All model downloads: https://huggingface.co/Kijai/WanVideo_comfy

Combined and quantized models for WanVideo, sourced from here:

https://huggingface.co/Wan-AI/

Can be used with the following nodes: https://github.com/kijai/ComfyUI-WanVideoWrapper and native ComfyUI WanVideo nodes.

fp8_scaled version: https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled

Other model sources:

TinyVAE from https://github.com/madebyollin/taehv

SkyReels: https://huggingface.co/collections/Skywork/skyreels-v2-6801b1b93df627d441d0d0d9

WanVideoFun: https://huggingface.co/collections/alibaba-pai/wan21-fun-v11-680f514c89fe7b4df9d44f17

Lightx2v:

CausVid 14B: https://huggingface.co/lightx2v/Wan2.1-T2V-14B-CausVid

CFG and Step Distillation 14B: https://huggingface.co/lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill

CausVid 1.3B: https://huggingface.co/tianweiy/CausVid

AccVideo: https://huggingface.co/aejion/AccVideo-WanX-T2V-14B

Phantom: https://huggingface.co/bytedance-research/Phantom

ATI: https://huggingface.co/bytedance-research/ATI

MiniMaxRemover: https://huggingface.co/zibojia/minimax-remover

MAGREF: https://huggingface.co/MAGREF-Video/MAGREF

Fantasy Talking: https://github.com/Fantasy-AMAP/fantasy-talking

MultiTalk: https://github.com/MeiGen-AI/MultiTalk

Anisora: https://huggingface.co/IndexTeam/Index-anisora/tree/main/14B

Box: https://huggingface.co/RaphaelLiu/PusaV1/tree/main

FastVideo: https://huggingface.co/FastVideo

EchoShot: https://github.com/D2I-ai/EchoShot

CausVid LoRA is an experimental extraction from the CausVid fine-tune, aimed at benefiting from the distillation in CausVid rather than any actual causal inference.

v1 = Direct extraction; has an adverse effect on motion and introduces flashing artifacts at maximum strength.

v1.5 = Same as above, but without the first block, which completely fixes the flashing.

v2 = Further pruned version with only attention layers and no first block; fixes flashing, preserves motion better, requires more steps, and can also benefit from CFG.