Qing

https://github.com/Sanster/lama-cleaner Lama-cleaner: Image inpainting tool powered by [LaMa](https://github.com/saic-mdal/lama) https://user-images.githubusercontent.com/3998421/153323093-b664bb68-2928-480b-b59b-7c1ee24a4507.mp4

- [x] add corpus for get_sample line by line from txt file: 9f8b2561667259a8cab27076b7140fa379d52d29 - [x] add helper runner to generate images by different configs : 02147a6a145a902fdf8c79682d6f953a3e7d8481 - [x] image width...

Optimize the logic of the brush at the edge

11

https://github.com/Sanster/lama-cleaner/issues/40#issuecomment-1103926970

Inspired by: https://github.com/initml/cleanup.pictures/issues/36

Questions about training data

24

Thanks for your code and dataset! I have two questions about training data: 1. Some images' short side length is not equal to 600(e.g. img_1651), but the label's width is...

https://github.com/Sanster/lama-cleaner (It started out as a way to self-hosting the [LaMa](https://github.com/saic-mdal/lama) model, so...) https://user-images.githubusercontent.com/3998421/153323093-b664bb68-2928-480b-b59b-7c1ee24a4507.mp4

Thank you for open-sourcing your code and pre-training model. I maintain an inpainting tool [Lama Cleaner](https://github.com/Sanster/lama-cleaner) that allows anyone to easily use the SOTA inpainting model. https://user-images.githubusercontent.com/3998421/196976498-ba1ad3ab-fa18-4c55-965f-5c6683141375.mp4 It's really easy...

Question about training Tnet model only using real data

19

Have you ever tried to train Tnet only using real data(using unsupervised training)? I am curious if it is possible to converge. Thanks

Question about joint training

1

I'm trying to implement joint training of PaperEdge. Although PaperEdge's Supplementary Material mentions joint training did get further improvement, in my opinion, end-to-end training is more practical from a practical...

In the past two days, lama-cleaner got over 200 stars, I can't find any clues why this happen. I would appreciate it if any recent stargazers could tell me where...