GFPGAN

GFPGAN copied to clipboard

Model GFPGANv1.3 does not exist

3

I am trying to use GFPGAN but it says the model doesn't exist and I downloaded the model

Abelmarumo

How to run GFPGANv1.pth (paper model with colorization) on CPU or non-nVidia GPUs?

2

I suspect it might not be an easy tweak otherwise it'd already be out in github, but wonder which option could be easier, even if it takes a long time...

ullaf

Running on CPU

2

Hi, i am missing option to run inference on cpu. I have low memory on my GPU, so its useless with it. How can i avoid running this on GPU...

bochkarev-artem

ImportError: No module named 'deform_conv'

1

$ BASICSR_JIT=True python inference_gfpgan.py -i inputs/whole_imgs -o results -v 1 -s 2 E:\Anaconda3\lib\site-packages\setuptools\distutils_patch.py:25: UserWarning: Distutils was imported before Setuptools. This usage is discouraged and may exhibit undesirable behaviors or errors....

lj350201364

windows error NameError: name 'fused_act_ext' is not defined

1

E:\AIDeepLearn\旧照片修复\GFPGAN>python inference_gfpgan.py -i inputs/whole_imgs -o results -v 1 -s 2 Processing 2.png ... Traceback (most recent call last): File "inference_gfpgan.py", line 155, in main() File "inference_gfpgan.py", line 119, in main...

lj350201364

Higher resolution pretrained model ?

3

512*512 is generally enough for video, but portrait needs 1024*1024 or 2048*2048.

Michaelwhite34

How can I use gfpgan for video?

8

Hello, how can i use gfpgan for video?

osmankaya

关于增加额外数据训练

1

请问一下，增加额外数据集（FFHQ以外的数据）训练，是否需要先在新数据集上训练或微调stylegan2后，再训练GFPGAN

bondruy

I cant train the model when set BASICSR_JIT == 'True'

1

The error is as following: Traceback (most recent call last): File "/data/zx/miniconda3/envs/D22/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1723, in _run_ninja_build env=env) File "/data/zx/miniconda3/envs/D22/lib/python3.7/subprocess.py", line 512, in run output=stdout, stderr=stderr) subprocess.CalledProcessError: Command '['ninja', '-v']' returned...

1145520074

chore: Run GFPGAN in docker container

8

**Why we need it:** * Maintainers can develop in a container * Potential users can re-train GFPGAN in a containerized environment * Others can try it in an isolated environment...

mmenbawy