PytorchStreamReader failed reading file data/567: invalid header or archive is corrupted

[eformx]

When I hit generate I get that error message. Win 10 pro 32gb ram, gtx 1050 ti 4gb vram (works for deforum and other SD extensions). I put a print statement to make sure the paths are correct, downloaded half weights from hugging face via the download arrow. I pip installed modelscope and have the scripts to run this in the correct folder. Is there a solution to this?

ModelScope text2video extension for auto1111 webui
Git commit: Unknown
Starting text2video
Pipeline setup
model_dir
D:\sites\stable-diffusion-webui\models/ModelScope/t2v
config namespace(framework='pytorch', task='text-to-video-synthesis', model={'type': 'latent-text-to-video-synthesis', 'model_args': {'ckpt_clip': 'open_clip_pytorch_model.bin', 'ckpt_
unet': 'text2video_pytorch_model.pth', 'ckpt_autoencoder': 'VQGAN_autoencoder.pth', 'max_frames': 16, 'tiny_gpu': 1}, 'model_cfg': {'unet_in_dim': 4, 'unet_dim': 320, 'unet_y_dim': 768
, 'unet_context_dim': 1024, 'unet_out_dim': 4, 'unet_dim_mult': [1, 2, 4, 4], 'unet_num_heads': 8, 'unet_head_dim': 64, 'unet_res_blocks': 2, 'unet_attn_scales': [1, 0.5, 0.25], 'unet_
dropout': 0.1, 'temporal_attention': 'True', 'num_timesteps': 1000, 'mean_type': 'eps', 'var_type': 'fixed_small', 'loss_type': 'mse'}}, pipeline={'type': 'latent-text-to-video-synthes
is'})
path...
D:\sites\stable-diffusion-webui\models/ModelScope/t2v\VQGAN_autoencoder.pth
Traceback (most recent call last):
File "D:\sites\stable-diffusion-webui\scripts\modelscope-text2vid.py", line 74, in process
pipe = setup_pipeline()
File "D:\sites\stable-diffusion-webui\scripts\modelscope-text2vid.py", line 30, in setup_pipeline
return TextToVideoSynthesis(ph.models_path+'/ModelScope/t2v')
File "D:\sites\stable-diffusion-webui\scripts\t2v_pipeline.py", line 141, in init
self.autoencoder = AutoencoderKL(
File "D:\sites\stable-diffusion-webui\scripts\t2v_model.py", line 1557, in init
self.init_from_ckpt(ckpt_path)
File "D:\sites\stable-diffusion-webui\scripts\t2v_model.py", line 1562, in init_from_ckpt
sd = torch.load(path, map_location='cpu')['state_dict']
File "D:\sites\stable-diffusion-webui\modules\safe.py", line 106, in load
return load_with_extra(filename, extra_handler=global_extra_handler, *args, **kwargs)
File "D:\sites\stable-diffusion-webui\modules\safe.py", line 151, in load_with_extra
return unsafe_torch_load(filename, *args, **kwargs)
File "C:\Users\eform\anaconda3\lib\site-packages\torch\serialization.py", line 789, in load
return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
File "C:\Users\eform\anaconda3\lib\site-packages\torch\serialization.py", line 1131, in _load
result = unpickler.load()
File "C:\Users\eform\anaconda3\lib\site-packages\torch\serialization.py", line 1101, in persistent_load
load_tensor(dtype, nbytes, key, _maybe_decode_ascii(location))
File "C:\Users\eform\anaconda3\lib\site-packages\torch\serialization.py", line 1079, in load_tensor
storage = zip_file.get_storage_from_record(name, numel, torch.UntypedStorage).storage().untyped()
RuntimeError: PytorchStreamReader failed reading file data/567: invalid header or archive is corrupted
Exception occurred: PytorchStreamReader failed reading file data/567: invalid header or archive is corrupted

[kabachuha]

Well, most like it's corrupted then. Try deleting the files and redownloading them. If it won't help, compare the checksums first

[eformx]

Did. My machine says the checksum for open_clip... is e707fa0435b56d48ca416ae6ded5fc7e Is this correct? Where are the checksums for the files in hugging face?

[spiritform]

i get the same error... did you figure it out?