1.1.1

Use Segment Anything model to do interactive segmentation. See demo here: https://twitter.com/sfjccz/status/1643992289294057472?s=20

--enable-interactive-seg --interactive-seg-model=vit_l  --interactive-seg-device=cuda

• Available:
  • vit_b: small
  • vit_l: mid (Recommend)
  • vit_h: large
• Available device:
  • cuda
  • cpu
  • mps

1.0.0

This version contains a lot of features, so I set the version number to 1.0. I hope these updates will help you in your work.

Plugins

plugins_demo_720.-.720WebShareName.mov

In the post-processing of image cleaning, in addition to erasing, algorithms such as facial repair or super-resolution are often used. Now you can directly use them in Lama Cleaner. See the Plugins Doc for how to use it.

• RemoveBG: Remove images background
• RealESRGAN: Super Resolution
• GFPGAN: Face Restoration
• RestoreFormer: Face Restoration

Other Features

• Stable Diffusion ControlNet Inpainting: thanks for https://github.com/mikonvergence/ControlNetInpaint, now you can use ControlNet inpainting when using sd1.5 model. This can make your inpainting results more consistent with the original structure. Run lama-cleaner with--sd-controlnet to enable it.
• Load Stable Diffusion 1.5 model(ckpt/safetensors) from local path: Run lama-cleaner with--model sd.15 --sd-local-model-path /path/to/your/local/inpainting_model.ckpt to enable it. You can learn how to create a inpainting in AUTO1111's webui here
• MAT model vRAM usage improvement: Now defaulting to using fp16 format, which use less vRAM and run faster.
• Better FileManager: implement some improve suggestion mentioned here

0.37.0

New Stable Diffusion inpainting model, you can choose different models for different scenarios

• --model=anything4: converted from https://huggingface.co/andite/anything-v4.0
• --model=realisticVision1.4: converted from https://huggingface.co/SG161222/Realistic_Vision_V1.4

Original	sd1.5	anything4

0.36.0

• Rerun last mask: #209
  
• Save result image without confirm when --output-dir is used: #220
• Keep brush size when switch image: #214
• new side-project tldream: Turn your sketch into a refined image using Stable Diffusion and ControlNet https://github.com/Sanster/tldream

0.35.0

0.35.0

New Model: InstructPix2Pix

• --model instruct_pix2pix
• github: https://github.com/timothybrooks/instruct-pix2pix
• paper: https://arxiv.org/abs/2211.09800

InstructPix2Pix model can work without mask.

original	result	Prompt	Guidance Scale	Image Guidance Scale	Seed
		turn the duck blue, in the style of van gogh	9	1.6	108227038
		make her hair black	7	1.5	749559112
		make it summer	7	1.5	195504576

Share result by GIF

Click the GIF button in the toolbar, you can download a result GIF, it's fun!

0.34.0: Windows Installer v2

Windows Installer v2

https://lama-cleaner-docs.vercel.app/install/windows_1click_installer

Remove the tasks.py file, and add a gradio based web config page to help the user set command line args. Click the Save configurations button will save an installer_config.json file in the same directory and the win_start.bat script will load this JSON file when starting the server.

New command line args

--no-gui-auto-close: when starting as a desktop app, the backend server will auto close, if the app is closed, but some users may have bug like #188 . If it happens to you, this arg can prevent the backend auto close after the GUI window is closed.

docker image 0.33.0

New GPU docker image, update Cuda and pytorch version, add xformers. With --enable-xformers, SD model get 30%~40% performance improvement

• cuda: 11.7
• pytorch: 1.13.1
• minimum nvidia driver: 515.43.04+
• xformers: 0.0.16rc425

docker run --gpus all -p 8080:8080 \
-v /path/to/cache_dir:/root/.cache/ \
--rm cwq1913/lama-cleaner:gpu-0.33.0 \
lama-cleaner --device=cuda --port=8080 --host=0.0.0.0 --enable-xformers

0.33.0

Optimize GPU Memory

Correctly implement --cpu-offload, test result for 512x512 image:

Stable Diffusion Model

• fp16: 2GB
• --no-half: 3GB

Paint by Example Model

• fp16: 2.6GB
• --no-half: 4.5GB

Document: https://lama-cleaner-docs.vercel.app/memory

0.32.1

• fix image EXIF rotation bug: #185

0.32.0

Lama Cleaner Docs

Docs website: https://lama-cleaner-docs.vercel.app/

New command line arg

To solve the most frequently asked question: how to change the model directory

--model-dir: set model download directory