Downloads · 30 days
0
The-frizzy1/Wan21-GGUF-4GB-Workflow
Wan21-GGUF-4GB-Workflow is a image-to-video model from The-frizzy1. Use it for the image-to-video task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
By: Thefrizzy1 Hardware target: RTX 3050 Laptop (4 GB VRAM) CivitAI: https://civitai.com/models/1309674/wan21gguf-only-4gb-vram-comfyui-workflow YouTube: https://www.youtube.com/@thefrizzy1
Downloads · 30 days
0
Access
Public
Updated Mar 24, 2026
Repo size
38.1 KB
Likes
5
Public
Click a slice to open those files.
.zip38.1 KB · 89%
From the Hugging Face model README
By: The_frizzy1 Hardware target: RTX 3050 Laptop (4 GB VRAM) CivitAI: https://civitai.com/models/1309674/wan21gguf-only-4gb-vram-comfyui-workflow YouTube: https://www.youtube.com/@the_frizzy1
A ComfyUI workflow pack for running Wan2.1 video generation on low-VRAM GPUs (as low as 4 GB). Uses GGUF-quantised models and custom nodes from Kijai and others.
| Node | Link |
|---|---|
| GGUF | https://github.com/calcuis/gguf |
| WanVideoWrapper | https://github.com/kijai/ComfyUI-WanVideoWrapper |
| Tiled KSampler | https://github.com/FlyingFireCo/tiled_ksampler |
| KJNodes | https://github.com/kijai/ComfyUI-KJNodes |
| Video Helper Suite | https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite |
| rgthree-comfy (LoRA stacking only) | https://github.com/rgthree/rgthree-comfy |
| Model | Link | Notes |
|---|---|---|
| WAN GGUF | https://huggingface.co/calcuis/wan-gguf | Main source |
| I2V alternative | https://huggingface.co/city96/Wan2.1-I2V-14B-480P-gguf/tree/main | Better for I2V |
| 1.3B GGUF | https://huggingface.co/calcuis/wan-1.3b-gguf/tree/main | Fun/inpainting/T2V/VACE |
| Fun Control 14B | https://huggingface.co/city96/Wan2.1-Fun-14B-Control-gguf/tree/main | Fun-Control |
| Fun Camera 14B | https://huggingface.co/QuantStack/Wan2.1-Fun-V1.1-14B-Control-Camera-GGUF/tree/main | Camera-Control |
| VACE GGUF alt | https://huggingface.co/QuantStack/Wan2.1_14B_VACE-GGUF | VACE alternative |
VAE / CLIP / Text Encoder: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files
Place all .gguf files in ComfyUI/models/diffusion_models/
| Level | VRAM | Quality |
|---|---|---|
| Q5 | Medium | Best balance |
| Q3_K_M | Low | Good |
| Q2_K | Lowest | Usable |
| 14B | High | Best quality |
Enable Xformers, Sage Attention, or Triton for extra speed. Triton install guide: https://www.patreon.com/posts/easy-guide-sage-124253103
| Version | Notes |
|---|---|
| v2.0 | Teacache, Torch Compile, new GGUF loader |
| v1.8 | See install video |
| v1.1 | Better quality and stability |
| v1.0 | Initial release |