Speed Up ComfyUI with Flash Attention (54s → 40s)
🌟 Simple Setup for Flash Attention in Comfy UI 🌟
In this video, I show how to use Flash Attention in ComfyUI to speed up image generation.
On my test workflow, generation time was reduced from 54 seconds to 40 seconds with a simple patch node.
Keep in mind that results depend on the model and workflow you're using. In my testing, Flash Attention did not work with some models such as Wan and Flux Klein, so you'll need to test it with your own setup.
Workflow and node links are included below.
#ComfyUI #FlashAttention #AIImageGeneration #StableDiffusion #Flux
💻 Hardware Used:
(i5 14400F, 64GB RAM, RTX 5060 TI 16GB)
🔍 Resources:
⭐IMP: Update Comfy UI KJ nodes & Restart Comfy UI
🙏 Thanks to "mjun0812" on GitHub for sharing the Flash-Attention Prebuild Wheels:
https://mjunya.com/flash-attention-pr...
👉 Guide to Install Sage Attention
1: • Faster Wan 2.2 - Install Triton + Sage Att...
2: • Update on Triton + Sage Attention Setup fo...
📥 Get Started with Comfy UI: • ComfyUI for Beginner - Part - 1 - Stable D...
Low VRAM - Small GPU? try Nunchaku: • Flux models for smaller GPU – Nunchaku is ...
💬 Drop a comment below!
🔔 Stay Updated: Stay connected to find the latest AI applications!
Happy creating! 🎨✨
Playlist For Comfy UI - Stable Diffusion
• How To Use Comfy UI
Playlist For Krita AI Diffusion
• Krita AI Diffusion
Playlist For Fooocus AI - Stable Diffusion
• Fooocus User Guide - Stable Diffusion AI i...
Playlist for Forge UI
• Forge UI