stability-ai / stable-diffusion-inpainting

Fill in masked parts of images with Stable Diffusion

  • Public
  • 19.5M runs
  • A100 (80GB)
  • GitHub
  • License

Run stability-ai/stable-diffusion-inpainting with an API

Input schema

maskuri

Black and white image to use as mask for inpainting over the image provided. White pixels are inpainted and black pixels are preserved.

seedinteger

Random seed. Leave blank to randomize the seed

imageuri

Initial image to generate variations of. Will be resized to height x width

widthinteger

Width of generated image in pixels. Needs to be a multiple of 64

Default
512
heightinteger

Height of generated image in pixels. Needs to be a multiple of 64

Default
512
promptstring

Input prompt

Default
"a vision of paradise. unreal engine"
schedulerstring

Choose a scheduler.

Default
"DPMSolverMultistep"
num_outputsinteger

Number of images to generate.

Default
1
Minimum
1
Maximum
4
guidance_scalenumber

Scale for classifier-free guidance

Default
7.5
Minimum
1
Maximum
20
negative_promptstring

Specify things to not see in the output

num_inference_stepsinteger

Number of denoising steps

Default
50
Minimum
1
Maximum
500
disable_safety_checkerboolean

Disable safety checker for generated images. This feature is only available through the API. See [https://replicate.com/docs/how-does-replicate-work#safety](https://replicate.com/docs/how-does-replicate-work#safety)

Output schema

Type
uri[]