CodeFormer

CodeFormer copied to clipboard

Codeformer Colab doesn't enhance video

1

I tried codeformer colab for a mp4 video segment, but after I uploaded the video I got this bug: raceback (most recent call last): File "/content/CodeFormer/inference_codeformer.py", line 116, in raise...

navasgejza

Predicted face problem in Stage1

5

I trained 80000 steps in Stage1, and I found that the output faces were very strange, is it OK ? prediction:  gt:  So I used the pre-trained model...

HualeiZhuu

My limit issue

tabre98

My limit change please

tabre98

Hair in b&w images get green patches after face restore

4

# Command used: python inference_codeformer.py -w 0.5 -s 1 --input_path input.jpeg # Input Image  # Output Image  Any idea how to resolve it ?

vicky-aipaintr

Output of Codeformer is a black image

5

Hi everyone, Ive encountered some problem when trying the google collab version of the codeformer demo. It seems fine for some images, but I've found out that there are some...

ChrisDeantana

Is it normal for big loss in stage2, cross entropy loss?

6

I find the cross_entropy_loss is big in training stage2, between 1e-1~1e0. From a numerical perspective, it seems that this represents almost no optimization of codebook searching.

YilanWang

IndexError: list index out of range - pytorch nightly/cuda 12.1

1

Ran the entire setup but had to install pytorch nightly to match my cuda version. Verified pytorch and cuda are working fine. `print(torch.__version__) 2.1.0.dev20230728+cu121 print(torch.version.cuda) 12.1 print(torch.cuda.is_available()) True` But now...

sloflo

Hi, when I set the fidelity_weight w to be greater than 0 in the inference stage, the following error occurs: return F.conv2d(input, weight, bias, self.stride, RuntimeError: cuDNN error: CUDNN_STATUS_MAPPING_ERROR Could...

JeremyLinky

I tried the colorization script, which works, but I noticed I cannot set the identity weight fidelity option and the dlib model to keep the identity of the person in...

epicstar7