Facefusion ( Local )

4 месеца ago
tasko1
2 minutes
First working test environment
OS : Windows 11 Pro Build 26220 10.0.26220
GPU: RTX 4060m
CPU: i5-13500H
A) On Widnows Cmd (win+R => cmd)
01. winget install -e –id Git.Git
02. winget install -e –id Anaconda.Miniconda3 –version py312_25.1.1-2 –override „/AddToPath=1“
03. winget install -e –id Gyan.FFmpeg –version 7.0.2
B) Change conda env folder
   – copy file .condarc to C:\Users\<user name>\ or create in manual with folling structure
envs_dirs:
  – E:\Programs\Conda\env
pkgs_dirs:
  – E:\Programs\Conda\cache
C) On Anaconda Promt (under admin rights)
01. conda create –name facefusion python=3.12 pip=25.0
02. conda activate facefusion
03. conda install nvidia/label/cuda-12.9.1::cuda-runtime nvidia/label/cudnn-9.10.0::cudnn
04. E:/
05. cd Programs
06. Unzip facefusion-master.zip to E:\Programs or use git to download fresh copy
    – git clone https://github.com/facefusion/facefusion
07. cd facefusion
08. Copy file requirements.txt to E:\Programs\facefusion\ or edit manual
   – remove all on E:\Programs\facefusion\requirements.txt and add following and save it :
gradio-rangeslider==0.0.8
gradio==5.42.0
numpy==2.1.0
onnx==1.19.0
onnxruntime==1.23.2
onnxruntime-gpu==1.23.2
opencv-python==4.11.0.86
psutil==7.1.3
tqdm==4.67.1
scipy==1.16.3
09. Copy file installer.py to E:\Programs\facefusion\facefusion or edit manual
    – Edit following E:\Programs\facefusion\facefusion\installer.py
     – search for : with open(‘requirements.txt’, ‘r’) as file:
     – replace it with : with open(‘requirements.txt’, ‘r’, encoding=’utf-8′) as file:
10. For test if all ok can be run or direct go to 11.
    – pip install -r requirements.txt
11. python install.py –onnxruntime cuda
    – if there some error run :
– conda deactivate
  – conda activate facefusion
12. python facefusion.py run –open-browser