Hunyuan Video

Industry’s Best Performance
Surpassing Commercial Models
HunyuanVideo represents the most parameter-rich and high-performce text-to-video model currently available in the open-source domain. With 13 billion parameters, it is capable of generating videos that exhibit high physical accuracy and scene consistency, thereby actualizing conceptual visions and fostering creative expression.
Cinematic Video Quality, Artistic Experience
Experience the cinematic feel with just a touch of a button, and switch freely

Trendy Waves, Action, Expression Driven
As if giving machines a lively eye and a keen heart. It captures nuanced human movements and expressions in real-time, accurately parsing every gesture, movements, and subtle emotional expressions, and converting them into command beacons for the intelligent device to move forward.