andreasjansson/stable-diffusion-inpainting

Inpainting using RunwayML's stable-diffusion-inpainting checkpoint

Input
Configure the inputs for the AI model.

Black and white image to use as mask. White pixels are inpainted and black pixels are preserved.

Random seed. Leave blank to randomize the seed

Input image to in-paint. Width and height should both be divisible by 8. If they're not, the image will be center cropped to the nearest width and height divisible by 8

Input prompt

If this is true, then black pixels are inpainted and white pixels are preserved.

1
4

Number of images to output. NSFW filter in enabled, so you may get fewer outputs than requested if flagged

1
20

Scale for classifier-free guidance

The prompt or prompts not to guide the image generation. Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).

1
500

Number of denoising steps

Output
The generated output will appear here.

No output yet

Click "Generate" to create an output.

stable-diffusion-inpainting - ikalos.ai