ComfyUI Windows Installation
First-time installation checklists for Windows 10 and 11, PyTorch CUDA 12.4 wheels, Git setup, and shared checkpoint folders.
Updated Oct 17, 2026 · 3 min read
- Section
- Install
- Platform
- Windows 10 & 11 (64-bit)
- Supported GPUs
- NVIDIA RTX 20 / 30 / 40 / 50 (CUDA 12.4+)
- Installer
- Available on /download
How ComfyUI Windows Installation works on Windows
First-time installation checklists for Windows 10 and 11, PyTorch CUDA 12.4 wheels, Git setup, and shared checkpoint folders. Getting from /download to your first rendered image with verified GPU acceleration and clean dependencies.
Every page in this directory focuses on practical local execution on Windows 10 and Windows 11, keeping your checkpoints, LoRAs, and generated outputs entirely on your own SSD.
Start by grabbing the current Windows build from /download, or browse the guides and node blueprints linked below.
Key workflow principles
- Keep large `.safetensors` and `.gguf` weights inside organized `models/` subfolders or map shared directories through extra_model_paths.yaml.
- Match your model precision (FP16, FP8 e4m3fn, or GGUF Q4/Q8) to your card's VRAM tier so sampling stays in GPU memory without paging to disk.
- Drag any generated PNG directly onto the ComfyUI Studio canvas to reload its exact node wiring, seed, and sampler values.
Featured pages in ComfyUI Windows Installation
- How to Install ComfyUI on Windows (Step-by-Step) — Direct Windows guide for "how to install comfyui on windows": folder paths, node wiring, and VRAM settings in ComfyUI.
- How to Install ComfyUI Manager on Windows — Direct Windows guide for "install comfyui manager windows": folder paths, node wiring, and VRAM settings in ComfyUI.
- Configure extra_model_paths.yaml in ComfyUI — Direct Windows guide for "comfyui extra_model_paths.yaml setup": folder paths, node wiring, and VRAM settings in ComfyUI.
- Share Checkpoints Between ComfyUI, A1111 & Forge — Direct Windows guide for "share models between comfyui and automatic1111": folder paths, node wiring, and VRAM settings in ComfyUI.
- ComfyUI PyTorch & CUDA 12.4 Setup on Windows — Direct Windows guide for "comfyui pytorch cuda 12.4 windows": folder paths, node wiring, and VRAM settings in ComfyUI.
- Fix Git Not Found in ComfyUI Manager on Windows — Direct Windows guide for "comfyui git not found windows fix": folder paths, node wiring, and VRAM settings in ComfyUI.
- Install Python Packages in ComfyUI python_embeded — Direct Windows guide for "comfyui python_embeded pip install": folder paths, node wiring, and VRAM settings in ComfyUI.
- Install InsightFace for ComfyUI on Windows without C++ Errors — Direct Windows guide for "install insightface comfyui windows": folder paths, node wiring, and VRAM settings in ComfyUI.
- PyTorch SDPA vs xFormers in ComfyUI on Windows — Direct Windows guide for "comfyui xformers vs pytorch cross attention": folder paths, node wiring, and VRAM settings in ComfyUI.
- Running ComfyUI on AMD Radeon GPUs on Windows — Direct Windows guide for "comfyui amd gpu windows zluda directml": folder paths, node wiring, and VRAM settings in ComfyUI.
- NVIDIA Game Ready & Studio Driver Requirements for ComfyUI — Direct Windows guide for "comfyui nvidia driver requirements": folder paths, node wiring, and VRAM settings in ComfyUI.
- Verify & Allow ComfyUI Installer on Windows 11 — Direct Windows guide for "comfyui windows smartscreen defender": folder paths, node wiring, and VRAM settings in ComfyUI.
FAQs
Where do I download ComfyUI for Windows to use install?
Download the Windows desktop installer or portable package directly from /download on this site.
Does ComfyUI run 100% locally without a cloud subscription?
Yes. Once installed on Windows with your local checkpoints in `models/`, ComfyUI executes every node graph locally on your GPU with zero per-image fees.
Run on your hardware. Free forever.
The full ComfyUI engine: open source, fast, extensible, and yours to run however you want. Download the desktop app and open this workflow on your own machine.
