今日は何をつくりますか？

Up to 30s multi-reference video with native audio

Cinematic multi-reference video up to 30s with native audio

Multi-reference (image, video, audio) with native audio

Realistic world & audio simulation

First/last frame control with multimodal references

Realistic visuals with native audio

Cinematic visuals with native audio and lip-sync

Flexible 3–15s clips in five aspect ratios, budget-friendly