You're looking at a specific version of this model. Jump to the model overview.

andreasjansson /stable-diffusion-inpainting:e490d072

Input

string
Shift + Return to add a new line

Input prompt

Default: ""

string
Shift + Return to add a new line

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`).

Default: ""

*file

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

*file

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

boolean

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

Default: false

integer
(minimum: 1, maximum: 4)

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

Default: 1

integer
(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

number
(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7.5

integer

Random seed. Leave blank to randomize the seed

Output

No output yet! Press "Submit" to start a prediction.