stylegan2-ada-pytorch icon indicating copy to clipboard operation
stylegan2-ada-pytorch copied to clipboard

StyleGAN2-ADA - Official PyTorch implementation

Results 25 stylegan2-ada-pytorch issues
Sort by recently updated
recently updated
newest added

**Describe the bug** I'm getting this error when attempting to run the apply_factor.py script in your colab notebook: File "apply_factor.py", line 190, in value_range=(-1, 1) # change range to value_range...

I have been able to reproduce this colab's [SG2_ADA_PT_to_Rosinality.ipynb]( https://github.com/dvschultz/stylegan2-ada-pytorch/blob/main/SG2_ADA_PT_to_Rosinality.ipynb) test, but it seems to only work with 1024 and 512 resolutions. It fails for all the 256 resolution pkl...

**Describe the bug** trying to run `python generate.py --outdir=C:\StyleGan2_Tutorial\GeneratedImages --space="z" --trunc=1 --process="interpolation" --interpolation="slerp" --seeds=85,265,297,849 --network=C:\StyleGan2_Tutorial\Training_Runs\00013-columnsDataSet_1-auto1-resumecustom\network-snapshot-000800.pkl --frames=24 ` A clear and concise description of what the bug is. ![Capture](https://user-images.githubusercontent.com/25883191/151626237-3ba50c89-ed62-445e-9fc8-92964dca501c.PNG) - OS:...

When learning stylegan2-ada with custom data of 256*256 size, cfg seems to have no choice but to be auto. In this case, if I change pkl to pt, it does...

…pdates the main notebook with flags for these features.

Update allow version of Pytorch to 1.10 i had this error whe run the train: stylegan conv2d_gradfix not supported on PyTorch 1.10.0+cu111 So it works without the warning when the...

**Describe the bug** Title Exact Error - ` File "style_mixing.py", line 29, in num_range m = range_re.match(s) TypeError: expected string or bytes-like object` **To Reproduce** Steps to reproduce the behavior:...

- I trained a custom sg2-ada model from [the official pytorch implementation](https://github.com/NVlabs/stylegan2-ada-pytorch#training-new-networks) and now it is in .pkl (Custom Dataset and 256px) - I used export_weights.py to convert them. It...

If I want to freeze mapping layer and some cnn layers, can you give me some suggestions?

Hi, I saw augpipe option in the train-help.txt. augpipe [blit|geom|color|filter|noise|cutout|bg|bgc|bgcf|bgcfn|bgcfnc] However, what is the detail of blit|geom|color|filter? geom means affine transform? color means color jitter? what is blit and filter?...