Wan2.2 I2V A14B Lightning Diffusers

提供商magespace
分类text-to-video
许可证apache-2.0
下载量49.1K
星标0

简介

Wan2.2 I2V A14B Lightning 是一个高性能的图生视频模型，专门针对推理速度进行了‘闪电级’优化。它能将静态图像转化为高质量的动态视频，在保持画面一致性的同时，极大地降低了生成时间。对于习惯使用 Diffusers 库的开发者来说，该模型无缝集成到现有工作流中，上手门槛极低。相比于传统的视频生成模型，它在算力消耗和出片速度之间取得了极佳平衡，非常适合需要快速迭代视觉内容的创作者或需要将视频生成能力集成到 App 中的开发者。

核心亮点

  • 图生视频能力强，画面动态自然且一致性高
  • Lightning 优化大幅提升生成速度，降低显存压力
  • 原生支持 Diffusers 库，开发者部署极其便捷
  • Apache-2.0 开源协议，商业化应用灵活度高

使用方法

安装依赖
# 安装 Hugging Face transformers
pip install transformers torch
SDK 使用
# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("magespace/Wan2.2-I2V-A14B-Lightning-Diffusers")
tokenizer = AutoTokenizer.from_pretrained("magespace/Wan2.2-I2V-A14B-Lightning-Diffusers")

Hugging Face 下载

我们推荐使用命令行或者 Hugging Face Hub SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 huggingface_hub：

操作指引 
pip install -U huggingface_hub

命令行下载

下载完整模型库

下载完整模型库 
huggingface-cli download magespace/Wan2.2-I2V-A14B-Lightning-Diffusers

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例）

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例） 
huggingface-cli download magespace/Wan2.2-I2V-A14B-Lightning-Diffusers config.json --local-dir ./dir

更多命令行下载选项，可参见官方文档

SDK 下载

SDK 下载 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('magespace/Wan2.2-I2V-A14B-Lightning-Diffusers')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://huggingface.co/magespace/Wan2.2-I2V-A14B-Lightning-Diffusers

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/magespace/Wan2.2-I2V-A14B-Lightning-Diffusers

模型文件托管在 Hugging Face Hub，使用 HF CLI / SDK / Git 直接下载，不经过本站。

PyTorch / Transformers 使用

安装 Transformers

安装 Transformers 
pip install -U transformers torch

模型加载和推理

模型加载和推理 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('magespace/Wan2.2-I2V-A14B-Lightning-Diffusers')
tokenizer = AutoTokenizer.from_pretrained('magespace/Wan2.2-I2V-A14B-Lightning-Diffusers')

完整文档

来源: HuggingFace

---
license: apache-2.0
pipeline_tag: text-to-video
library_name: diffusers
---

Wan2.2 + Lightx2v

<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>

<p align="center">
🔗 <a href="https://huggingface.co/lightx2v/Wan2.2-Lightning"><b>Lightx2v</b></a> — Distilled & optimized Wan2.2 for fast, high-quality 480P / 720P image-to-video generation
</p>
<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 T2V-A14B model, which supports generating 5s videos at both 480P and 720P resolutions. Built with a Mixture-of-Experts (MoE) architecture, it delivers outstanding video generation quality. On our new benchmark Wan-Bench 2.0, the model surpasses leading commercial models across most key evaluation dimensions.

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-T2V-A14B --local-dir ./Wan2.2-T2V-A14B

code
Download models using modelscope-cli:
sh
pip install modelscope
modelscope download Wan-AI/Wan2.2-T2V-A14B --local_dir ./Wan2.2-T2V-A14B
code
#### Run Text-to-Video Generation


This repository supports the Wan2.2-T2V-A14B Text-to-Video model and can simultaneously support video generation at 480P and 720P resolutions.


##### (1) Without Prompt Extension


To facilitate implementation, we will start with a basic version of the inference process that skips the prompt extension step.


  • Single-GPU inference
sh python generate.py --task t2v-A14B --size 1280*720 --ckpt_dir ./Wan2.2-T2V-A14B --offload_model True --convert_model_dtype --prompt "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage."
code
> 💡 This command can run on a GPU with at least 80GB VRAM.

> 💡If you encounter OOM (Out-of-Memory) issues, you can use the --offload_model True, --convert_model_dtype and --t5_cpu options to reduce GPU memory usage.


  • Multi-GPU inference using FSDP + DeepSpeed Ulysses


We use PyTorch FSDP and DeepSpeed Ulysses to accelerate inference.
sh
torchrun --nproc_per_node=8 generate.py --task t2v-A14B --size 1280*720 --ckpt_dir ./Wan2.2-T2V-A14B --dit_fsdp --t5_fsdp --ulysses_size 8 --prompt "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage."
`

##### (2) Using Prompt Extension

Extending the prompts can effectively enrich the details in the generated videos, further enhancing the video quality. Therefore, we recommend enabling prompt extension. We provide the following two methods for prompt extension:

  • Use the Dashscope API for extension.
- Apply for a dashscope.api_key in advance (EN | CN). - Configure the environment variable DASH_API_KEY` to specify the Dashscope API key. For users of Alibaba Cloud's international site, you also need to set the environment var
查看官方来源