【人脸图清晰化神器】GFPGAN_GPEN_CodeFormer 3合1人像增强工具集

BENZUNYH

感谢分享

EineKleine

感谢大佬分享

lll133133

感谢分享

lll133133

感谢分享

haiou_f

楼主，用gpen时出现这个提示怎么解决，gfpgan能用
当前运行GPEN增强
初始化中...如长时间未响应，请清理缓存
Traceback (most recent call last):
  File "G:\Program Files\GPEN_GFPGAN_Windows\_internal\Python37\lib\site-packages\torch\utils\cpp_extension.py", line 1672, in _run_ninja_build
    env=env)
  File "G:\Program Files\GPEN_GFPGAN_Windows\_internal\Python37\lib\subprocess.py", line 512, in run
    output=stdout, stderr=stderr)
subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "face_enhancement.py", line 17, in <module>
    from face_model.face_gan import FaceGAN
  File "G:\Program Files\GPEN_GFPGAN_Windows\GPEN\face_model\face_gan.py", line 13, in <module>
    from gpen_model import FullGenerator
  File "G:\Program Files\GPEN_GFPGAN_Windows\GPEN\face_model\gpen_model.py", line 16, in <module>
    from op import FusedLeakyReLU, fused_leaky_relu, upfirdn2d
  File "G:\Program Files\GPEN_GFPGAN_Windows\GPEN\face_model\op\__init__.py", line 1, in <module>
    from .fused_act import FusedLeakyReLU, fused_leaky_relu
  File "G:\Program Files\GPEN_GFPGAN_Windows\GPEN\face_model\op\fused_act.py", line 16, in <module>
    os.path.join(module_path, 'fused_bias_act_kernel.cu'),
  File "G:\Program Files\GPEN_GFPGAN_Windows\_internal\Python37\lib\site-packages\torch\utils\cpp_extension.py", line 1092, in load
    keep_intermediates=keep_intermediates)
  File "G:\Program Files\GPEN_GFPGAN_Windows\_internal\Python37\lib\site-packages\torch\utils\cpp_extension.py", line 1303, in _jit_compile
    is_standalone=is_standalone)
  File "G:\Program Files\GPEN_GFPGAN_Windows\_internal\Python37\lib\site-packages\torch\utils\cpp_extension.py", line 1408, in _write_ninja_file_and_build_library
    error_prefix=f"Error building extension '{name}'")
  File "G:\Program Files\GPEN_GFPGAN_Windows\_internal\Python37\lib\site-packages\torch\utils\cpp_extension.py", line 1682, in _run_ninja_build
    raise RuntimeError(message) from e
RuntimeError: Error building extension 'fused': [1/2] G:\Program Files\GPEN_GFPGAN_Windows\_internal\CUDA\bin\nvcc --generate-dependencies-with-compile --dependency-output fused_bias_act_kernel.cuda.o.d -Xcudafe --diag_suppress=dll_interface_conflict_dllexport_assumed -Xcudafe --diag_suppress=dll_interface_conflict_none_assumed -Xcudafe --diag_suppress=field_without_dll_interface -Xcudafe --diag_suppress=base_class_has_different_dll_interface -Xcompiler /EHsc -Xcompiler /wd4190 -Xcompiler /wd4018 -Xcompiler /wd4275 -Xcompiler /wd4267 -Xcompiler /wd4244 -Xcompiler /wd4251 -Xcompiler /wd4819 -Xcompiler /MD -DTORCH_EXTENSION_NAME=fused -DTORCH_API_INCLUDE_EXTENSION_H "-IG:\Program Files\GPEN_GFPGAN_Windows\_internal\Python37\lib\site-packages\torch\include" "-IG:\Program Files\GPEN_GFPGAN_Windows\_internal\Python37\lib\site-packages\torch\include\torch\csrc\api\include" "-IG:\Program Files\GPEN_GFPGAN_Windows\_internal\Python37\lib\site-packages\torch\include\TH" "-IG:\Program Files\GPEN_GFPGAN_Windows\_internal\Python37\lib\site-packages\torch\include\THC" "-IG:\Program Files\GPEN_GFPGAN_Windows\_internal\CUDA\include" "-IG:\Program Files\GPEN_GFPGAN_Windows\_internal\Python37\Include" -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_61,code=compute_61 -gencode=arch=compute_61,code=sm_61 -c "G:\Program Files\GPEN_GFPGAN_Windows\GPEN\face_model\op\fused_bias_act_kernel.cu" -o fused_bias_act_kernel.cuda.o

FAILED: fused_bias_act_kernel.cuda.o

G:\Program Files\GPEN_GFPGAN_Windows\_internal\CUDA\bin\nvcc --generate-dependencies-with-compile --dependency-output fused_bias_act_kernel.cuda.o.d -Xcudafe --diag_suppress=dll_interface_conflict_dllexport_assumed -Xcudafe --diag_suppress=dll_interface_conflict_none_assumed -Xcudafe --diag_suppress=field_without_dll_interface -Xcudafe --diag_suppress=base_class_has_different_dll_interface -Xcompiler /EHsc -Xcompiler /wd4190 -Xcompiler /wd4018 -Xcompiler /wd4275 -Xcompiler /wd4267 -Xcompiler /wd4244 -Xcompiler /wd4251 -Xcompiler /wd4819 -Xcompiler /MD -DTORCH_EXTENSION_NAME=fused -DTORCH_API_INCLUDE_EXTENSION_H "-IG:\Program Files\GPEN_GFPGAN_Windows\_internal\Python37\lib\site-packages\torch\include" "-IG:\Program Files\GPEN_GFPGAN_Windows\_internal\Python37\lib\site-packages\torch\include\torch\csrc\api\include" "-IG:\Program Files\GPEN_GFPGAN_Windows\_internal\Python37\lib\site-packages\torch\include\TH" "-IG:\Program Files\GPEN_GFPGAN_Windows\_internal\Python37\lib\site-packages\torch\include\THC" "-IG:\Program Files\GPEN_GFPGAN_Windows\_internal\CUDA\include" "-IG:\Program Files\GPEN_GFPGAN_Windows\_internal\Python37\Include" -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_61,code=compute_61 -gencode=arch=compute_61,code=sm_61 -c "G:\Program Files\GPEN_GFPGAN_Windows\GPEN\face_model\op\fused_bias_act_kernel.cu" -o fused_bias_act_kernel.cuda.o

nvcc fatal   : Could not set up the environment for Microsoft Visual Studio using 'G:/Program Files/GPEN_GFPGAN_Windows/_internal/Microsoft Visual Studio/2019/Community/VC/Tools/MSVC/14.29.30133/bin/Hostx64/x64/../../../../../../../VC/Auxiliary/Build/vcvars64.bat'

ninja: build stopped: subcommand failed.

haiou_f

另外把那个滚石优化版文件覆盖依然提示出错
提示：
当前运行GPEN增强
初始化中...如长时间未响应，请清理缓存
Traceback (most recent call last):
  File "face_enhancement.py", line 13, in <module>
    from retinaface.retinaface_detection import RetinaFaceDetection
ModuleNotFoundError: No module named 'retinaface'

fktz008

谢谢，学习了

wceo

感谢分享

mayi666

自己研究半天搞不定，还是直接站在大佬肩膀上安逸