Iopaint

- add `--remove-bg-model briaai/RMBG-2.0` from: https://huggingface.co/briaai/RMBG-2.0
- add `--remove-bg-device`, device(cpu/cuda/mps) for remove background plugin, only supports briaai models(briaai/RMBG-1.4 and briaai/RMBG-2.0). For other remvoe-bg model(e.g Birefnet) you can install gpu version of `rembg` package to use gpu, see more at: https://github.com/danielgatis/rembg?tab=readme-ov-file#installation
- fix `--output-dir` not work: https://github.com/Sanster/IOPaint/issues/597
- fix all 404 error in the terminal
- fix remove-bg plugin requirements
- Frontend
- now support smaller brushsize
- better error handle

No more huggingface access token is needed at the first download time

Add anime manga big lama model

https://huggingface.co/dreMaz/AnimeMangaInpainting

`--model=anime-lama`

|Original Image| big-lama result| anime manga big-lama result|
|---------------|---------------|------------------------------|
||||


Add BiRefNet

Requires `rembg>=2.0.59`

`pip install -U rembg`

- birefnet-general: A pre-trained model for general use cases.
- birefnet-general-lite: A light pre-trained model for general use cases.
- birefnet-portrait: A pre-trained model for human portraits.
- birefnet-dis: A pre-trained model for dichotomous image segmentation (DIS).
- birefnet-hrsod: A pre-trained model for high-resolution salient object detection (HRSOD).
- birefnet-cod: A pre-trained model for concealed object detection (COD).
- birefnet-massive: A pre-trained model with massive dataset.

Add sam2.1

`--interactive-seg-model=sam2_1_tiny`

- sam2_1_tiny
- sam2_1_small
- sam2_1_base
- sam2_1_large

- remove basicsr/gfpgan/realesrgan dependencies, migrate the required code to iopaint. fix https://github.com/Sanster/IOPaint/issues/559 https://github.com/Sanster/IOPaint/issues/470
- Fix the issue where using Alt + Tab to switch windows causes the brush size to change via the mouse scroll wheel on Windows. fix: https://github.com/Sanster/lama-cleaner-docs/issues/58
- Add sam2 models: `--interactive-seg-model sam2_base`
- sam2_tiny
- sam2_small
- sam2_base
- sam2_large
- Add `mask tab` in fileManager, `--mask-dir`

<img width="1125" alt="image" src="https://github.com/user-attachments/assets/656ad1fa-b12a-4139-97f3-db7934161315">

[BrushNet](https://www.iopaint.com/models/diffusion/brushnet) and [PowerPaintV2](https://www.iopaint.com/models/diffusion/powerpaint_v2) can turn any normal sd1.5 model into an inpainting model.
When using any SD1.5 base model(e.g: `runwayml/stable-diffusion-v1-5`), the option for BrushNet/PowerPaintV2 will appear in the sidebar. The model will automatically download the first time it is used.

For BrushNet, there are two models to choose from: `brushnet_segmentation_mask` and `brushnet_random_mask`.
Using `brushnet_segmentation_mask` means that the final inpainting result will maintain consistency with the mask shape,
while `brushnet_random_mask` provides a more general ckpt for random mask shapes.

For PowerPaintV2, just like PowerPaintV1, it was trained with "learnable task prompts" to guide the model in achieving specific tasks more effectively. These tasks include `text-guided`, `shape-guided`, `object-remove`, and `outpainting`.



<img width="279" alt="image" src="https://github.com/Sanster/IOPaint/assets/3998421/9c1bd719-c4d4-42f9-92fb-146bc6b75b1f">

- Press and hold `Alt`/`Option` and use the mouse wheel to adjust the mouse
- Fix minor bug in Extender(outpainting)