Cost-Effective
Streamlined and affordable, reducing creator expenses while offering more output options.
One prompt, audio and video match all the way through.
Try Wan 2.5 Today • Starting at $5/month
More affordable and faster than Google Veo3 — Wan 2.5 makes audio-embedded video generation efficient and accessible.
Streamlined and affordable, reducing creator expenses while offering more output options.
Generate fully synchronized video with audio and lip-sync from a single prompt — no extra recording or alignment needed.
Reliable handling of multiple languages, including Chinese prompts, for synchronized outputs.
Produce videos up to 10 seconds in 6 aspect ratios — more freedom for storytelling and publishing.
Upload your own audio or let Wan 2.5 generate one — plug-and-play simplicity.
Turn text prompts into fully animated, synchronized video clips.
Animate still images into smooth, realistic video sequences.
Generate stunning still images directly from descriptive text prompts.
Quick-turnaround mode for shorter clips with faster processing.
Accelerated conversion of images into video with optimized speed.
Yes. Video-to-video maps lip-sync and expressions onto a silent clip while preserving identity and scene context.
Up to 10 minutes per generation.
Multiple languages and various dialects are supported and can be mixed within one clip. Heads-up: Rapid switching within the same clip can reduce alignment stability.
Yes. Wan 2.5 supports uploading a voice track to drive lip-sync and pacing.
To use Wan 2.5 in ComfyUI, load the Wan 2.5 custom node from the model library, connect your audio track and video input, then run the workflow. You can adjust lip-sync precision, pacing, and expression controls directly in the ComfyUI workflow editor.
Wan 2.5 now in Promptus and start creating AI-powered videos in seconds.