DazzleML/comfyui-triton-and-sageattention-installer
Cross-platform installer for Triton and SageAttention on ComfyUI. Simplifies GPU-accelerated inference setup for Windows users with automated dependency management and RTX 5090 support.
This installer helps ComfyUI users on Windows get faster image generation by setting up advanced GPU optimizations like Triton and SageAttention. It takes your existing ComfyUI installation and automatically configures the necessary components, letting you produce high-quality images and videos more quickly. It's designed for anyone using ComfyUI on a Windows PC with an NVIDIA GPU, especially those frustrated with slow performance.
Use this if you are a ComfyUI user on Windows and want to significantly speed up your image and video generation tasks using advanced GPU optimizations.
Not ideal if you are not using ComfyUI, do not have an NVIDIA GPU, or are not running Windows.
Stars
90
Forks
3
Language
Python
License
MIT
Category
Last pushed
Mar 16, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/DazzleML/comfyui-triton-and-sageattention-installer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Comfy-Org/comfy-cli
Command Line Interface for Managing ComfyUI
YanWenKun/ComfyUI-Docker
🐳Dockerfile for 🎨ComfyUI. | 容器镜像与启动脚本
Comfy-Org/ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
runpod-workers/worker-comfyui
ComfyUI as a serverless API on RunPod
Acly/comfyui-tooling-nodes
Nodes for using ComfyUI as a backend for external tools. Send and receive images directly...