IOPaint VS lama

„Inpaint anything“ and „cleaner“ extension can remove text or anything you mark, if you are on A1111 webui, you can install them from extension tab. Standalone , there is lama cleaner , https://github.com/Sanster/lama-cleaner

This is an app developed from my other open source side project Lama Cleaner.

When you're training, the model learns things you don't prompt for, like the face you want, but it also learns things that don't change much, even if prompted. So if there is a necklace there, it'll learn that something goes in the neck area. You might look into Lama Cleaner to remove the necklaces without messing anything else up.

I prefer Lamar Cleaner: https://github.com/Sanster/lama-cleaner to anything built into A1111.

I use Lama Cleaner for stuff like this. Works great and supports all the SD models + Segment Anything, etc etc etc : https://github.com/Sanster/lama-cleaner

You could try to use ControlNet inpaint+lama locally, but results aren't as good in my experience. Or you could try local install of lama directly, but the setup process isn't very smooth.

You may be able to remove the actor with lama. https://github.com/advimman/lama

LaMa: Resolution-robust Large Mask Inpainting with Fourier Convolutions (Apache-2.0 license) Roman Suvorov, Elizaveta Logacheva, Anton Mashikhin, Anastasia Remizova, Arsenii Ashukha, Aleksei Silvestrov, Naejin Kong, Harshith Goka, Kiwoong Park, Victor Lempitsky (Samsung Research and EPFL)

You could try using LaMA: https://github.com/saic-mdal/lama .

Task 1: 30$ Write a script to prepare data for https://github.com/saic-mdal/lama. You should be able to prove on video that your script works properly after i give you some data and you train and there's some acceptable output (not perfect, since i know how ml works).

I have some interest in image inpainting, but the recent paper introduced by Samsung - https://github.com/saic-mdal/lama seems like it reached a stage where there isn't much room that we can add for novelty. I am quite interested but not confident if I can come up with a novel idea that can do better than the proposed model, especially if they trained the model on multiple GPUs for days, which is something that I don't have.

Code: https://github.com/saic-mdal/lama