Minimax Hailuo V1 | Subject to Video

Minimax Hailuo S2V-01 turns a single subject image into a short, subject-focused video. Provide a clear, front-facing portrait and a concise 10–30 word prompt describing action, emotion, and setting to guide subtle to moderate motion (e.g., head turns, expressions, small gestures). The model prioritizes identity consistency across frames and works best on close-ups with simple backgrounds. You can suggest camera cues and styles, and enable prompt optimization for clearer results. It’s ideal for expressive portraits, social clips, avatars, and profile cards. Keep prompts unambiguous and avoid conflicting directions; complex scenes, multi-subject shots, and detailed backgrounds are less reliable.