引言
虽然量化不适用于常规 UNET 模型 (conv2d)，但 flux 等 transformer/DiT 模型似乎受量化的影响较小。这允许在低端 GPU 上以量化的方式运行它。近期GGUF 量化支持原生 ComfyUI 和FLUX模型。
模型链接：
https://modelscope.cn/models/AI-ModelScope/FLUX.1-dev-gguf
ComfyUI代码链接：
https://github.com/city96/ComfyUI-GGUF
因为FLUX对显卡有较高的要求，DashScope也推出了FLUX-API，支持中文输入，免费大碗，对于初体验FLUX的用户，也非常方便。
API文档链接：
https://help.aliyun.com/zh/dashscope/developer-reference/flux-apis
ComfyUI代码链接：
https://github.com/modelscope/comfyscope/
魔搭创空间：
https://modelscope.cn/studios/AI-ModelScope/flux
基于ComfyUI的FLUX最佳实践
除了在魔搭创空间上直接体验之外，这里我们提供基于ComfyUI的FLUX-GGUF模型和FLUX-API上手使用体验。ComfyUI是一个功能强大、模块化程度高的AIGC图形和视频生成的用户界面和后台。本文使用ComfyUI，在魔搭社区提供的免费GPU Notebook上，体验FLUX模型的使用：
下载和部署ComfyUI
clone代码，并安装相关依赖：
#@title Environment Setup from pathlib import Path OPTIONS = {} UPDATE_COMFY_UI = True #@param {type:"boolean"} INSTALL_COMFYUI_MANAGER = True #@param {type:"boolean"} INSTALL_CUSTOM_NODES_DEPENDENCIES = True #@param {type:"boolean"} INSTALL_FLUX = True INSTALL_FLUX_API = True #@param {type:"boolean"} OPTIONS['UPDATE_COMFY_UI'] = UPDATE_COMFY_UI OPTIONS['INSTALL_COMFYUI_MANAGER'] = INSTALL_COMFYUI_MANAGER OPTIONS['INSTALL_FLUX'] = INSTALL_FLUX OPTIONS['INSTALL_FLUX_API'] = INSTALL_FLUX_API OPTIONS['INSTALL_CUSTOM_NODES_DEPENDENCIES'] = INSTALL_CUSTOM_NODES_DEPENDENCIES current_dir = !pwd WORKSPACE = f"{current_dir[0]}/ComfyUI" !pip install --upgrade gguf %cd /mnt/workspace/ ![ ! -d $WORKSPACE ] && echo -= Initial setup ComfyUI =- && git clone https://github.com/comfyanonymous/ComfyUI %cd $WORKSPACE if OPTIONS['UPDATE_COMFY_UI']: !echo "-= Updating ComfyUI =-" !git pull # 安装FLUX-GGUF node if OPTIONS['INSTALL_FLUX']: %cd custom_nodes !echo -= Initial setup FLUX =- && git clone https://github.com/city96/ComfyUI-GGUF if OPTIONS['INSTALL_COMFYUI_MANAGER']: ![ ! -d ComfyUI-Manager ] && echo -= Initial setup ComfyUI-Manager =- && git clone https://github.com/ltdrdata/ComfyUI-Manager %cd ComfyUI-Manager !git pull # 安装FLUX-API node if OPTIONS['INSTALL_FLUX_API']: %cd ../ ![ ! -d comfy-flux ] && echo -= Initial setup dashscope_api =- && git clone https://github.com/modelscope/comfyscope.git %cd comfy-flux !git pull %cd $WORKSPACE if OPTIONS['INSTALL_CUSTOM_NODES_DEPENDENCIES']: !pwd !echo "-= Install custom nodes dependencies =-" ![ -f "custom_nodes/ComfyUI-Manager/scripts/colab-dependencies.py" ] && python "custom_nodes/ComfyUI-Manager/scripts/colab-dependencies.py"
模型下载
#@markdown ###Download standard resources %cd /mnt/workspace/ComfyUI ### FLUX1-DEV !modelscope download --model=AI-ModelScope/FLUX.1-dev-gguf --local_dir ./models/unet/ flux1-dev-Q5_1.gguf ### clip !modelscope download --model=AI-ModelScope/flux_text_encoders --local_dir ./models/clip/ t5xxl_fp16.safetensors !modelscope download --model=AI-ModelScope/flux_text_encoders --local_dir ./models/clip/ clip_l.safetensors !modelscope download --model=AI-ModelScope/flux_text_encoders --local_dir ./models/clip/ t5xxl_fp8_e4m3fn.safetensors ### vae !modelscope download --model=AI-ModelScope/FLUX.1-dev --local_dir ./models/vae/ ae.safetensors
使用cloudflared运行ComfyUI
!wget "https://modelscope.oss-cn-beijing.aliyuncs.com/resource/cloudflared-linux-amd64.deb" !dpkg -i cloudflared-linux-amd64.deb %cd /mnt/workspace/ComfyUI import subprocess import threading import time import socket import urllib.request def iframe_thread(port): while True: time.sleep(0.5) sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM) result = sock.connect_ex(('127.0.0.1', port)) if result == 0: break sock.close() print("\nComfyUI finished loading, trying to launch cloudflared (if it gets stuck here cloudflared is having issues)\n") p = subprocess.Popen(["cloudflared", "tunnel", "--url", "http://127.0.0.1:{}".format(port)], stdout=subprocess.PIPE, stderr=subprocess.PIPE) for line in p.stderr: l = line.decode() if "trycloudflare.com " in l: print("This is the URL to access ComfyUI:", l[l.find("http"):], end='') #print(l, end='') threading.Thread(target=iframe_thread, daemon=True, args=(8188,)).start() !python main.py --dont-print-server
load流程图
flux1-dev流程图:
https://modelscope.oss-cn-beijing.aliyuncs.com/resource/example_gguf_workflow.json
flux1 dashscope api 流程图：
https://github.com/modelscope/comfyscope/blob/main/workflow_examples/dashscope_flux.json 
点击链接👇直达创空间体验
https://www.modelscope.cn/studios/AI-ModelScope/flux?from=alizishequ__text
