Inpainting from text

Replace part of an image using two texts: the target and its replacement.
powered by Stable Diffusion AI

Mask prompt

Describe the object that should be changed


Describe how the final image should look like

Init image

Upload the original image to be modified.
Max: 512x512px (auto-resized)
Drag and drop files here or click


The AI used to generate the image.
Stable Diffusion Inpaint 2 (inpaint, general)

Available in Power Mode


Number of images to generate
More options

Negative prompt

Describe what you DON'T want in the generated image


Adjusts how much the AI tries to fit the prompt (higher = stricter, lower = more freedom). The sweet spot is between 6-10, extreme values may produce more artifacts.



Defines the sampling method used to generate the image.
Euler Ancestral


Unique image seed number. If not provided, the image will be random.

Available in Power Mode


Number of sampling steps. More steps = more details but also longer computation time.

Available in Power Mode


Upscale the image by this factor using the Real-ESRGAN model. Currently only a factor of 2 is supported.
You're provided with the AI raw output under the terms of the CreativeML Open RAIL-M license.
An error has occurred. This application may need to be reloaded. Reload Dismiss