Inpaint Anything extension performs stable diffusion inpainting on a browser UI using any mask selected from the output of Segment Anything.
Using Segment Anything enables users to specify masks by simply pointing to the desired areas, instead of manually filling them in. This can increase the efficiency and accuracy of the mask creation process, leading to potentially higher-quality inpainting results while saving time and effort.
To install the software, please follow these steps:
- Open the
Extensions
tab on the AUTOMATIC1111's Stable Diffusion Web UI. - Select the
Install from URL
option. - Enter
https://github.com/Uminosachi/sd-webui-inpaint-anything.git
in theURL for extension's git repository
field. - Click on the
Install
button. - Once installation is complete, restart the Web UI.
- Note: This extension supports v1.3.0 or higher of AUTOMATIC1111's Stable Diffusion Web UI.
- If you intend to use the memory-efficient xformers, please append the
--xformers
argument to your startup command. For example, run./webui.sh --xformers
orwebui.bat --xformers
- Note: If you have a privacy protection extension enabled in your web browser, such as DuckDuckGo, you may not be able to retrieve the mask from your sketch.
- Note: In Gradio version 3.23.0 or older, the segmentation image may appear small on the Web UI.
To download the model:
- Go to the
Inpaint Anything
tab of the Web UI. - Click on the
Download model
button located next to the Segment Anything Model ID that include Segment Anything in High Quality Model ID and Fast Segment Anything.- The SAM is available in three sizes. The sizes are: Base < Large < Huge. Please note that larger sizes consume more VRAM.
- Wait for the download to complete.
- The downloaded model file will be stored in the
models
directory of this application's repository.
- Drag and drop your image onto the input image area.
- Outpainting can be achieved by the
Padding options
, configuring the scale and balance, and then clicking on theRun Padding
button.
- Outpainting can be achieved by the
- Click on the
Run Segment Anything
button. - Use sketching to point the area you want to inpaint. You can undo and adjust the pen size.
- Click on the
Create mask
button. The mask will appear in the selected mask image area.
Expand mask region
button: Use this to slightly expand the area of the mask for broader coverage.Trim mask by sketch
button: Clicking this will exclude the sketched area from the mask.
- Enter your desired Prompt and Negative Prompt, then choose the Inpainting Model ID.
- Click on the
Run Inpainting
button (Please note that it may take some time to download the model for the first time).- In the Advanced options, you can adjust the Sampler, Sampling Steps, Guidance Scale, and Seed.
- If you enable the
Mask area Only
option, modifications will be confined to the designated mask area only.
- Inpainting process is performed using diffusers.
- Tips: You can directly drag and drop the inpainted image into the input image field on the Web UI.
- Choose the Cleaner Model ID.
- Click on the
Run Cleaner
button (Please note that it may take some time to download the model for the first time). - Cleaner process is performed using Lama Cleaner.
- This tab becomes accessible when you have an inpainting model.
- The required model should include
inpaint
(case-insensitive) in its filename and must be located in thestable-diffusion-webui/models
directory. - Once the model is recognized, it becomes selectable from the Inpainting Model ID dropdown list.
- The process can be executed swiftly, without requiring model loading, when the Stable Diffusion checkpoint (located in the upper left corner of the Web UI) matches the selected Inpainting Model ID.
- To execute inpainting, use the Stable Diffusion checkpoint, located in the upper left of the Web UI, with the ControlNet inpaint model.
- Enter your desired Prompt and Negative Prompt.
- Click on the
Run ControlNet Inpaint
button to start the process.- In the Advanced options, you can adjust the Sampler, Sampling Steps, Guidance Scale, Denoising Strength, and Seed.
- The Control Weight and Control Mode can be modified in the ControlNet options.
- The Reference-Only Control can be utilized if the Multi ControlNet setting is configured to 2 or higher.
- Make sure to install the ControlNet extension that supports the
inpaint_only
preprocessor and the ControlNet inpaint model. - Requires: The sd-webui-controlnet extension and the ControlNet-v1-1 inpaint model in the
extensions/sd-webui-controlnet/models
directory.
- Gives ability to just save mask without any other processing, so it's then possible to use the mask in img2img's
Inpaint upload
with any model/extensions/tools you already have in your AUTOMATIC1111. Get mask as alpha of image
button: Save the mask as RGBA image, with the mask put into the alpha channel of the input image.Get mask
button: Save the mask as RGB image.- After the
Get mask
button press you can useSend to img2img inpaint
button under the mask image to send both input image and mask to the img2img tab.
- The inpainted image will be automatically saved in the folder that matches the current date within the
outputs/inpaint-anything
directory. - You can switch to the
outputs/img2img-images
directory via theInpaint Anything
section found in theSettings
tab on the Web UI.
The source code is licensed under the Apache 2.0 license.
- Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., Lo, W-Y., Dollár, P., & Girshick, R. (2023). Segment Anything. arXiv:2304.02643.
- Ke, L., Ye, M., Danelljan, M., Liu, Y., Tai, Y-W., Tang, C-K., & Yu, F. (2023). Segment Anything in High Quality. arXiv:2306.01567.
- Zhao, X., Ding, W., An, Y., Du, Y., Yu, T., Li, M., Tang, M., & Wang, J. (2023). Fast Segment Anything. ArXiv:2306.12156 [cs.CV].