Skip to content

Latest commit

 

History

19 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ComfyUI-Sage-EasyInstall

Automated installers for SageAttention on Windows for ComfyUI portable.

SageAttention accelerates AI video generation significantly. If you're using models like WAN in ComfyUI, SageAttention can make your renders up to twice as fast — but installing it on Windows has always been a pain. This installer handles everything automatically so you can get the speed boost without the headache.

Automatically detects your Python, PyTorch, and CUDA versions, selects the correct wheel, installs triton-windows, and creates a ready-to-use launcher.

Installers

File Description
install-sage-only.bat Installs SageAttention + Triton and creates a launcher
install-comfyui-setup.bat Same as above, plus optionally installs ComfyUI-Manager and network access (--listen)

Prerequisites

Install these before running the installer:

Requirements

  • Windows 10/11
  • ComfyUI portable (with embedded Python)
  • NVIDIA GPU with CUDA 12.x or 13.x
  • PyTorch 2.4+

GPU Support

GPU Minimum PyTorch Minimum CUDA
RTX 50xx (Blackwell) 2.7 12.8
RTX 40xx (Ada) 2.4 12.4
RTX 30xx (Ampere) 2.4 12.4

GTX 16xx / RTX 20xx (Turing) support was dropped in triton-windows 3.3+ (PyTorch 2.7+). Use PyTorch 2.6 or older.

How to Use

  1. Download the latest version or clone this repository
  2. Double-click install-sage-only.bat or install-comfyui-setup.bat
  3. Enter the path to your ComfyUI portable folder (e.g. D:\ComfyUI_windows_portable)
  4. The installer auto-detects your environment and installs everything
  5. Use the generated run_nvidia_gpu_sage.bat in your ComfyUI folder to launch with SageAttention enabled

Troubleshooting

  • c10.dll error — Install the Visual C++ Redistributable
  • ComfyUI won't start — Update your NVIDIA drivers to the latest version
  • Wheel auto-detection fails — The installer falls back to manual wheel selection
  • All-black / dark video on RTX 50xx — SageAttention's Blackwell (sm_120) fp8 kernel overflows fp16 on models like WAN (fp8 weights run fp16 math), producing NaNs → black frames. This is most commonly seen when working with 2:1 resolutions (e.g. 1280x640). The installer offers an optional fp16 black-frame fix (drops a small node into custom_nodes\sage_fp16_fix) that routes fp16 attention through the stable bf16 Triton backend. It activates automatically; set SAGE_FP16_FIX=0 to disable, or SAGE_FP16_FIX_GUARD=1 for an extra fp32 fallback safety net.

Third-Party Licenses

See the THIRD_PARTY folder for licenses of bundled components:

License

MIT

About

No description, website, or topics provided.

Resources

Stars

42 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages