nerdyrodent / VQGAN-CLIP

Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.
Other
2.59k stars 428 forks source link

RuntimeError: PytorchStreamReader #149

Closed Nyexaas closed 2 years ago

Nyexaas commented 2 years ago

Hello, after fix few errors by myself i tryed to do a test but an error happen and i can't fix the last one here is the error :

(vqgan) C:\Users\Nyexa\VQGAN-CLIP>python generate.py -p "Black art cathedral" Working with z of shape (1, 256, 16, 16) = 65536 dimensions. loaded pretrained LPIPS loss from taming/modules/autoencoder/lpips\vgg.pth VQLPIPSWithDiscriminator running with hinge loss. Traceback (most recent call last): File "C:\Users\Nyexa\VQGAN-CLIP\generate.py", line 546, in model = load_vqgan_model(args.vqgan_config, args.vqgan_checkpoint).to(device) File "C:\Users\Nyexa\VQGAN-CLIP\generate.py", line 520, in load_vqgan_model model.init_from_ckpt(checkpoint_path) File "C:\Users\Nyexa\VQGAN-CLIP\taming-transformers\taming\models\vqgan.py", line 45, in init_from_ckpt sd = torch.load(path, map_location="cpu")["state_dict"] File "C:\Users\Nyexa\anaconda3\envs\vqgan\lib\site-packages\torch\serialization.py", line 600, in load with _open_zipfile_reader(opened_file) as opened_zipfile: File "C:\Users\Nyexa\anaconda3\envs\vqgan\lib\site-packages\torch\serialization.py", line 242, in init super(_open_zipfile_reader, self).init(torch._C.PyTorchFileReader(name_or_buffer)) RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

Nyexaas commented 2 years ago

I found a solution, i downloaded everything again and also after write : cd VQGAN-CLIP