stable-diffusion-webui
stable-diffusion-webui copied to clipboard
[Bug]: codeformer - RuntimeError: unexpected EOF, expected X more bytes. The file might be corrupted.
Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits
What happened?
When I select face restoration, the console can see that it is downloading, and then he tells me that it is not the right size?
Steps to reproduce the problem
1.Check face restoration 2.Download codeformer-v0.1.0.pth 3. error
What should have happened?
It should run normally after downloading
Commit where the problem happens
0cc0ee1
What platforms do you use to access the UI ?
Windows
What browsers do you use to access the UI ?
Microsoft Edge
Command Line Arguments
YES
@echo off
set PYTHON=
set GIT=
set VENV_DIR=
set COMMANDLINE_ARGS= --listen
call webui.bat
List of extensions
yes https://github.com/dtlnor/stable-diffusion-webui-localization-zh_CN.git
Console logs
To create a public link, set `share=True` in `launch()`.
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:04<00:00, 4.90it/s]
Downloading: "https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth" to F:\Noviai\newsteble\new\stable-diffusion-webui-master\models\Codeformer\codeformer-v0.1.0.pth
100%|███████████████████████████████████████████████████████████████████████████████| 359M/359M [00:16<00:00, 23.2MB/s]
Error completing request
Arguments: ('task(yap3w3yng0gndcu)', 'AI', '', [], 20, 0, True, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0) {}
Traceback (most recent call last):
File "F:\Noviai\newsteble\new\stable-diffusion-webui-master\modules\call_queue.py", line 56, in f
res = list(func(*args, **kwargs))
File "F:\Noviai\newsteble\new\stable-diffusion-webui-master\modules\call_queue.py", line 37, in f
res = func(*args, **kwargs)
File "F:\Noviai\newsteble\new\stable-diffusion-webui-master\modules\txt2img.py", line 56, in txt2img
processed = process_images(p)
File "F:\Noviai\newsteble\new\stable-diffusion-webui-master\modules\processing.py", line 486, in process_images
res = process_images_inner(p)
File "F:\Noviai\newsteble\new\stable-diffusion-webui-master\modules\processing.py", line 661, in process_images_inner
x_sample = modules.face_restoration.restore_faces(x_sample)
File "F:\Noviai\newsteble\new\stable-diffusion-webui-master\modules\face_restoration.py", line 19, in restore_faces
return face_restorer.restore(np_image)
File "F:\Noviai\newsteble\new\stable-diffusion-webui-master\modules\codeformer_model.py", line 88, in restore
self.create_models()
File "F:\Noviai\newsteble\new\stable-diffusion-webui-master\modules\codeformer_model.py", line 71, in create_models
face_helper = FaceRestoreHelper(1, face_size=512, crop_ratio=(1, 1), det_model='retinaface_resnet50', save_ext='png', use_parse=True, device=devices.device_codeformer)
File "F:\Noviai\newsteble\new\stable-diffusion-webui-master\repositories\CodeFormer\facelib\utils\face_restoration_helper.py", line 105, in __init__
self.face_det = init_detection_model(det_model, half=False, device=self.device)
File "F:\Noviai\newsteble\new\stable-diffusion-webui-master\repositories\CodeFormer\facelib\detection\__init__.py", line 16, in init_detection_model
model = init_retinaface_model(model_name, half, device)
File "F:\Noviai\newsteble\new\stable-diffusion-webui-master\repositories\CodeFormer\facelib\detection\__init__.py", line 36, in init_retinaface_model
load_net = torch.load(model_path, map_location=lambda storage, loc: storage)
File "F:\Noviai\newsteble\new\stable-diffusion-webui-master\modules\safe.py", line 106, in load
return load_with_extra(filename, extra_handler=global_extra_handler, *args, **kwargs)
File "F:\Noviai\newsteble\new\stable-diffusion-webui-master\modules\safe.py", line 151, in load_with_extra
return unsafe_torch_load(filename, *args, **kwargs)
File "F:\Noviai\newsteble\new\stable-diffusion-webui-master\venv\lib\site-packages\torch\serialization.py", line 795, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "F:\Noviai\newsteble\new\stable-diffusion-webui-master\venv\lib\site-packages\torch\serialization.py", line 1020, in _legacy_load
typed_storage._storage._set_from_file(
RuntimeError: unexpected EOF, expected 375406 more bytes. The file might be corrupted.
Additional information
No response
+1 same bug occured
+1
https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/4951
set COMMANDLINE_ARGS= --xformers, 也出现同样的错误
stable-diffusion-webui\repositories\CodeFormer\weights\facelib File directory under detection_Resnet50_Final.pth Error, suggest retry
#4951
It works! I find my parsing_parsenet.pth at "stable-diffusion-webui\repositories\CodeFormer\weights\facelib" is only 12.5MB, and it should be 81.3MB. I guess the connection was dropped while downloading the file through e.g. a VPN.
delect stable-diffusion-webui/models/GFPGAN mkdir stable-diffusion-webui/models/GFPGAN
run
Thanks @pangzheng , thats worked for me!
Same mistake
delect stable-diffusion-webui/models/GFPGAN mkdir stable-diffusion-webui/models/GFPGAN
run
it works. but why??