You can deploy this model and start earning money today!

fal/
Wan2.2-Animate-2-Base-FlashPack

Name: Wan2.2-Animate-2-Base-FlashPack
Availability: InStock

2608.06009

apache-2.0

Views

No views yet

Wan-Animate-2: Pushing the Application Boundaries of Character Animation Models

Guangyuan Wang^∗^, Li Hu^*†^, Dechao Meng^∗^, Zhongyi Zhang^∗^, Peng Zhang^∗^, Mingyang Huang, Ruoshi Zhang, Ke Sun, Zhe Zhang, Xingjun Wang, Gang Cheng, Hai Xu, Bang Zhang^‡^

^∗Core Contribution ^†Project leaders ^‡Sponsor

License

arXiv

Demo

📝 Introduction

We present Wan-Animate-2, a novel end-to-end character animation framework that directly consumes driving videos in a redesigned Diffusion Transformer, which achieves high-fidelity motion generation and strong identity preservation by eliminating intermediate motion extractors. We further add text-driven viewpoint control to decouple the output camera perspective from the driving video. In addition, we develop Wan-Animate-2-Lite, an efficient variant that reduces inference latency to real-time thresholds for streaming character animation.

Release Notes:

August 07, 2026: 🎉 We release the Wan-Animate-2 inference scripts.
August 07, 2026: 🎉 We release the Wan-Animate-2 Base model weights.
August 07, 2026: 🎉 We release the Wan-Animate-2 Distillation model weights.

📑 Todo List

Wan-Animate-2 Character Animation
- Inference code of Wan-Animate-2
- Checkpoints of Wan-Animate-2
- Diffusers integration
- DiffSynth-Studio integration
- ComfyUI integration

🚀 Quick Start

Installation

Clone this repo:

git clone --recursive https://github.com/Wan-Video/Wan-Animate-2.git

Create python environment and install torch:

bash

conda create -n wan_animate_2 python==3.11 -y
pip install torch==2.7.0 torchvision==0.22.0 torchaudio==2.7.0 --index-url https://download.pytorch.org/whl/cu126

Install dependencies (please refer to requirements.txt):

pip install -r requirements.txt

Install flash_attn:

pip install flash-attn --no-build-isolation

Install this repository as a local editable package:

pip install -e .

Model Download

Model	Download Links
Wan-Animate-2	🤗 HuggingFace 🤖 ModelScope

Download models using huggingface-cli:

pip install "huggingface_hub[cli]"
huggingface-cli download Wan-AI/Wan2.2-Animate-2-14B --local-dir ./ckpts/

Download models using modelscope-cli:

pip install modelscope
modelscope download --model Wan-AI/Wan2.2-Animate-2-14B --local_dir ./ckpts/

Inference

Before inference, use an LLM model (e.g. Qwen3.7-Plus) with the prompt below to get the image caption, then use it as the prompt for Wan-Animate-2.

用中文客观描述图片中的内容，包括以下要点：人物外观描述，不描述动作行为。 背景描述，忽略主观评价和情绪推测。 下面给出描述范例，必须遵循这个范式，不要输出额外的符号： 人物外观描述：穿着一件浅蓝色的校服衬衫，领口和袖口有白色边饰。胸前有一个圆形徽章。 背景描述：背景为明亮、整洁的教室或办公室，氛围安静有序。

Note: The default settings in this repository are tuned for 8× A800 GPUs and support 720P video generation. We have also tested 480P generation on 2× A800 GPUs. If your hardware setup is different, please adjust the parallel configs in the YAML files accordingly.

Wan-Animate-2 Base:
bash
1export PYTHONPATH="$(pwd)" 2cd infer 3python wan_animate_2_demo.py \ 4 --prompt "人物外观描述：一只银灰色虎斑纹的小猫，拥有圆润的脸庞、竖立的耳朵和巨大的圆形眼睛。它身穿一套深蓝色的制服套装，包括一件带有金色纽扣的西装外套和一条百褶裙。外套里面搭配着白色衬衫，领口处系着一个红色的蝴蝶结，袖口露出白色的衬衫边缘。背景描述：背景为纯白色，光线均匀明亮，无其他杂物或装饰。" \ 5 --refer-img-file ../examples/demo1/reference.png \ 6 --refer-video-file ../examples/demo1/template.mp4 \ 7 --config ./wan_animate_2.yaml
Wan-Animate-2 Distillation:
bash
1export PYTHONPATH="$(pwd)" 2cd infer 3python wan_animate_2_demo.py \ 4 --prompt "人物外观描述：一只银灰色虎斑纹的小猫，拥有圆润的脸庞、竖立的耳朵和巨大的圆形眼睛。它身穿一套深蓝色的制服套装，包括一件带有金色纽扣的西装外套和一条百褶裙。外套里面搭配着白色衬衫，领口处系着一个红色的蝴蝶结，袖口露出白色的衬衫边缘。背景描述：背景为纯白色，光线均匀明亮，无其他杂物或装饰。" \ 5 --refer-img-file ../examples/demo1/reference.png \ 6 --refer-video-file ../examples/demo1/template.mp4 \ 7 --config ./wan_animate_2_distillation.yaml \ 8 --sample_guide_scale 1.0 9 --step 10

🧨 Diffusers Inference

Wan-Animate-2 is supported by the 🤗 diffusers library (see PR #14412).

Install diffusers from source (until the next release):

bash

pip install git+https://github.com/huggingface/diffusers.git
pip install flash-attn --no-build-isolation

Wan-Animate-2 Base:

python
1import torch 2from diffusers import WanAnimate2Pipeline 3from diffusers.utils import export_to_video, load_image 4 5pipe = WanAnimate2Pipeline.from_pretrained( 6 "Wan-AI/Wan2.2-Animate-2-14B-Diffusers", torch_dtype=torch.bfloat16 7).to("cuda") 8 9output = pipe( 10 image=load_image("../examples/demo1/reference.png"), 11 driving_video="../examples/demo1/template.mp4", 12 prompt="人物外观描述：一只银灰色虎斑纹的小猫，拥有圆润的脸庞、竖立的耳朵和巨大的圆形眼睛。它身穿一套深蓝色的制服套装，包括一件带有金色纽扣的西装外套和一条百褶裙。外套里面搭配着白色衬衫，领口处系着一个红色的蝴蝶结，袖口露出白色的衬衫边缘。背景描述：背景为纯白色，光线均匀明亮，无其他杂物或装饰。", 13 height=800, 14 width=640, 15 num_inference_steps=40, 16) 17 18export_to_video(output.frames[0], "output.mp4", fps=24)
Wan-Animate-2 Distillation (10 steps, no CFG):

python
1pipe = WanAnimate2Pipeline.from_pretrained( 2 "Wan-AI/Wan2.2-Animate-2-14B-Distilled-Diffusers", torch_dtype=torch.bfloat16 3).to("cuda") 4 5output = pipe( 6 image=load_image("../examples/demo1/reference.png"), 7 driving_video="../examples/demo1/template.mp4", 8 prompt="人物外观描述：一只银灰色虎斑纹的小猫，拥有圆润的脸庞、竖立的耳朵和巨大的圆形眼睛。它身穿一套深蓝色的制服套装，包括一件带有金色纽扣的西装外套和一条百褶裙。外套里面搭配着白色衬衫，领口处系着一个红色的蝴蝶结，袖口露出白色的衬衫边缘。背景描述：背景为纯白色，光线均匀明亮，无其他杂物或装饰。", 9 num_inference_steps=10, 10 guidance_scale=1.0, # no classifier-free guidance 11 flow_solver="euler", # Euler scheduler for distilled model 12) 13 14export_to_video(output.frames[0], "output.mp4", fps=24)

🤖 Gradio Demo

Try the online demo: ModelScope Studio

Run locally:

Wan-Animate-2 Base:
bash
1cd infer 2python wan_animate_2_gradio.py
Wan-Animate-2 Distillation:
bash
1cd infer 2python wan_animate_2_gradio_distillation.py

📜 Citation

If you find this work helpful, please consider citing:

BibTeX

@article{wang2026wananimate2,
  title   = {Wan-Animate-2: Real-Time End-to-End Character Animation via Diffusion Transformer},
  author  = {Wang, Guangyuan and Hu, Li and Meng, Dechao and Zhang, Zhongyi and Zhang, Peng and
             Huang, Mingyang and Zhang, Ruoshi and Sun, Ke and Zhang, Zhe and
             Wang, Xingjun and Cheng, Gang and Zhang, Bang},
  journal = {arXiv preprint arXiv:TODO.06009},
  year    = {2026},
  url     = {https://arxiv.org/abs/TODO.06009}
}

⚖️ License

This project is licensed under the Apache License 2.0.

fal/Wan2.2-Animate-2-Base-FlashPack