【人脸清晰工具】codeformer新支持40系显卡20240114

chiiren

感谢大佬分享

paco90

非常好用，速度很快，效果很好，修普通照片也可以，感觉之前用美团秀秀一张一张看广告来修真是大冤种

stonebark

谢谢分享！

滚石

windjet 发表于 2023-1-23 23:10
嗯，谢谢大佬解答，不解压到dfl是不影响dfl的使用的，但这里没有使用说明，不知道这个codeformer图形界面 ...

没有依赖dfl代码，用到的部分都单独拿出来了

滚石

mature50 发表于 2023-1-26 00:05
請問一下下載codeformer人臉清晰化神器新手包，好像都不能用，流程也對，只顯示正在运行，运行日志只顯示開 ...

用纯英文路径试试

Juventus

感谢大佬分享

lweny

感谢推荐，已下载

cdf2dfl

威货....

hujiaxv

之前还用的好好的，今天使用就提示这个：

开始处理...
Face detection model: retinaface_resnet50
[1/1] 正在处理: IMG_20230206_110041.jpg
Traceback (most recent call last):
  File "CodeFormer/inference_codeformer.py", line 209, in <module>
    only_center_face=args.only_center_face, resize=640, eye_dist_threshold=5)
  File "D:\codeface\_internal\CodeFormer\facelib\utils\face_restoration_helper.py", line 154, in get_face_landmarks_5
    bboxes = self.face_det.detect_faces(input_img)
  File "D:\codeface\_internal\CodeFormer\facelib\detection\retinaface\retinaface.py", line 209, in detect_faces
    loc, conf, landmarks, priors = self.__detect_faces(image)
  File "D:\codeface\_internal\CodeFormer\facelib\detection\retinaface\retinaface.py", line 156, in __detect_faces
    loc, conf, landmarks = self(inputs)
  File "D:\codeface\_internal\Python37\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl
    return forward_call(*input, **kwargs)
  File "D:\codeface\_internal\CodeFormer\facelib\detection\retinaface\retinaface.py", line 121, in forward
    out = self.body(inputs)
  File "D:\codeface\_internal\Python37\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl
    return forward_call(*input, **kwargs)
  File "D:\codeface\_internal\Python37\lib\site-packages\torchvision\models\_utils.py", line 62, in forward
    x = module(x)
  File "D:\codeface\_internal\Python37\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl
    return forward_call(*input, **kwargs)
  File "D:\codeface\_internal\Python37\lib\site-packages\torch\nn\modules\container.py", line 139, in forward
    input = module(input)
  File "D:\codeface\_internal\Python37\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl
    return forward_call(*input, **kwargs)
  File "D:\codeface\_internal\Python37\lib\site-packages\torchvision\models\resnet.py", line 136, in forward
    identity = self.downsample(x)
  File "D:\codeface\_internal\Python37\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl
    return forward_call(*input, **kwargs)
  File "D:\codeface\_internal\Python37\lib\site-packages\torch\nn\modules\container.py", line 139, in forward
    input = module(input)
  File "D:\codeface\_internal\Python37\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl
    return forward_call(*input, **kwargs)
  File "D:\codeface\_internal\Python37\lib\site-packages\torch\nn\modules\batchnorm.py", line 178, in forward
    self.eps,
  File "D:\codeface\_internal\Python37\lib\site-packages\torch\nn\functional.py", line 2282, in batch_norm
    input, weight, bias, running_mean, running_var, training, momentum, eps, torch.backends.cudnn.enabled
RuntimeError: CUDA out of memory. Tried to allocate 360.00 MiB (GPU 0; 2.00 GiB total capacity; 1.43 GiB already allocated; 0 bytes free; 1.70 GiB reserved in total by PyTorch)

有哪位大佬知道怎么解决吗？

jpjpq

支持这样神器