Wan2.2 TI2V 5B Diffusers

ProviderWan-AI
Categorytext-to-video
Licenseapache-2.0
Downloads11.4K
Stars22

Overview

Wan2.2 TI2V 5B is a specialized image-to-video diffusion model designed for high-fidelity temporal animation. Unlike general text-to-video generators, this 5-billion parameter model focuses on transforming static source images into dynamic sequences, maintaining strong structural consistency and spatial coherence. For developers, the primary draw is its integration with the Diffusers library, which simplifies the pipeline for custom weights, scheduling, and deployment in Python environments. It is particularly effective for cinematic b-roll, product animations, and character movement where precise control over the starting frame is required. Compared to larger models, the 5B scale offers a balanced trade-off between inference speed and visual quality, making it more accessible for local hosting or scaled API implementations.

Highlights

  • Native Diffusers integration for streamlined Python deployment
  • Strong spatial consistency from source image to video
  • Efficient 5B parameter scale for faster inference
  • Permissive Apache-2.0 license for commercial flexibility
  • Optimized for high-fidelity temporal motion and animation

Usage

Install
# Install Hugging Face transformers
pip install transformers torch
SDK Usage
# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("Wan-AI/Wan2.2-TI2V-5B-Diffusers")
tokenizer = AutoTokenizer.from_pretrained("Wan-AI/Wan2.2-TI2V-5B-Diffusers")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance 
pip install -U huggingface_hub

CLI Download

Download the full repository

Download the full repository 
huggingface-cli download Wan-AI/Wan2.2-TI2V-5B-Diffusers

Download a single file to a local folder (e.g. config.json into ./dir)

Download a single file to a local folder (e.g. config.json into ./dir) 
huggingface-cli download Wan-AI/Wan2.2-TI2V-5B-Diffusers config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('Wan-AI/Wan2.2-TI2V-5B-Diffusers')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B-Diffusers

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B-Diffusers

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

Install Transformers 
pip install -U transformers torch

Load the model and run inference

Load the model and run inference 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('Wan-AI/Wan2.2-TI2V-5B-Diffusers')
tokenizer = AutoTokenizer.from_pretrained('Wan-AI/Wan2.2-TI2V-5B-Diffusers')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance 
pip install modelscope

CLI Download

Download the full repository

Download the full repository 
modelscope download --model Wan-AI/Wan2.2-TI2V-5B-Diffusers

Download a single file to a local folder (e.g. README.md into ./dir)

Download a single file to a local folder (e.g. README.md into ./dir) 
modelscope download --model Wan-AI/Wan2.2-TI2V-5B-Diffusers README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('Wan-AI/Wan2.2-TI2V-5B-Diffusers')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://www.modelscope.cn/Wan-AI/Wan2.2-TI2V-5B-Diffusers.git

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/Wan-AI/Wan2.2-TI2V-5B-Diffusers.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

Install the ModelScope library 
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

Load the model and run inference 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'Wan-AI/Wan2.2-TI2V-5B-Diffusers')

Full Documentation

来源: HuggingFace

---
license: apache-2.0
language:

  • en

  • zh

pipeline_tag: text-to-video
---

Wan2.2

<p align="center">
<img src="assets/logo.png" width="400"/>
<p>

<p align="center">
💜 <a href="https://wan.video"><b>Wan</b></a> &nbsp&nbsp ｜ &nbsp&nbsp 🖥️ <a href="https://github.com/Wan-Video/Wan2.2">GitHub</a> &nbsp&nbsp | &nbsp&nbsp🤗 <a href="https://huggingface.co/Wan-AI/">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href="https://modelscope.cn/organization/Wan-AI">ModelScope</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://arxiv.org/abs/2503.20314">Technical Report</a> &nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://wan.video/welcome?spm=a2ty_o02.30011076.0.0.6c9ee41eCcluqg">Blog</a> &nbsp&nbsp | &nbsp&nbsp💬 <a href="https://gw.alicdn.com/imgextra/i2/O1CN01tqjWFi1ByuyehkTSB_!!6000000000015-0-tps-611-1279.jpg">WeChat Group</a>&nbsp&nbsp | &nbsp&nbsp 📖 <a href="https://discord.gg/AKNgpMK4Yj">Discord</a>&nbsp&nbsp
<br>

-----

Wan: Open and Advanced Large-Scale Video Generative Models <be>

We are excited to introduce Wan2.2, a major upgrade to our foundational video models. With Wan2.2, we have focused on incorporating the following innovations:

  • 👍 Effective MoE Architecture: Wan2.2 introduces a Mixture-of-Experts (MoE) architecture into video diffusion models. By separating the denoising process cross timesteps with specialized powerful expert models, this enlarges the overall model capacity while maintaining the same computational cost.
  • 👍 Cinematic-level Aesthetics: Wan2.2 incorporates meticulously curated aesthetic data, complete with detailed labels for lighting, composition, contrast, color tone, and more. This allows for more precise and controllable cinematic style generation, facilitating the creation of videos with customizable aesthetic preferences.
  • 👍 Complex Motion Generation: Compared to Wan2.1, Wan2.2 is trained on a significantly larger data, with +65.6% more images and +83.2% more videos. This expansion notably enhances the model's generalization across multiple dimensions such as motions, semantics, and aesthetics, achieving TOP performance among all open-sourced and closed-sourced models.
  • 👍 Efficient High-Definition Hybrid TI2V: Wan2.2 open-sources a 5B model built with our advanced Wan2.2-VAE that achieves a compression ratio of 16×16×4. This model supports both text-to-video and image-to-video generation at 720P resolution with 24fps and can also run on consumer-grade graphics cards like 4090. It is one of the fastest 720P@24fps models currently available, capable of serving both the industrial and academic sectors simultaneously.

This repository contains our TI2V-5B model, built with the advanced Wan2.2-VAE that achieves a compression ratio of 16×16×4. This model supports both text-to-video and image-to-video generation at 720P resolution with 24fps and can runs on single consumer-grade GPU such as the 4090. It is one of the fastest 720P@24fps models available, meeting the needs of both industrial applications and academic research.

Video Demos

<div align="center">
<video width="80%" controls>
<source src="https://cloud.video.taobao.com/vod/4szTT1B0LqXvJzmuEURfGRA-nllnqN_G2AT0ZWkQXoQ.mp4" type="video/mp4">
Your browser does not support the video tag.
</video>
</div>

🔥 Latest News!!

  • Jul 28, 2025: 👋 We've released the inference code and model weights of Wan2.2.

Community Works

If your research or project builds upon Wan2.1 or Wan2.2, we welcome you to share it with us so we can highlight it for the broader community.

📑 Todo List

  • Wan2.2 Text-to-Video
- [x] Multi-GPU Inference code of the A14B and 14B models - [x] Checkpoints of the A14B and 14B models - [x] ComfyUI integration - [x] Diffusers integration
  • Wan2.2 Image-to-Video
- [x] Multi-GPU Inference code of the A14B model - [x] Checkpoints of the A14B model - [x] ComfyUI integration - [x] Diffusers integration
  • Wan2.2 Text-Image-to-Video
- [x] Multi-GPU Inference code of the 5B model - [x] Checkpoints of the 5B model - [x] ComfyUI integration - [x] Diffusers integration

Run Wan2.2

#### Installation
Clone the repo:

sh
git clone https://github.com/Wan-Video/Wan2.2.git
cd Wan2.2

Install dependencies:

sh
# Ensure torch >= 2.4.0
pip install -r requirements.txt

#### Model Download

| Models | Download Links | Description |
|--------------------|---------------------------------------------------------------------------------------------------------------------------------------------|-------------|
| T2V-A14B | 🤗 Huggingface 🤖 ModelScope | Text-to-Video MoE model, supports 480P & 720P |
| I2V-A14B | 🤗 Huggingface 🤖 ModelScope | Image-to-Video MoE model, supports 480P & 720P |
| TI2V-5B | 🤗 Huggingface 🤖 ModelScope | High-compression VAE, T2V+I2V, supports 720P |

> 💡Note:
> The TI2V-5B model supports 720P video generation at 24 FPS.

Download models using huggingface-cli:
`` sh
pip install "huggingface_hub[cli]"
huggingface-cli download Wan-AI/Wan2.2-TI2V-5B --local-dir ./Wan2.2-TI2V-5B

code
Download models using modelscope-cli:
sh
pip install modelscope
modelscope download Wan-AI/Wan2.2-TI2V-5B --local_dir ./Wan2.2-TI2V-5B
code
#### Run Text-Image-to-Video Generation


This repository supports the Wan2.2-TI2V-5B Text-Image-to-Video model and can support video generation at 720P resolutions.


  • Single-GPU Text-to-Video inference
sh python generate.py --task ti2v-5B --size 1280*704 --ckpt_dir ./Wan2.2-TI2V-5B --offload_model True --convert_model_dtype --t5_cpu --prompt "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage"
code
> 💡Unlike other tasks, the 720P resolution of the Text-Image-to-Video task is 1280*704 or 704*1280.

> This command can run on a GPU with at least 24GB VRAM (e.g, RTX 4090 GPU).


> 💡If you are running on a GPU with at least 80GB VRAM, you can remove the --offload_model True, --convert_model_dtype and --t5_cpu options to speed up execution.


  • Single-GPU Image-to-Video inference
sh python generate.py --task ti2v-5B --size 1280*704 --ckpt_dir ./Wan2.2-TI2V-5B --offload_model True --convert_model_dtype --t5_cpu --image examples/i2v_input.JPG --prompt "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside."
code
> 💡If the image parameter is configured, it is an Image-to-Video generation; otherwise, it defaults to a Text-to-Video generation.

> 💡Similar to Image-to-Video, the size` parameter represents the area of the generated video, with the aspect ratio following that of the original input image.


  • Multi-GPU inference using FSDP + DeepSpeed Ulysses
sh torchrun --nproc_per_node=8 generate.py --task ti2v-5B --size 1280*704 --ckpt_dir ./Wan2.2-TI2V-5B --dit_fsdp --t5_fsdp --ulysses_size 8 --image examples/i2v_input.JPG --prompt "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The
View official source
Join our Telegram