WAN 2.2 14B Low-VRAM Text-to-Image
Fast WAN 2.2 image generation on low-VRAM GPUs using quantized GGUF models — sharper, high-detail rendering with strong style consistency. 960×960 in under 3 minutes on a 6GB RTX 4050, from a unified image/video workflow.
✓ 100% free — download the workflow and run it locally.Preview
Requirements
- GPU: NVIDIA RTX 30XX/40XX/50XX (FP16)
- VRAM: 4–6 GB minimum
- OS: Windows
- Storage: 40 GB+ free
Model downloads
- umt5-xxl encoder Q5_K_M GGUF https://huggingface.co/city96/umt5-xxl-encoder-gguf/tree/main
- wan_2.1_vae.safetensors https://huggingface.co/Kijai/WanVideo_comfy/tree/main
- WAN 2.1 T2V GGUF models https://huggingface.co/city96/Wan2.1-T2V-14B-gguf/tree/main
- 2xLexicaRRDBNet_Sharp (upscaler) https://huggingface.co/Thelocallab/2xLexicaRRDBNet_Sharp/blob/main/2xLexicaRRDBNet_Sharp.pth
- WAN 2.1 T2V 14B lightx2v LoRA https://huggingface.co/Thelocallab/WAN-2.1-loras/tree/main
Custom nodes
- ComfyUI Manager https://github.com/ltdrdata/ComfyUI-Manager
- ComfyUI_LayerStyle https://github.com/chflame163/ComfyUI_LayerStyle
- ComfyUI-KJNodes https://github.com/kijai/ComfyUI-KJNodes
- rgthree-comfy https://github.com/rgthree/rgthree-comfy
- ComfyUI-GGUF https://github.com/city96/ComfyUI-GGUF
Setup steps
- Install ComfyUI Manager + its requirements and the custom nodes above.
- Download all models to their folders (clip, vae, unet, upscale_models, loras).
- Import the WAN 2.2 T2I workflow below.
- Enter a detailed prompt (LLM enhancement recommended) and run.
Notes & tips
- Compatible with WAN models beyond 2.2.
- Prefer one-click? A WAN 2.2 installer is available.
Want the 1-click version?
Skip the manual model downloads and node installs — get a ready-to-run installer, or unlock all 75+ with Local Lab Pro.