wangame_zelda

Wan2.1

<p align="center"> <img src="assets/logo.png" width="400"/> <p> <p align="center"> 💜 <a href=""><b>Wan</b></a> &nbsp&nbsp ｜ &nbsp&nbsp 🖥️ <a href="https://github.com/Wan-Video/Wan2.1">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="">Paper (Coming soon)</a> &nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://wanxai.com">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/p5XbdQV7">Discord</a>&nbsp&nbsp <br>

---

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

In this repository, we present Wan2.1, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation. Wan2.1 offers these key features:

• 👍 SOTA Performance: Wan2.1 consistently outperforms existing open-source models and state-of-the-art commercial solutions across multiple benchmarks.
• 👍 Supports Consumer-grade GPUs: The T2V-1.3B model requires only 8.19 GB VRAM, making it compatible with almost all consumer-grade GPUs. It can generate a 5-second 480P video on an RTX 4090 in about 4 minutes (without optimization techniques like quantization). Its performance is even comparable to some closed-source models.
• 👍 Multiple Tasks: Wan2.1 excels in Text-to-Video, Image-to-Video, Video Editing, Text-to-Image, and Video-to-Audio, advancing the field of video generation.
• 👍 Visual Text Generation: Wan2.1 is the first video model capable of generating both Chinese and English text, featuring robust text generation that enhances its practical applications.
• 👍 Powerful Video VAE: Wan-VAE delivers exceptional efficiency and performance, encoding and decoding 1080P videos of any length while preserving temporal information, making it an ideal foundation for video and image generation.

This repo contains our I2V-14B model, which is capable of generating 480P videos, offering advantages in terms of fast generation and excellent quality.

Video Demos

<div align="center"> <video width="80%" controls> <source src="https://cloud.video.taobao.com/vod/Jth64Y7wNoPcJki_Bo1ZJTDBvNjsgjlVKsNs05Fqfps.mp4" type="video/mp4"> Your browser does not support the video tag. </video> </div>

🔥 Latest News!!

• Feb 25, 2025: 👋 We've released the inference code and weights of Wan2.1.

📑 Todo List

• Wan2.1 Text-to-Video
  • Multi-GPU Inference code of the 14B and 1.3B models
  • Checkpoints of the 14B and 1.3B models
  • Gradio demo
  • Diffusers integration
  • ComfyUI integration
• Wan2.1 Image-to-Video
  • Multi-GPU Inference code of the 14B model
  • Checkpoints of the 14B model
  • Gradio demo
  • Diffusers integration
  • ComfyUI integration

Quickstart

Installation

Clone the repo:

git clone https://github.com/Wan-Video/Wan2.1.git
cd Wan2.1

Install dependencies:

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

Model Download

💡Note: The 1.3B model is capable of generating videos at 720P resolution. However, due to limited training at this resolution, the results are generally less stable compared to 480P. For optimal performance, we recommend using 480P resolution.

Download models using 🤗 huggingface-cli:

pip install "huggingface_hub[cli]"
huggingface-cli download Wan-AI/Wan2.1-I2V-14B-480P-Diffusers --local-dir ./Wan2.1-I2V-14B-480P-Diffusers

Download models using 🤖 modelscope-cli:

pip install modelscope
modelscope download Wan-AI/Wan2.1-I2V-14B-480P-Diffusers --local_dir ./Wan2.1-I2V-14B-480P-Diffusers

Run Image-to-Video Generation

Similar to Text-to-Video, Image-to-Video is also divided into processes with and without the prompt extension step. The specific parameters and their corresponding settings are as follows:

<table> <thead> <tr> <th rowspan="2">Task</th> <th colspan="2">Resolution</th> <th rowspan="2">Model</th> </tr> <tr> <th>480P</th> <th>720P</th> </tr> </thead> <tbody> <tr> <td>i2v-14B</td> <td style="color: green;">❌</td> <td style="color: green;">✔️</td> <td>Wan2.1-I2V-14B-720P</td> </tr> <tr> <td>i2v-14B</td> <td style="color: green;">✔️</td> <td style="color: red;">❌</td> <td>Wan2.1-T2V-14B-480P</td> </tr> </tbody> </table>

(1) Without Prompt Extention

• Single-GPU inference

python generate.py --task i2v-14B --size 832*480 --ckpt_dir ./Wan2.1-I2V-14B-480P --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."

💡For the Image-to-Video task, 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 + xDiT USP

pip install "xfuser>=0.4.1"
torchrun --nproc_per_node=8 generate.py --task i2v-14B --size 832*480 --ckpt_dir ./Wan2.1-I2V-14B-480P --image examples/i2v_input.JPG --dit_fsdp --t5_fsdp --ulysses_size 8 --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."

Wan can also be run directly using 🤗 Diffusers!

import torch
import numpy as np
from diffusers import AutoencoderKLWan, WanImageToVideoPipeline
from diffusers.utils import export_to_video, load_image
from transformers import CLIPVisionModel

# Available models: Wan-AI/Wan2.1-I2V-14B-480P-Diffusers, Wan-AI/Wan2.1-I2V-14B-720P-Diffusers
model_id = "Wan-AI/Wan2.1-I2V-14B-480P-Diffusers"
image_encoder = CLIPVisionModel.from_pretrained(model_id, subfolder="image_encoder", torch_dtype=torch.float32)
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
pipe = WanImageToVideoPipeline.from_pretrained(model_id, vae=vae, image_encoder=image_encoder, torch_dtype=torch.bfloat16)
pipe.to("cuda")

image = load_image(
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"
)
max_area = 480 * 832
aspect_ratio = image.height / image.width
mod_value = pipe.vae_scale_factor_spatial * pipe.transformer.config.patch_size[1]
height = round(np.sqrt(max_area * aspect_ratio)) // mod_value * mod_value
width = round(np.sqrt(max_area / aspect_ratio)) // mod_value * mod_value
image = image.resize((width, height))
prompt = (
    "An astronaut hatching from an egg, on the surface of the moon, the darkness and depth of space realised in "
    "the background. High quality, ultrarealistic detail and breath-taking movie-like camera shot."
)
negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards"

output = pipe(
    image=image, prompt=prompt, negative_prompt=negative_prompt, height=height, width=width, num_frames=81, guidance_scale=5.0
).frames[0]
export_to_video(output, "output.mp4", fps=16)

(2) Using Prompt Extention

Run with local prompt extention using Qwen/Qwen2.5-VL-7B-Instruct:

python generate.py --task i2v-14B --size 832*480 --ckpt_dir ./Wan2.1-I2V-14B-480P --image examples/i2v_input.JPG --use_prompt_extend --prompt_extend_model Qwen/Qwen2.5-VL-7B-Instruct --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."

Run with remote prompt extention using dashscope:

DASH_API_KEY=your_key python generate.py --task i2v-14B --size 832*480 --ckpt_dir ./Wan2.1-I2V-14B-480P --image examples/i2v_input.JPG --use_prompt_extend --prompt_extend_method 'dashscope' --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."

(3) Runing local gradio

cd gradio
# if one only uses 480P model in gradio
DASH_API_KEY=your_key python i2v_14B_singleGPU.py --prompt_extend_method 'dashscope' --ckpt_dir_480p ./Wan2.1-I2V-14B-480P

# if one only uses 720P model in gradio
DASH_API_KEY=your_key python i2v_14B_singleGPU.py --prompt_extend_method 'dashscope' --ckpt_dir_720p ./Wan2.1-I2V-14B-720P

# if one uses both 480P and 720P models in gradio
DASH_API_KEY=your_key python i2v_14B_singleGPU.py --prompt_extend_method 'dashscope' --ckpt_dir_480p ./Wan2.1-I2V-14B-480P --ckpt_dir_720p ./Wan2.1-I2V-14B-720P

Manual Evaluation

We conducted extensive manual evaluations to evaluate the performance of the Image-to-Video model, and the results are presented in the table below. The results clearly indicate that Wan2.1 outperforms both closed-source and open-source models.

<div align="center"> <img src="assets/i2v_res.png" alt="" style="width: 80%;" /> </div>

Computational Efficiency on Different GPUs

We test the computational efficiency of different Wan2.1 models on different GPUs in the following table. The results are presented in the format: Total time (s) / peak GPU memory (GB).

<div align="center"> <img src="assets/comp_effic.png" alt="" style="width: 80%;" /> </div>

The parameter settings for the tests presented in this table are as follows: (1) For the 1.3B model on 8 GPUs, set --ring_size 8 and --ulysses_size 1; (2) For the 14B model on 1 GPU, use --offload_model True; (3) For the 1.3B model on a single 4090 GPU, set --offload_model True --t5_cpu; (4) For all testings, no prompt extension was applied, meaning --use_prompt_extend was not enabled.

---

Introduction of Wan2.1

Wan2.1 is designed on the mainstream diffusion transformer paradigm, achieving significant advancements in generative capabilities through a series of innovations. These include our novel spatio-temporal variational autoencoder (VAE), scalable training strategies, large-scale data construction, and automated evaluation metrics. Collectively, these contributions enhance the model’s performance and versatility.

(1) 3D Variational Autoencoders

We propose a novel 3D causal VAE architecture, termed Wan-VAE specifically designed for video generation. By combining multiple strategies, we improve spatio-temporal compression, reduce memory usage, and ensure temporal causality. Wan-VAE demonstrates significant advantages in performance efficiency compared to other open-source VAEs. Furthermore, our Wan-VAE can encode and decode unlimited-length 1080P videos without losing historical temporal information, making it particularly well-suited for video generation tasks.

<div align="center"> <img src="assets/video_vae_res.jpg" alt="" style="width: 80%;" /> </div>

(2) Video Diffusion DiT

Wan2.1 is designed using the Flow Matching framework within the paradigm of mainstream Diffusion Transformers. Our model's architecture uses the T5 Encoder to encode multilingual text input, with cross-attention in each transformer block embedding the text into the model structure. Additionally, we employ an MLP with a Linear layer and a SiLU layer to process the input time embeddings and predict six modulation parameters individually. This MLP is shared across all transformer blocks, with each block learning a distinct set of biases. Our experimental findings reveal a significant performance improvement with this approach at the same parameter scale.

<div align="center"> <img src="assets/video_dit_arch.jpg" alt="" style="width: 80%;" /> </div>

Data

We curated and deduplicated a candidate dataset comprising a vast amount of image and video data. During the data curation process, we designed a four-step data cleaning process, focusing on fundamental dimensions, visual quality and motion quality. Through the robust data processing pipeline, we can easily obtain high-quality, diverse, and large-scale training sets of images and videos.

Comparisons to SOTA

We compared Wan2.1 with leading open-source and closed-source models to evaluate the performace. Using our carefully designed set of 1,035 internal prompts, we tested across 14 major dimensions and 26 sub-dimensions. We then compute the total score by performing a weighted calculation on the scores of each dimension, utilizing weights derived from human preferences in the matching process. The detailed results are shown in the table below. These results demonstrate our model's superior performance compared to both open-source and closed-source models.

Citation

If you find our work helpful, please cite us.

@article{wan2.1,
    title   = {Wan: Open and Advanced Large-Scale Video Generative Models},
    author  = {Wan Team},
    journal = {},
    year    = {2025}
}

License Agreement

The models in this repository are licensed under the Apache 2.0 License. We claim no rights over the your generate contents, granting you the freedom to use them while ensuring that your usage complies with the provisions of this license. You are fully accountable for your use of the models, which must not involve sharing any content that violates applicable laws, causes harm to individuals or groups, disseminates personal information intended for harm, spreads misinformation, or targets vulnerable populations. For a complete list of restrictions and details regarding your rights, please refer to the full text of the license.

Acknowledgements

We would like to thank the contributors to the SD3, Qwen, umt5-xxl, diffusers and HuggingFace repositories, for their open research.

Contact Us

If you would like to leave a message to our research or product teams, feel free to join our Discord or WeChat groups!