WAN 2.1

image to video

An image and video generation model based on Alibaba's advanced technology. It creates high-quality videos from a single image that maintain consistency and detail while featuring camera work and natural movements.

Text Friendly
Commercial Use

Input

First frame*

Drag and drop media files from your computer, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted: .jpg, .jpeg, .png, .webp

Tail frame image

Drag and drop media files from your computer, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted: .jpg, .jpeg, .png, .webp

Result

Idle

Ready to Generate

Configure your inputs and click run to generate an image preview.

WAN 2.1 Model Introduction

Model Overview

WAN 2.1 is an image-to-video generation model developed by Alibaba Tongyi Lab, which leverages cutting-edge AI technology. From a single still image provided, it generates a smooth, consistent, high-quality video of up to 5 seconds while fully preserving the worldview, characters, and texture. By adopting its original "Wan-VAE" and the latest diffusion transformer technology, it overcomes issues such as physical law disruptions and unnatural deformities that have been challenges for conventional models. It even depicts subtle facial expressions of characters, dynamic camera work, and intricate changes in light and shadow with cinematic realism. It also excels at text reproducibility, enabling animation of text such as signs and logos in videos without distortion. It is also compatible with commercial use, delivering overwhelming expressive power and improved production efficiency for advertising production, creative design, entertainment, and video content creation for social media.

Pricing

ResolutionCredits Consumed
480p(credits/s)6
720p(credits/s)12

Technical Specifications

ParameterSpecification
Core Capabilityimage_to_video
Resolution480p,720p
Aspect Ratio16:9,9:16,1:1
Duration5
License