Lama-cleaner

Latest version: v1.2.5

Safety actively analyzes 638452 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 6 of 8

0.17.0

- [Bug fix] resize strategy will lose some edge mask area
- Add model from https://github.com/SHI-Labs/FcF-Inpainting

||Lama|FcF|
|-----|-----|-----|
|![texture](https://user-images.githubusercontent.com/3998421/188305027-a4260545-c24e-4df7-9739-ac5dc3cae879.jpeg)|![texture_lama](https://user-images.githubusercontent.com/3998421/188305024-2064ed3e-5af4-4843-ac10-7f9da71e15f8.jpeg)|![texture_fcf](https://user-images.githubusercontent.com/3998421/188305006-a08d2896-a65f-43d5-b9a5-ef62c3129f0c.jpeg)|

0.16.0

Add [MAT](https://github.com/fenglinglwb/MAT) model

![mat](https://user-images.githubusercontent.com/3998421/186435417-ae413583-f3fe-46bf-a1b7-9152a6f8d234.gif)

0.15.0

High-Resolution Strategy configuration

Each model has its own independent High-Resolution Strategy configuration.

Download Mask

Enable download inpainting mask when download result

![image](https://user-images.githubusercontent.com/3998421/180629601-02c83332-9f3a-4828-be95-4c5f76618846.png)


New Model: [ZITS](https://github.com/DQiaole/ZITS_inpainting)

| Original Image | ZITS | LaMa |
| ---------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------- |
| ![zits_original](https://user-images.githubusercontent.com/3998421/180464918-eb13ebfb-8718-461c-9e8b-7f6d8bb7a84f.png) | ![zits_compare_zits](https://user-images.githubusercontent.com/3998421/180464914-4db722c9-047f-48fe-9bb4-916ba09eb5c6.png) | ![zits_compare_lama](https://user-images.githubusercontent.com/3998421/180464903-ffb5f770-4372-4488-ba76-4b4a8c3323f5.png) |

Image is from [ZITS](https://github.com/DQiaole/ZITS_inpainting) paper. I didn't find a good example to show the advantages of ZITS and let me know if you have a good example. There can also be possible problems with my code, if you find them, please let me know too!

0.14.0

- Redo: Now you can `Redo` the inpainting result
<img width="297" alt="image" src="https://user-images.githubusercontent.com/3998421/176456044-199349c4-eb1f-477c-a37a-cb0fb6bf5b0b.png">


- Gradually Inpainting(enabled by default): Perform inpainting on the last inpainting result, this makes it possible to further improve the inpainting result. It also helps to keep unmasked previous inpainting regions unchanged

<img width="708" alt="image" src="https://user-images.githubusercontent.com/3998421/176455800-777d3933-2e64-453f-869e-54f6c9c6fc8b.png">

- `Start New` change to `Upload New`: upload new file at editor page
<img width="188" alt="image" src="https://user-images.githubusercontent.com/3998421/176459988-dc664dcc-7fbc-4bc1-91b9-3c87ffd4d746.png">

0.13.0

latent-diffusion model add [plms](https://arxiv.org/abs/2202.09778) sampler. In general plms can get better results with fewer steps.

Original Image
![overture-creations-5sI6fQgYIuo](https://user-images.githubusercontent.com/3998421/173237980-f3594979-2851-4be7-9e3e-54d7fa996ca2.jpg)

ddim sampler steps=5
![dog_ddim_5](https://user-images.githubusercontent.com/3998421/173237956-785c298d-3f84-4373-93f9-2294b3d4897f.jpeg)

plms sampler steps=5
![dog_plms_5](https://user-images.githubusercontent.com/3998421/173237949-0d7e7bf5-00dd-4413-b9ad-b69411380802.jpeg)

0.12.0

- bug fix: fix sizeLimit reset after inpainting.
- ldm model fp16 support, use less GPU memory. Benchmark on 3090

|Image size| GPU memory|
|-----------|-------------|
| 720x519 | 6147mb|
|1080x778|17499mb|

Page 6 of 8

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.