Blog
Replicate
STABLE

Stable Diffusion 3

A text-to-image model with greatly improved performance in image quality, typography, complex prompt understanding, and resource-efficiency

Usage

Specify a detailed text prompt

Inputs
aspect_ratio
Cfg
The guidance scale tells the model how similar the output should be to the prompt.
Negative Prompt
Things you do not want to see in your image
output_format
Format of the output images
Output Quality
Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.
Prompt
Seed
Set a seed for reproducibility. Random by default.
Outputs
Urls
URLs of the images