Official

stability-ai / stable-diffusion-3.5-large

A text-to-image model that generates high-resolution images with fine details. It supports various artistic styles and produces diverse outputs from the same prompt, thanks to Query-Key Normalization.

  • Public
  • 830K runs
  • $0.065 per image
  • Commercial use
  • Weights
  • Paper
  • License
Run with an API
Playground API Examples README

Run replicate/stable-diffusion-3.5-large-internal with an API

Input schema

cfgnumber

The guidance scale tells the model how similar the output should be to the prompt.

Default
4.5
Maximum
20
seedinteger

Set a seed for reproducibility. Random by default.

imageuri

Input image for image to image mode. The aspect ratio of your output will match this image.

stepsinteger

Number of steps to run the sampler for.

Default
40
Minimum
1
Maximum
50
promptstring

Text prompt for image generation

aspect_ratiostring

The aspect ratio of your output image. This value is ignored if you are using an input image.

Default
"1:1"
output_formatstring

Format of the output images

Default
"webp"
output_qualityinteger

Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.

Default
90
Maximum
100
prompt_strengthnumber

Prompt strength (or denoising strength) when using image to image. 1.0 corresponds to full destruction of information in image.

Default
0.85

Output schema

Type
uri[]