lama icon indicating copy to clipboard operation
lama copied to clipboard

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

Results 149 lama issues
Sort by recently updated
recently updated
newest added

Hi, I have trained lama-fourier model on my own dataset. I found that the saved model size is 676 MB. I thought the model size is too large. May I...

In the example of lama, I found that the texture of masked area is reasonable but with chromatic aberration. What could be the reason for this? ![5089a2acbb6b480d73fa0557ac323b1e](https://github.com/advimman/lama/assets/50061868/8f0fc9a6-352c-4add-a059-248600368d7b) ![b13d8205e8c9ddf60959ee208f0d88f4](https://github.com/advimman/lama/assets/50061868/ec3f973f-8a28-4408-920e-77fe836bc923)

Hello, Is running via GPU going to always be more faster than CPU? I do not have a GPU for my server and am only able to run via device=cpu....

Hello, I am unable to load celebaHq model.ckpt for fine tuning purpose. It show the below warning even after using "+trainer.kwargs.resume_from_checkpoint=LaMa_models/lama-celeba-hq/lama-fourier/models/best.ckpt" flag for using pretrained checkpoints. UserWarning: No checkpoint file...

I try to run lama inside WSL2 and here's the issue I'm getting. What's the correct way to install for WSL? ``` UserWarning: NVIDIA RTX A6000 with CUDA capability sm_86...

Firstly, thank you very much for your research! Secondly, I would like to inquire about the meaning of the grayscale images generated by the model on the training, validation, and...

Hello, I've noticed a discrepancy between the results I see during training and the predictions made when loading the trained weights. When I train the model, the visuals look as...

I have added resume_from_checkpoint in the yaml,but the output of the first epoch is still 0

usage: gen_mask_dataset.py [-h] [--n-jobs N_JOBS] [--ext EXT] config indir outdir gen_mask_dataset.py: error: the following arguments are required: outdir when I run this as instructed here I get this error on...