Installation procedure:
If you have a powerful display card, first install CUDA 11.7 (since
PyTorch only support up to CUDA 11.7) then follow the installation sequence:
1. Python, during installation enable path.
2. Anaconda
3. PyTorch (install under Anaconda prompt)
https://pytorch.org/get-started/locally/
4. Dependencies Installation, follow the procedure in:
https://github.com/sczhou/CodeFormer
Under Anaconda prompt:
CD Codeformer
The you can start to play with the program by execute:
python inference_codeformer.py -w 0.7 -s 2 --bg_upsampler realesrgan
--input_path D:\Codeformer\input --output_path D:\Codeformer\output
(the above command will also install realesrgan when you run it the
first time, which is for background processing, it do quite well in
image enlargement)
-w is fidelity weight "0 to 1"
-s is image enlargement "1,2,3,4.." default 2
input/output path suit yourself.
The procedure is a little complicated, I hope I haven't miss anything.
C.H.Ling
On 31/1/2023 13:21, Moose wrote:
Pretty impressive!
So . .
install Python
download code from Github
run Python on code to
runtime?
executable?
Does that do it?
Ex Coder Moose
--
_________________________________________________________________
Options: http://lists.thomasclausen.net/mailman/listinfo/olympus
Archives: http://lists.thomasclausen.net/mailman/private/olympus/
Themed Olympus Photo Exhibition: http://www.tope.nl/
|