CodeFormer
CodeFormer copied to clipboard
sczhou
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
Is it possible to train, or has someone, willing to share, a lower resolution trained model? e.g. 256x256 pixel ? I would need it for speed of inference reason and...
I have set up this code as they indicated in description. I was trying to upscale images from AFLW with a factor of 5. However, even that I had scaling...
None of your applications are working on my image. Can you lend a hand in troubleshooting the issue?
I couldn't find any of the applications you claim to be working. Could you help me figure out what the problem is? Input image  command that i used ```...
Modify the cross layer connections of the networks in stages 2 and 3. In stage 3, train the GAN loss to nan and the tensor of the network output image...
$ python inference_codeformer.py --input_path inputs/cropped_faces/0143.png Segmentation fault: 11 we are found this function has problem: # ------------------ set up CodeFormer restorer ------------------- net = ARCH_REGISTRY.get('CodeFormer')(dim_embd=512, codebook_size=1024, n_head=8, n_layers=9, connect_list=['32', '64',...
D:\ProgramData\anaconda3\CodeFormer>python inference_codeformer.py --bg_upsampler realesrgan --face_upsample -w 0.8 --input_path E:\shipin\ Traceback (most recent call last): File "D:\ProgramData\anaconda3\CodeFormer\inference_codeformer.py", line 116, in raise FileNotFoundError('No input image/video is found...\n' ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ FileNotFoundError: No input image/video...
Name CodeFormer_basicsr is not found, use name: CodeFormer_basicsr_basicsr! Traceback (most recent call last): File "/content/drive/MyDrive/dreamtalk/CodeFormer/inference_codeformer.py", line 135, in net = ARCH_REGISTRY.get('CodeFormer_basicsr')(dim_embd=512, codebook_size=1024, n_head=8, n_layers=9, File "/content/drive/MyDrive/dreamtalk/CodeFormer/basicsr/utils/registry.py", line 71, in get...
