(For SOTAI Squad) FINALLY! ComfyUI WAN2.2 Animate: Longer Videos + Low VRAM Workflow Guide

Link video: https://youtu.be/kFYxdc5PMFE

In this video, I’ll walk you through a complete ComfyUI WAN2.2 Animate workflow that works even on Low VRAM GPUs (12GB tested). You’ll learn how to unlock longer video outputs without sacrificing quality — perfect for creators who want cinematic results with limited hardware.

? What you’ll discover:

• Step-by-step ComfyUI WAN2.2 Animate setup

• How to run animations on 12GB VRAM (or less)

• Tricks to extend video length while keeping smooth results

• Tips to optimize speed and memory usage

Step 1: Prepare environment

• Update the newest ComfyUI version

• Install and update ComfyUI-WanVideoWrapper custom node

Step2: Download models

• Wan2.2 animate GGUF: https://huggingface.co/QuantStack/Wan2.2-Animate-14B-GGUF/tree/main

• umt5-xxl-enc-fp8_e4m3fn.safetensors : https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/umt5-xxl-enc-fp8_e4m3fn.safetensors

• wan2.1 vae: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors

• Wan21_T2V_14B_lightx2v_cfg_step_distill_lora_rank32.safetensors: https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/Wan21_T2V_14B_lightx2v_cfg_step_distill_lora_rank32.safetensors

Note:

• Install custom node "ComfyUI_LayerStyle" to get "Purge VRAM" node

• Gradually reduce the video size (width, height, number of frames) if you’re still running out of memory when using the workflow.

• Please check the workflow in the attachments.