WAN 2.5

image to video

An enhanced version of the expressive WAN model, which generates videos from still images while maintaining character consistency and natural movement, and also supports lip-syncing and basic audio generation.

Text Friendly
Audio Support
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

Result

Idle

Ready to Generate

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

WAN 2.5 Model Introduction

Model Overview

WAN 2.5 is an enhanced version of the WAN series, which has greatly evolved the expressive power of video generation. By combining static images and text input, it reproduces extremely natural actions and camera movements based on the laws of physics while faithfully maintaining the characters and details of the original image.

In particular, it has improved character consistency and lip-sync (mouth synchronization) performance, and shines when creating story-driven content featuring people. It also supports the simultaneous generation of basic audio (voice and sound effects) that matches the video. It delivers cinematic, immersive video expression in a single stop.

As a powerful assistant for video production that requires high-quality storytelling, such as advertising creativity, entertainment, and promotional videos, it intuitively brings creators' imaginations to life.

Pricing

ResolutionCredits Consumed
480p(credits/s)6
720p(credits/s)12
1080p(credits/s)18

Technical Specifications

ParameterSpecification
Core Capabilityimage_to_video
Resolution480p,720p,1080p
Aspect Ratio16:9,9:16,1:1
Duration5,10
License