Image
Generate images from text.
Create image
Given a text prompt, generate 1 or more images according to the prompt.
Required attributes
- Name
prompt
- Type
- string
- Description
A description of the images to be generated.
- Name
model
- Type
- string
- Description
The model used for image generations. (WARNING: At the moment only "stable-diffusion-2-1" is allowed)
If the model name is "default", the chat model from the configuration is used (see Documentation » Configuration for details).
If the model name is a valid model name recognized by Edgen, it is what is used.
Optional attributes
- Name
width
- Type
- integer
- Description
The width of the generated image.
- Name
height
- Type
- integer
- Description
The height of the generated image.
- Name
uncond_prompt
- Type
- string
- Description
The optional unconditional prompt.
- Name
steps
- Type
- integer
- Description
The number of steps to be used in the diffusion process.
- Name
images
- Type
- integer
- Description
The number of images to generate. Default: 1
- Name
seed
- Type
- integer
- Description
The random number generator seed to use for the generation. By default, a random seed is used.
- Name
guidance_scale
- Type
- float
- Description
The guidance scale to use for generation, that is, how much should the model follow the prompt. Values below 1 disable guidance. (the prompt is ignored)
- Name
vae_scale
- Type
- float
- Description
The Variational Auto-Encoder scale to use for generation. Required if
model
is not a pre-made descriptor name. This value should probably not be set, ifmodel
is a pre-made descriptor name.
- Default
Request
curl http://localhost:33322/v1/image/generations \
-H "Content-Type: application/json" \
-H "Authorization: Bearer no-key-required" \
-d '{
"model": "stable-diffusion-2-1",
"prompt": "A rusty robot"
}'
Response
{"images": [[123, 234, ..., 231, 213]]}