Updated: Sep 29, 2025
base model
Originally posted: https://wan.video/
Seamless audio-visual sync
Experience synchronized sound and visuals, with high-fidelity voices, ASMR, ambient sounds, music, multilingual support.
Richer video dynamics
Generate cinematic 10-second 1080P 24fps videos with richer temporal-spatial detail, full storytelling capability.
Accurate text in images
Bring your visuals to life with stunning aesthetics and realistic textures, precise text, and structured graphics.
Instruction-based editing
A dialogue-driven editing model for flexible single-image or multi-image refinement and creation.
Visual reasoning power
Unlock advanced natural language understanding and instruction following, creating images or videos from input.