Hailuo AIモデルシリーズ
Hailuo is MiniMax's AI video generation model that turns text or image prompts into smooth, cinematic, physically believable clips with strong motion and character consistency.
すべてのHailuoモデル

minimax/hailuo-02-fl2v
MiniMax's first-and-last-frame model for morphs and storyboard transitions that land on a chosen end image. It bridges the frames in a 6 or 10 second clip at 768p, or a 6 second clip at 1080p.

minimax/hailuo-02-i2v
MiniMax's image-to-video model for animating a product photo or a wide scene with physical motion. It makes a 6 or 10 second clip at 512p or 768p, and a 6 second clip at 1080p.

minimax/hailuo-2.3-fast-i2v
MiniMax's faster image-to-video model for rapid drafts and batch clips from one still. The image stays the opening frame, in a 6 or 10 second clip at 768p, or a 6 second clip at 1080p.

minimax/hailuo-2.3-i2v
MiniMax's image-to-video model for animating a portrait or illustrated still with facial detail and physical motion. The image stays the opening frame, in a 6 or 10 second clip at 768p, or a 6 second clip at 1080p.

minimax/hailuo-02-t2v
MiniMax's text-to-video model for product shots, sports, and wide scenes that need physical motion and close prompt following. It makes a 6 or 10 second clip at 768p, and a 6 second clip at 1080p.

minimax/hailuo-2.3-t2v
MiniMax's text-to-video model for character performance, stylized looks, and physical action from a prompt. It makes a 6 or 10 second clip at 768p, and a 6 second clip at 1080p.




