Shangchen Zhou

Update to support running on CPU. If there is a GPU in your workstation, you may need to check if your PyTorch was installed correctly, and make sure it is...

Thanks for this suggestion, maybe a video algorithm with frame propagation could help with temporal consistency.

Video interpolation could be an effective engineering solution for this case, but we will prioritize the algorithm updates, e.g., a video version of CodeFormer with recurrent frame propagation, which could...

There could be a model loading error in stable-diffusion-webui, please report this issue under their GitHub repo since our CodeFormer repo doesn't have this error.

@Zmax15 Instead, you can use our code or online demo (https://huggingface.co/spaces/sczhou/CodeFormer) until they fix this bug.

Hi @machinelearnear, thanks for your sharing and effort. You can set w to 1 (even 1.1, 1.2) to keep better temporal coherence, you could have a try :)

Woc, the video results are awesome :+1: Thanks @machinelearnear for making this demo for us!

@AlonDan well got it. I will modify it in a later update. Thanks!

@AlonDan has updated, please try it out!

@MushroomFleet @roboldham We updated input arguments with **uniform naming**. The readme file and official Colab have been modified accordingly. Update: - `--w` to `--fidelity_weight` or `-w` - `--test_path` to `--input_path`...