WAN 2.2 14B Low VRAM Text To Image(6GB) - ComfyUI Workflow - One Click Installer
Generate high resolution images with the new WAN 2.2 14B GGUF Video Models locally in ComfyUI.
WAN 2.2 ushers in a significant leap for text-to-image (and text-to-video) generation, offering sharper, high-detail rendering, improved aesthetic fidelity, and robust style consistency—even on lower VRAM GPUs. With advanced Mixture of Experts (MoE) architecture, GGUF quantization, and optimized model pipelines, WAN 2.2 enables cinematic-quality images and videos with fewer artifacts and better semantic alignment than previous versions. Notably, it supports both text-to-image and text-to-video in a single workflow, allowing seamless creative iteration and fast, high-res output. This update makes it easier than ever to generate professional-grade visuals at home—no expensive hardware required147.
I've developed a one-click installer and a custom workflow that lets you run WAN 2.2 quantized GGUF models for fast image generation on lower VRAM devices. The installer automatically installs the Wan2.2 T2V A14B Low Noise Q3_K_S GGUF models but if you have more compute, you can download a higher quant for better quality.
Preloaded Models within the Installer (Low VRAM)
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
Wan2.2-T2V-A14B-LowNoise-Q3_K_S.gguf (ComfyUI\models\unet) - https://huggingface.co/QuantStack/Wan2.2-T2V-A14B-GGUF/tree/main/LowNoise
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
Speed: 960 x 960 resolution in under 3 minutes on RTX 4050 6GB VRAM; even faster on enterprise GPUs. Workflow comes with an automatic upscaler
System Requirements:
Nvidia RTX 30XX, 40XX, or 50XX series GPU (FP16 support required; GTX 10XX/20XX not tested)
CUDA-compatible GPU with at least 6 GB VRAM
Windows OS
At least 40 GB free storage
What’s Included:
Portable ComfyUI Windows Installer, pre-configured for WAN 2.2 text-to-image
Custom workflow supporting text-to-image generation
Automatic downloads for all required nodes and models
Usage Notes: Type in your detailed text prompt describing the image you want. Use an LLM to enhance your prompt for best results.
Support and More Information
Community Support: For troubleshooting or to connect with other users, join the Discord server.
Get Every Installer with Local Lab Pro
Buy this installer on its own here, or get every installer in the store — plus every new release — with Local Lab Pro for $10/month. Cancel anytime. Join Local Lab Pro →
