Wan-Animate-2

by Alibaba

Character animation model by Alibaba's Wan team. Reference image + driving video: the character performs the full motion and expression of the video, with viewpoint and background controlled by prompt. Native ComfyUI support, self-contained repo, 832x480 in 81-frame chainable segments.

VideoApache 2.0Released Aug 202614B parameters

Hugging Face repo ↗

Drag or click to move along the pipeline

full qualitylightest

Lighter tiers fit smaller GPUs and lose some detail. Start with the heaviest one that loads.

The model

Wan-Animate-2

BF1642.5 GB

Three pieces, three separate downloads.

Diffusion modelGoes in diffusion_models/

Generates the image

30.5 GB↓↗

Text encoderGoes in text_encoders/

Turns your prompt into guidance

Pick one: smaller loads faster, larger keeps more detail.

10.6 GB↓↗

1.2 GB↓↗

VAEGoes in vae/

Decodes the result into pixels

0.2 GB↓↗

LoRAs (optional)Goes in loras/

0.7 GB↓↗

SamplerKSampler

Copy these values into your KSampler.

Steps6

CFG1

Samplerlcm

Schedulersimple

Native res.832x480, 81-frame segments, 24 fps

Shift5

Usage notes

Apache 2.0. Check the official repo for usage terms.

Click a file name to copy it.