name
prompt
Type
string
Description
The textual prompt used to generate the image.
Name
model_name
Type
string
Description
The name of the model to use for image generation. Options:
- AnimeV3
- DreamShaperXL
- JuggernautXL
- RealitiesEdgeXL
- StickerMaker

Optional attributes

Name
seed
Type
integer
Description
The seed value for the random number generator. Use 0 for a random seed. Default: 0.
Name
aspect_ratio
Type
string
Description
Ratio of image to generate. Options: "1:1" (default), "2:3", "3:2", "16:9", "9:16", "13:19", "19:13".
Name
negative_prompt
Type
string
Description
List of things to avoid in the generation. Default: empty string.
Name
advanced_params
Type
object
Description
Advanced parameters such as number of steps and guidance scale:
- num_inference_steps: Number of inference steps (default: 20)
- use_expansion: Use prompt expansion for more aesthetic output (default: false)

This endpoint is authenticated. Get your API key

Request

POST

v1/23/text-to-image

curl -X POST https://api.bitmind.ai/oracle/v1/23/text-to-image \
  -H "Authorization: Bearer {token}" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "a cute cat",
    "model_name": "AnimeV3",
    "seed": 0,
    "aspect_ratio": "13:19",
    "negative_prompt": "low quality",
    "advanced_params": {
      "num_inference_steps": 20,
      "use_expansion": true
    }
  }'

Response

{
  "image": "/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAgGBgcGBQgHBwcJCQgKDBQNDAsLDBkSEw8UHRofHh0aHBwgJC4n"
}

The image generation model

The image generation model contains the generated image.

Properties

Name
image
Type
string
Description
The generated image.