Wan 2.1 Video in ComfyUI
High-temporal-consistency video suite offering both a consumer-friendly 1.3B model for 8 GB GPUs and a 14B flagship for studio shots. Requires 8 GB (1.3B) to 16 GB+ (14B) VRAM and loads from models/diffusion_models/.
Updated Oct 17, 2026 · 1 min read
- Model Family
- Alibaba Wan
- VRAM Target
- 8 GB (1.3B) to 16 GB+ (14B)
- ComfyUI Folder
- models/diffusion_models/
- Precision
- FP16, FP8, or GGUF
- Default Sampler
- uni_pc / euler flow match, 25 steps
Where to place Wan 2.1 Video weights on Windows
High-temporal-consistency video suite offering both a consumer-friendly 1.3B model for 8 GB GPUs and a 14B flagship for studio shots.
Place the primary `.safetensors` or `.gguf` weight file inside `models/diffusion_models/` inside your ComfyUI directory, or point extra_model_paths.yaml to your existing shared models drive.
After moving the file, press **R** on the ComfyUI Studio canvas (or click Refresh) so the loader dropdown lists the new checkpoint immediately without restarting the server.
Recommended loader nodes and sampler settings
- **Precision & Memory:** FP16, FP8, or GGUF. Cards at the lower end of 8 GB (1.3B) to 16 GB+ (14B) should pair this model with FP8 or GGUF quantization and VAE Decode (Tiled).
- **Sampler & Scheduler:** uni_pc / euler flow match, 25 steps. Wire the model output into KSampler and connect the matching CLIP and VAE streams.
- **Installer:** If you have not set up the desktop environment yet, get the Windows build at /download.
Wan 2.1 Video Quick Reference for ComfyUI Windows
| Parameter | Recommended Setting | Notes |
|---|---|---|
| Target Directory | models/diffusion_models/ | Refresh canvas with R key after copying |
| VRAM Tier | 8 GB (1.3B) to 16 GB+ (14B) | Use --lowvram or GGUF Q4 on 8 GB cards |
| Weight Format | FP16, FP8, or GGUF | Never load untrusted .ckpt pickle files |
| Sampler Recipe | uni_pc / euler flow match, 25 steps | Wire through core KSampler node |
FAQs
Which folder does Wan 2.1 Video go into in ComfyUI?
Put Wan 2.1 Video inside `models/diffusion_models/` in your ComfyUI installation, then press R on the canvas to refresh node dropdowns.
Can I run Wan 2.1 Video on an 8 GB NVIDIA GPU?
Yes — use FP8 or GGUF Q4/Q5 weights via ComfyUI-GGUF and keep tiled VAE decoding enabled so peak VRAM stays under 8 GB.
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.
