Add Wan InfiniteTalk (3 Modes)

We’re planning to add Wan InfiniteTalk with 3 creation modes to expand talking-video workflows.

This model is designed for audio-driven video generation with strong lip sync, more natural head, body, and facial motion, and better identity consistency across longer results. It’s a strong option for creators who want more flexible and expressive talking videos.

Key benefits:

• Audio-driven talking video generation

• Accurate lip sync

• More natural facial and body motion

• Better identity consistency

• Works well for longer video workflows