Shangchen Zhou

Thank you! We have now released a web interface for our model, which can be accessed at https://huggingface.co/spaces/sczhou/CodeFormer. It's simple to use and we encourage you to give it a...

Hi, Since the network also takes the bicubic downsampled LR as the LR Guidance when downscale images, I also wonder if the model can generate LR images that lay in...

Thank you @pkuxmq for your answer.

Will add this option. Thanks for your suggestion.

The current inference script only supports video frame enhancement, its workflow is as follows: ``` 1. Extract frame images from the input video 2. Enhance frame images by CodeFormer and...

Hi @BiubiuGreen, the updated CodeFormer scripts can add back the original sound into enhanced video. Welcome to have a try! :hugs:

Could you please share this test image? We didn't get this before

Hi @WebberShaw , we have fixed this issue, you can pull the new update and check out our new commands for video enhancement. Note that: ``` # For Windows/Mac users,...

@chicman That sounds great, I will take a look at it and try to include it in the next update.

@chicman Have updated to support M1 chip now!