No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from lightx2v/LightVAE
All models by lightx2v →LightVAE accelerates pretrained video autoencoders through temporal low-rank compression and block pruning while preserving their latent interfaces.
This repository provides checkpoints for Wan2.1, Wan2.2, and MiniMax-H3, including exports for our ComfyUI custom node.
Paper: LightVAE: Towards Compact and Efficient Video Autoencoders
Code and examples: ModelTC/LightVAE
Pro retains the original decoder depth for higher reconstruction fidelity. Lite applies additional pruning for faster inference.
Wan models retain their original encoders. MiniMax-H3 can use either its original encoder or the provided Lite encoder.
Wan2.2 model selection: Wan2.2 14B uses the Wan2.1 VAE; Wan2.2 5B TI2V uses the Wan2.2 VAE. Choose the decoder accordingly.
Important: The
-comfy.safetensorscheckpoints require our Load LightVAE (TLR) custom node. Do not load them with ComfyUI's standard Load VAE / VAELoader node.
Taking MiniMax-H3 as an example, run these commands in the same Python environment used by ComfyUI:
Restart ComfyUI, then add a Load LightVAE (TLR) node.
In Load LightVAE (TLR), select:
decoder: lightvae-lite-h3-decoder-comfy.safetensorsencoder: noneprecision, backend, and device set to auto.Connect its VAE output to your existing VAE Decode node.
Keep the original VAE connections for first/last-frame encoding unchanged. For this decoder-only connection, base_vae can remain disconnected.
The same decoder-only replacement also works for REF2V.
To also accelerate reference-image/video encoding, download the Lite encoder:
Restart ComfyUI and select both H3 Lite files in Load LightVAE (TLR):
decoder: lightvae-lite-h3-decoder-comfy.safetensorsencoder: lightvae-lite-h3-encoder-comfy.safetensorsConnect its VAE output to both the reference-encoding node and VAE Decode. No original video VAE is needed for these connections.
Keep the H3 audio VAE and its connections unchanged in all cases.
See the ComfyUI guide and example workflows for more details and Wan examples.
Use the standard checkpoints without the -comfy suffix:
For example, reconstruct a video with the Wan2.1 Lite decoder and original encoder:
See the GitHub repository for Wan2.2 and MiniMax-H3 examples, benchmarks, and visual comparisons.
If you find LightVAE useful, please consider starring LightVAE and LightX2V. Your support helps us keep improving efficient video generation!
cd /path/to/ComfyUI
git clone https://github.com/ModelTC/LightVAE.git LightVAEpython -m pip install ./LightVAE huggingface_hubpython LightVAE/comfyui/install.py --comfy-root .
hf download lightx2v/LightVAE \ lightvae-lite-h3-decoder-comfy.safetensors \ --local-dir models/vae/LightVAEhf download lightx2v/LightVAE \ lightvae-lite-h3-encoder-comfy.safetensors \ --local-dir models/vae/LightVAEgit clone https://github.com/ModelTC/LightVAE.gitcd LightVAEpython -m pip install -r requirements.txt
hf download lightx2v/LightVAE \ lightvae-lite-wan21-decoder.safetensors \ --local-dir weights/LightVAEhf download Wan-AI/Wan2.1-T2V-1.3B \ Wan2.1_VAE.pth \ --local-dir weights/Wan2.1
python infer.py \ --model wan21 --variant lite \ --encoder weights/Wan2.1/Wan2.1_VAE.pth \ --decoder weights/LightVAE/lightvae-lite-wan21-decoder.safetensors \ --input demo.mp4 --frames 81 --height 480 --width 832 \ --output outputs/wan21_lite_recon.mp4