Models / Hailuo (MiniMax)
How to prompt Hailuo (MiniMax)
Last checked 2026-10-11Price checked 2026-10-11Hailuo / MiniMax H3
6 of 6 generation modes have a sourced guide. Modes the vendor docs don't confirm are shown greyed out, not guessed. Cheapest supported price: $0.1/s (Hailuo 3 (via Runway API) via Runway API).
Text to videotext-to-videoT2VA has no image-alignment instruction and begins directly with the three fields; build the whole audiovisual timeline from text.3 examples · checked 2026-10-11Image to videoimage-to-video (start frame)Open with: 'For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.' Then establis1 examples · checked 2026-10-11Start & end framestart/end frameFL2VA works best as a single shot describing the path between frames; L2VA invents a plausible earlier state and lands on the image.1 examples · checked 2026-10-11Reference to videoreference-to-videoCite refs as 'Image 1', 'Image 2', 'Video 1', 'Audio 1' by list order. Up to 9 images, 3 videos (2–15 s), 3 audio, 12 1 examples · checked 2026-10-11Video to videovideo-to-videoRefer to uploads by modality and order: Image 1, Video 1, Audio 1. Give each clip a job ('Match the camera move in Video 1', 'Make the sub1 examples · checked 2026-10-11Lip synclip sync / dialogueStable speaker IDs (S1), (S2) across shots; spoken words verbatim inside the dialogue tag; voiceover: 'says in an off-screen voiceover' and st1 examples · checked 2026-10-11