New:New: Wan2.1 AI Video Generation Model

Transform Images to Videos with Wan2.1

State-of-the-art AI model for generating high-quality 720P videos from images and text prompts

HD Video Generation

Generate 720P high-quality videos with smooth and natural motion and rich details.

Text to Video

Create amazing video content from simple text descriptions that match your imagination.

Image to Video

Transform static images into dynamic videos, bringing your creative ideas to life.

Advanced AI Video Generation

Discover the powerful capabilities of Wan2.1 that make it the leading choice for AI video generation

Image to Video. Transform static images into dynamic videos

Upload any image and watch as Wan2.1 brings it to life with natural motion and realistic animation.

Fast Generation

Generate videos in seconds, not minutes or hours, making your creative workflow more efficient.

Easy to Use

Simple interface that requires no technical expertise - just upload an image or enter text.

Consistent Results

Reliable output quality that maintains the essence of your input while adding natural motion.

Text to Video. Create videos from text descriptions

Simply describe what you want to see, and Wan2.1 will generate a high-quality video matching your description.

Versatile Applications

Perfect for marketing, social media, education, entertainment, and more.

Customizable

Fine-tune your results with adjustable parameters to get exactly the video you want.

Innovative Technology

Built on cutting-edge AI research to deliver state-of-the-art video generation capabilities.

High Quality. Enjoy 720P resolution with smooth motion

All videos are generated in 720P resolution with 16 frames, ensuring smooth motion and high visual quality.

Fast Generation

Generate videos in seconds, not minutes or hours, making your creative workflow more efficient.

Consistent Results

Reliable output quality that maintains the essence of your input while adding natural motion.

Innovative Technology

Built on cutting-edge AI research to deliver state-of-the-art video generation capabilities.

Feature Showcase

Explore the powerful capabilities of our platform through these videos to see how you can enhance your productivity

Open Source Resources

We release the code and weights for Wan2.1, a comprehensive and open suite of video foundation models designed to push the boundaries of video generation.

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.

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.

Model List

Wan2.1-T2V-1.3B

480P

Lightweight Text-to-Video model supporting almost all consumer-grade GPUs, requiring only 8.19GB VRAM to produce a 5-second 480P video.

Wan2.1-I2V-14B

480P

Image-to-Video model supporting both 480P and 720P resolutions, outperforming leading closed-source models and all existing open-source models.

Wan2.1-I2V-14B

720P

Image-to-Video model supporting both 480P and 720P resolutions, outperforming leading closed-source models and all existing open-source models.

Wan2.1-T2V-14B

480P-720P

Text-to-Video model setting a new SOTA performance among both open-source and closed-source models, supporting both Chinese and English text generation.

Technical Report

Stay tuned for the upcoming release of our comprehensive technical report for more details.

Built upon the mainstream diffusion transformer paradigm, Wan2.1 achieves significant advancements in generative capabilities through a series of innovations, including our novel spatio-temporal variational autoencoder (VAE), scalable pre-training strategies, large-scale data construction, and automated evaluation metrics.

Frequently Asked Questions

Common questions about Wan2.1 AI video generation

What is Wan2.1?

Wan2.1 is a state-of-the-art AI model that can generate high-quality 720P videos from images or text descriptions. It uses advanced machine learning techniques to create natural motion and realistic animations.

How do I use Wan2.1?

Simply upload an image or enter a text description of what you want to see, then click 'Generate'. Wan2.1 will process your input and create a video in seconds.

How long are the generated videos?

Currently, Wan2.1 generates videos with 16 frames, which translates to short clips. This is ideal for creating animations, GIFs, and short social media content.

Can I use the generated videos commercially?

Yes, with our Pro and Enterprise plans, you receive commercial usage rights for all videos generated through our platform.