Releases: Sanster/IOPaint
IOPaint-1.5.3
- 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 ofrembg
package to use gpu, see more at: https://github.com/danielgatis/rembg?tab=readme-ov-file#installation - fix
--output-dir
not work: #597 - fix all 404 error in the terminal
- fix remove-bg plugin requirements
- Frontend
- now support smaller brushsize
- better error handle
IOPaint-1.5.0
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
IOPaint-1.4.2
- remove basicsr/gfpgan/realesrgan dependencies, migrate the required code to iopaint. fix #559 #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: Sanster/lama-cleaner-docs#58
- Add sam2 models:
--interactive-seg-model sam2_base
- sam2_tiny
- sam2_small
- sam2_base
- sam2_large
- Add
mask tab
in fileManager,--mask-dir
IOPaint-1.3.3
BrushNet and PowerPaintV2 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
.
IOPaint-1.2.2
- Press and hold
Alt
/Option
and use the mouse wheel to adjust the mouse - Fix minor bug in Extender(outpainting)
IOPaint-1.2.0
-
New
--interactive-seg-model
from Segment Anything in High Quality- sam_hq_vit_b
- sam_hq_vit_l
- sam_hq_vit_h
-
Automatically expand the input box when prompt input is selected.
prompt_input.mp4
IOPaint-1.1.1
- Automatically open the browser after the service is started:
iopaint start --inbrowser
.
- RemoveBG add more model:
iopaint start --enable-remove-bg --remove-bg-model briaai/RMBG-1.4
- u2net
- u2netp
- u2net_human_seg
- u2net_cloth_seg
- silueta
- isnet-general-use
- briaai/RMBG-1.4
- If a plugin is enabled, the model of the plugin can be switched on the frontend page.
IOPaint
You can check the main feature updates of IOPaint in the Beta Release. This release mainly includes:
New Model: AnyText
--mode=Sanster/AnyText
AnyText.mp4
Other
- New docs site: https://www.iopaint.com/
- Reverse mask
IOPaint Beta release
IOPaint Beta Release
It's been a while since the last release of lama-cleaner(now renamed to IOPaint.), partly due to the fact that during this time I have released my own first macOS application OptiClean and started playing Baldur's Gate 3, which has taken up a lot of my free time. Apart from time constraints, another reason is because the code for the project has become increasingly complex, making it difficult to add new features. I was hesitant to make changes to the code, but in the end, I made the decision to completely refactor the front-end and back-end code of the project, hoping that this change will help the project moving forward.
The refactoring includes: switch to Vite, new css framework tailwindcss, new state management library zustand, new UI library shadcn/ui, using more modern python libraries such as fastapi and typer. These refactors were painful and involved significant changes, but I think they were worth it. They made the project structure clearer, easier to add new features, and more accessible for others to contribute code.
Although I am not an AIGC artist or creator, I enjoy developing tools and I wanted to make this project more practical for inpainting and outpainting needs. Below are the new features/models that have been added with this beta release:
New cli command: Batch processing
After pip install iopaint
, you can use the iopaint
command in the command line. iopaint start
is the command for starting the model service and web interface, while iopaint run
is used for batch processing. You can use iopaint start --help
or iopaint run --help
to view the supported arguments.
Better API doc
Thanks to fastapi, now all backend interfaces have clear API documentation. After starting the service with iopaint start
, you can access http://localhost:8080/docs
to view the API documentation.
Support all sd1.5/sd2/sdxl normal or inpainting model from HuggingFace
Previously, lama-cleaner only supported the built-in anything4
and realisticVision1.4
SD inpaint models. iopaint start --model
now supports automatically downloading models from HuggingFace, such as Lykon/dreamshaper-8-inpainting
. You can search available sd inpaint models on HuggingFace. Not only inpaint models, but you can also specify regular sd models, such as Lykon/dreamshaper-8
. The downloaded models can be seen and switched on the front-end page.
Single file ckpt
/safetensors
models are also supported. IOPaint will search model under stable_diffusion
folder in the --model-dir
(default value ~/.cache) directory.
Outpainting
You can use Extender
to expand images, with optional directions of x, y, and xy. You can use the built-in expansion ratio or adjust the expansion area yourself.
outpainting.mp4
Generate mask from segmentation model
RemoveBG
and Anime Segmentation
are two segmentation models. In previous versions, they could only be used to remove the background of an image. Now, the results from these two models can be used to generate masks for inpainting.
Enpand or shrink mask
It is possible to extend or shrink interactive segmentation mask or removebg/anime segmentation mask.
More samplers
I have added more samplers based on this Issue A1111 <> Diffusers Scheduler mapping #4167.
LCM Lora
https://huggingface.co/docs/diffusers/main/en/using-diffusers/inference_with_lcm_lora
Latent Consistency Models (LCM) enable quality image generation in typically 2-4 steps making it possible to use diffusion models in almost real-time settings. The model will be downloaded on first use.
FreeU
https://huggingface.co/docs/diffusers/main/en/using-diffusers/freeu
FreeU is a technique for improving image quality. Different models may require different FreeU-specific hyperparameters, you can find how to adjust these parameters in the original project: https://github.com/ChenyangSi/FreeU
New Models
- MIGAN: Much smaller (27MB) and faster than other inpainting models(LaMa is 200MB), it can also achieve good results.
- PowerPaint:
--model Sanster/PowerPaint-V1-stable-diffusion-inpainting
PowerPaint is a stable diffusion model optimized for inpainting/outpainting/remove_object tasks. We can control the model's results by specifying the task.
- Kandinsky 2.2 inpaint model:
--model kandinsky-community/kandinsky-2-2-decoder-inpaint
- SDXL inpaint model:
--model diffusers/stable-diffusion-xl-1.0-inpainting-0.1
- MobileSAM:
--interactive-seg-model mobile_sam
Lightweight SAM model, faster and requires fewer resources. Currently, there are many other variations of the SAM model. Feel free to submit a PR!
Other improvement
- If FileManager is enabled, you can use
left
orright
to switch Image - fix icc_profile loss issue(The color of the image changed globally after inpainting)
- fix exif rotate issue
Window installer user
For 1-click window installer users, first of all, I would like to thank you for your support. The current version of IOPaint is a beta version, and I will update the installation package after the official release of IOPaint.
Maybe a cup of coffee
During the development process, lots of coffee was consumed. If you find my project useful, please consider buying me a cup of coffee. Thank you! ❤️. https://ko-fi.com/Z8Z1CZJGY
1.2.0
Hi everyone, I am planning to create a macOS inpainting app, it would be completely native from UI to model, no JS/Python/PyTorch involved. The app will be small and has better local file support e.g. directly modify a local image file. Here is a demo video, the model runs MUCH faster on the M2 GPU than using pytorch(mps device).
mac_app2.mp4
If you are interested, please fill out this form with your email address. I will send an email notification when the app is released and provide a 50% discount code for you. Thank you.
1.2.0 Update
Better ControlNet support in Stable Diffusion
https://lama-cleaner-docs.vercel.app/models/controlnet
--sd-controlnet
: enable controlnet in stable diffusion--sd-controlnet-method
: set controlnet method used, method can be change in web ui- control_v11p_sd15_canny
- control_v11p_sd15_openpose
- control_v11p_sd15_inpaint
- control_v11f1p_sd15_depth
New plugin
Anime Segmentation: --enable-anime-seg