FaceFusion版本更新到了2.6.0，下面是安装的一些tips。

安装Conda

---

FaceFusion舍弃了python 虚拟环境，用了Conda。

curl -LO https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh

bash Miniconda3-latest-Linux-x86_64.sh

初始化Conda环境

---

conda init --all

conda create --name facefusion python=3.10

conda activate facefusion

下载代码

---

git clone https://github.com/facefusion/facefusion

cd facefusion

修改requirements.txt，因为我的Centos环境 onnxruntime只能安装到1.16.3

filetype==1.2.0
gradio==3.50.2
numpy==1.26.2
onnx==1.15.0
onnxruntime==1.16.3
opencv-python==4.9.0.80
psutil==5.9.6
tqdm==4.66.1
scipy==1.13.0

修改 facefusion/installer.py

from typing import Dict, Tuple
import sys
import os
import tempfile
import subprocess
import inquirer
from argparse import ArgumentParser, HelpFormatter

from facefusion import metadata, wording
from facefusion.common_helper import is_linux, is_macos, is_windows

if is_macos():
	os.environ['SYSTEM_VERSION_COMPAT'] = '0'

ONNXRUNTIMES : Dict[str, Tuple[str, str]] = {}

if is_macos():
	ONNXRUNTIMES['default'] = ('onnxruntime', '1.16.3')
else:
	ONNXRUNTIMES['default'] = ('onnxruntime', '1.16.3')
	ONNXRUNTIMES['cuda-12.2'] = ('onnxruntime-gpu', '1.17.1')
	ONNXRUNTIMES['cuda-11.8'] = ('onnxruntime-gpu', '1.17.1')
	ONNXRUNTIMES['openvino'] = ('onnxruntime-openvino', '1.15.0')
if is_linux():
	ONNXRUNTIMES['rocm-5.4.2'] = ('onnxruntime-rocm', '1.16.3')
	ONNXRUNTIMES['rocm-5.6'] = ('onnxruntime-rocm', '1.16.3')
if is_windows():
	ONNXRUNTIMES['directml'] = ('onnxruntime-directml', '1.16.3')


def cli() -> None:
	program = ArgumentParser(formatter_class = lambda prog: HelpFormatter(prog, max_help_position = 200))
	program.add_argument('--onnxruntime', help = wording.get('help.install_dependency').format(dependency = 'onnxruntime'), choices = ONNXRUNTIMES.keys())
	program.add_argument('--skip-conda', help = wording.get('help.skip_conda'), action = 'store_true')
	program.add_argument('-v', '--version', version = metadata.get('name') + ' ' + metadata.get('version'), action = 'version')
	run(program)


def run(program : ArgumentParser) -> None:
	args = program.parse_args()
	python_id = 'cp' + str(sys.version_info.major) + str(sys.version_info.minor)

	if not args.skip_conda and 'CONDA_PREFIX' not in os.environ:
		sys.stdout.write(wording.get('conda_not_activated') + os.linesep)
		sys.exit(1)
	if args.onnxruntime:
		answers =\
		{
			'onnxruntime': args.onnxruntime
		}
	else:
		answers = inquirer.prompt(
		[
			inquirer.List('onnxruntime', message = wording.get('help.install_dependency').format(dependency = 'onnxruntime'), choices = list(ONNXRUNTIMES.keys()))
		])
	if answers:
		onnxruntime = answers['onnxruntime']
		onnxruntime_name, onnxruntime_version = ONNXRUNTIMES[onnxruntime]

		subprocess.call([ 'pip', 'install', '-r', 'requirements.txt', '--force-reinstall' ])
		if onnxruntime == 'rocm-5.4.2' or onnxruntime == 'rocm-5.6':
			if python_id in [ 'cp39', 'cp310', 'cp311' ]:
				rocm_version = onnxruntime.replace('-', '')
				rocm_version = rocm_version.replace('.', '')
				wheel_name = 'onnxruntime_training-' + onnxruntime_version + '+' + rocm_version + '-' + python_id + '-' + python_id + '-manylinux_2_17_x86_64.manylinux2014_x86_64.whl'
				wheel_path = os.path.join(tempfile.gettempdir(), wheel_name)
				wheel_url = 'https://download.onnxruntime.ai/' + wheel_name
				subprocess.call([ 'curl', '--silent', '--location', '--continue-at', '-', '--output', wheel_path, wheel_url ])
				subprocess.call([ 'pip', 'uninstall', wheel_path, '-y', '-q' ])
				subprocess.call([ 'pip', 'install', wheel_path, '--force-reinstall' ])
				os.remove(wheel_path)
		else:
			subprocess.call([ 'pip', 'uninstall', 'onnxruntime', onnxruntime_name, '-y', '-q' ])
			if onnxruntime == 'cuda-12.2':
				subprocess.call([ 'pip', 'install', onnxruntime_name + '==' + onnxruntime_version, '--extra-index-url', 'https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-12/pypi/simple', '--force-reinstall' ])
			else:
				subprocess.call([ 'pip', 'install', onnxruntime_name + '==' + onnxruntime_version, '--force-reinstall' ])

安装依赖

---

python install.py

python run.py

更新模型（重要）

---

因为用了Conda，模型也更新了

https://github.com/facefusion/facefusion-assets

比如换脸模型inswapper_128_fp16.onnx， 别看名字一样，其实内容已经发生了变化，需要从网站下载，并且更新到/mnt/facefusion/.assets 中。

启动Gradio内网穿透

---

Gradio是一个用于创建机器学习模型交互式界面的Python库。通过Gradio，你可以为你的模型快速构建一个可视化的、易于使用的Web界面，无需编写任何前端代码。我们将通过Gradio将内网端口7860映射到公网上。

在facefusion/uis/layouts/目录下新建文件share.py

import gradio

from facefusion.uis.layouts import default


def pre_check() -> bool:
    return default.pre_check()


def pre_render() -> bool:
    return default.pre_render()


def render() -> gradio.Blocks:
    return default.render()


def listen() -> None:
    default.listen()


def run(ui : gradio.Blocks) -> None:
    ui.launch(show_api = False, share = True)

返回到facefusion目录下，重新启动run.py

python run.py --ui-layouts share

完成后，你会看到以下信息：

Running on local URL: http://127.0.0.1:7860
Running on public URL: https://e41b4898c4fad7cc83.gradio.live

This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)

现在，你可以通过你的独特的URL连接访问Facefusion界面。