WAN 2.2 SVI 2.0 — Infinite-Length Video
WAN 2.2 SVI 2.0 creates seamless, infinite-length video in ComfyUI using Stable Video Infinity LoRAs — extend clips indefinitely, optimized for low VRAM and faster rendering.
✓ 100% free — download the workflow and run it locally.Preview
Requirements
- GPU: NVIDIA RTX 30XX/40XX/50XX (FP16)
- VRAM: 6 GB minimum, 12 GB+ recommended
- 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/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main
- Wan2.2 I2V A14B LowNoise Q3_K_S GGUF https://huggingface.co/QuantStack/Wan2.2-I2V-A14B-GGUF/tree/main/LowNoise
- Wan2.2 I2V A14B HighNoise Q3_K_S GGUF https://huggingface.co/QuantStack/Wan2.2-I2V-A14B-GGUF/tree/main/HighNoise
- SVI v2 PRO LoRAs https://huggingface.co/Kijai/WanVideo_comfy/tree/main/LoRAs/Stable-Video-Infinity/v2.0
- Standard WAN 2.2 diffusion models https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/tree/main/split_files/diffusion_models
Custom nodes
- ComfyUI Manager https://github.com/ltdrdata/ComfyUI-Manager
Setup steps
- Install ComfyUI Manager + its requirements.
- Download all models to their ComfyUI folders (clip, vae, unet, loras, diffusion_models).
- Load the SVI workflow, set your segment length, and run to extend the clip.
Notes & tips
- 20s 480p at 6 steps in ~1 min per 5-second segment on an RTX 4090.
- The full ready-made workflow is a Patreon/Pro extra — grab the 1-click installer below for the complete graph.
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.