WAN 2.1 Low VRAM Text-to-Image

Requirements

• ComfyUI (portable or desktop), updated to a recent build
• GGUF builds are included — pick the quantisation that fits your VRAM
• 8 custom node(s), listed below
• NVIDIA GPU recommended; see the notes for model-specific VRAM guidance

Model downloads

• umt5-xxl-encoder-Q5_K_M.gguf (ComfyUI\models\clip) https://huggingface.co/city96/umt5-xxl-encoder-gguf/tree/main ⧉
• wan_2.1_vae.safetensors (ComfyUI\models\vae) https://huggingface.co/Kijai/WanVideo_comfy/tree/main ⧉
• self_forcing_dmd.pt (ComfyUI\models\diffusion_models) https://huggingface.co/gdhe17/Self-Forcing/tree/main/checkpoints ⧉
• WAN 2.1 T2V GGUF Models (ComfyUI\models\unet) https://huggingface.co/city96/Wan2.1-T2V-14B-gguf/tree/main ⧉
• 2xLexicaRRDBNet_Sharp.pth Upscale model (ComfyUI\models\upscale_models) https://huggingface.co/Thelocallab/2xLexicaRRDBNet_Sharp/blob/main/2xLexicaRRDBNet_Sharp.pth ⧉
• Wan21 T2V 14B lightx2v, Wan2.1 T2V 14B FusionX & WAN detailz-wan LoRA Models (ComfyUI\models\loras) https://huggingface.co/Thelocallab/WAN-2.1-loras/tree/main ⧉

Custom nodes

• ComfyUI Manager Command to install requirements:.\python_embeded\python.exe -m pip install -r .\ComfyUI\custom_nodes\ComfyUI-Manager\requirements.txt https://github.com/ltdrdata/ComfyUI-Manager ⧉
• ComfyUI-WanVideoWrapper via ComfyUI Manager https://github.com/kijai/ComfyUI-WanVideoWrapper ⧉
• ComfyUI-KJNodes via ComfyUI Manager https://github.com/kijai/ComfyUI-KJNodes ⧉
• rgthree-comfy via ComfyUI Manager https://github.com/rgthree/rgthree-comfy ⧉
• ComfyUI-GGUF via ComfyUI Manager https://github.com/city96/ComfyUI-GGUF ⧉
• gguf via ComfyUI Manager https://github.com/calcuis/gguf ⧉
• ComfyUI-Easy-Use via ComfyUI Manager https://github.com/yolain/ComfyUI-Easy-Use ⧉
• comfyui-vrgamedevgirl via ComfyUI Manager https://github.com/vrgamegirl19/comfyui-vrgamedevgirl ⧉

Setup steps

1. Download the 6 model file(s) listed below and place each one into their ComfyUI model folders.
2. Install the 8 custom node(s) listed below via ComfyUI Manager, then fully restart ComfyUI.
3. Download the workflow .json from the button above and drag it onto the ComfyUI canvas.
4. Open each loader node and confirm the model files are selected — a fresh install often defaults to the wrong one.
5. Run the workflow. If a node shows red, update ComfyUI and restart before troubleshooting anything else.

More resources

• https://get.runpod.io/WANVideo-ComfyUI-Template ⧉
• https://www.patreon.com/posts/133930453 ⧉
• Youtube Video Tutorial https://youtu.be/IpbsFXPPtWU ⧉
• Community Support: For troubleshooting or to connect with other users, join the Discord server. https://discord.gg/5hmB4N4JFc ⧉