Iopaint


- New model `--model sd2` : [Stable Diffusion 2](https://github.com/Stability-AI/stablediffusion)
- New sampler `dpm++`: [DPMSolverMultistepScheduler](https://huggingface.co/docs/diffusers/v0.9.0/en/api/schedulers#diffusers.DPMSolverMultistepScheduler) Empirically, sampling by DPM-Solver with only 20 steps can generate high-quality samples, and it can generate quite good samples even in only 10 steps.
- New device `--device mps`: M1/M2 Apple Silicon support, make sure your torch version is `1.13.0`. In theory, Lama Cleaner's code is device agnostic, but I don't have an M1 device to test it on, so if you encounter any problems, please try to provide a full screenshot of the error when opening an issue. Or just submit a PR to fix the problem, I'd appreciate it! ☮️ ✌️

Stable Diffusion
- Add match histogram option https://github.com/Sanster/lama-cleaner/pull/143, Match the inpainting result histogram to the source image histogram, which will improve the inpainting quality for some images.
- Add `--sd-enable-xformers` command line arg https://github.com/Sanster/lama-cleaner/pull/146, which gives a big boost in speed while also reducing GPU memory usage significantly. To use this option you need to Install `https://github.com/facebookresearch/xformers` first

Interactive Segmentation
In this release, Lama Cleaner integrates with a small model(so it can run on CPU) from [ClickSEG](https://github.com/XavierCHEN34/ClickSEG). I have wanted to add this feature for a long time, it's fun and useful in many scenarios.

The basic operation process is as follows:
- Enable `Interactive Segmentation` by clicking the button on the bottom toolbar, or by shortcut `i`
- Left click meaning `position click` (include things you want to mask)
- Right click meaning `negative click`(exclude things you want to mask)
- Complete the mask with the brush (If the result of interactive segmentation is not so good)
- Inpainting!

https://user-images.githubusercontent.com/3998421/205301195-f497922a-1037-4501-a865-d140a7455331.mp4

Manga inpainting model from: https://github.com/msxie92/MangaInpainting

Manga model works better on high-quality manga image then LaMa model.

Original Image


| Model | 1080x740 | 1470x1010 |
|--------|------------|------------|
|Manga|||
|[LaMa](https://github.com/saic-mdal/lama)|||

Lama Cleaner is no living on 🤗 Huggingface Spaces! https://huggingface.co/spaces/Sanster/Lama-Cleaner-lama

<img width="1760" alt="image" src="https://user-images.githubusercontent.com/3998421/202192760-a4f783f9-da39-4fac-a38d-2cb117a5e402.png">

- Add upload mask button. Once uploaded, you can rerun inpainting with the current mask by clicking the play button. The mask must have the same shape as the image.
<img width="208" alt="image" src="https://user-images.githubusercontent.com/3998421/202080438-dbd441e3-c1d3-4811-a9a3-81d4d34fbefe.png">
mask example(white area is mask area):

- Better error message when CUDA OOM
- Add `--disable-model-switch` when start server. Disable model switch from frontend
- sd1.5
- Faster model loading thanks to [diffusers 0.7.0 update](https://github.com/huggingface/diffusers/releases/tag/v0.7.0):
- Negative Prompt
- Add `k_euler` and `k_euler_a` sampler
- Make the cropper easier to drag and resize: https://github.com/Sanster/lama-cleaner/pull/111

- remove `torch.amp.autocast` in sd1.5, run 25% faster(tested on 3080)
- remove `Strength` from the sd side panel, it has nothing to do with inpainting
- fix the flaskwebgui version

win_one_click_installer
- Windows One Click Installer: Follow the guide here to install: https://github.com/Sanster/lama-cleaner/blob/main/scripts/README.md
- Add Buy Me a Coffee btn on page



one_click_installer
Follow the guide here to install it: https://github.com/Sanster/lama-cleaner/blob/main/scripts/README.md