Error with Face Restoration GFPGAN

[a3nima]

Hi lately I came accross this error, image generation works until the point face restoration would set in. It seems it worked in between the last week and then startet to not work again (or it's sometimes working for an unknown reason). Here's what s in the terminal:

Traceback (most recent call last): File "E:\SD\stable-diffusion-webui\modules\call_queue.py", line 56, in f res = list(func(*args, **kwargs)) File "E:\SD\stable-diffusion-webui\modules\call_queue.py", line 37, in f res = func(*args, **kwargs) File "E:\SD\stable-diffusion-webui\modules\txt2img.py", line 56, in txt2img processed = process_images(p) File "E:\SD\stable-diffusion-webui\modules\processing.py", line 486, in process_images res = process_images_inner(p) File "E:\SD\stable-diffusion-webui\modules\processing.py", line 657, in process_images_inner x_sample = modules.face_restoration.restore_faces(x_sample) File "E:\SD\stable-diffusion-webui\modules\face_restoration.py", line 19, in restore_faces return face_restorer.restore(np_image) File "E:\SD\stable-diffusion-webui\modules\gfpgan_model.py", line 111, in restore return gfpgan_fix_faces(np_image) File "E:\SD\stable-diffusion-webui\modules\gfpgan_model.py", line 53, in gfpgan_fix_faces model = gfpgann() File "E:\SD\stable-diffusion-webui\modules\gfpgan_model.py", line 40, in gfpgann model = gfpgan_constructor(model_path=model_file, upscale=1, arch='clean', channel_multiplier=2, bg_upsampler=None, device=devices.device_gfpgan) File "e:\SD\stable-diffusion-webui\venv\lib\site-packages\gfpgan\utils.py", line 92, in __init__ loadnet = torch.load(model_path) File "e:\SD\stable-diffusion-webui\modules\safe.py", line 106, in load return load_with_extra(filename, extra_handler=global_extra_handler, *args, **kwargs) File "e:\SD\stable-diffusion-webui\modules\safe.py", line 151, in load_with_extra return unsafe_torch_load(filename, *args, **kwargs) File "e:\SD\stable-diffusion-webui\venv\lib\site-packages\torch\serialization.py", line 795, in load return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args) File "e:\SD\stable-diffusion-webui\venv\lib\site-packages\torch\serialization.py", line 1020, in _legacy_load typed_storage._storage._set_from_file( RuntimeError: unexpected EOF, expected 1567018 more bytes. The file might be corrupted.

[a3nima]

ok i deleted everything in the models gfpgan folder and with the automatically downloaded new files the problem dissappeared! (old files were from feb 1st).