Models / Hailuo (MiniMax) / Reference to video
Hailuo (MiniMax) reference to video prompting guide
Last checked 2026-10-11Hailuo / MiniMax H3 · MiniMax H3 (hailuo3: t2v/i2v/r2v/v2v), H3 Max (h3_max: t2v/i2v first+last), Hailuo 2.3
How to prompt Hailuo (MiniMax) in reference-to-video mode. Every point links its source; community tips are marked. Your agent gets the same guide through the Atlas MCP (get_guide).
Prompt structure
ref jobs→subject with ref→action→camera amplitude speed→constraints→soundscape
- Three fields: integrated_multimodal_description (visuals, action, shots, dialogue on the timeline), overall_soundscape (1–4 sentences), non_diegetic_music (or N/A). source ↗
What the text should describe
- Cite 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 files total; audio refs need an image or video ref. source ↗
- Assign a job to every reference: 'Use Image 1 for the overall mood, location and film texture; Image 2 for the talent; Image 3 for the bag; Image 4 for the closing brand mark.' source ↗
- Runway hailuo3: promptImage without position = reference images (up to 9); cannot mix with first/last keyframe mode. source ↗
What not to describe
- Don't pass a literal opening frame as a reference — it belongs on Image to Video. source ↗
Camera vocabulary
- Camera = motion type + amplitude + speed as a sentence: 'The camera pushes in with small amplitude at slow speed toward ...'. Types: zoom, push/pull, pan, truck, tilt, pedestal, arc, tracking, static, shake, POV, roll. source ↗
Responds well to
- On-screen text in double quotes, verbatim. source ↗
Duration and limits
- H3 Reference to Video: up to 9 images, 3 videos (2–15 s), 3 audio, 12 files; Runway hailuo3 768p/2k, h3_max 480p/768p. source ↗
Multi-shot
- [Shot 1] (no timestamp), then '[Shot 2] At 00:03.500, the camera cuts to ...' with strictly increasing times. source ↗
Avoid and failure modes
- Use a cut only for new information; small angle changes = camera motion. source ↗
Negative prompt
Supported via .
Real prompts, credited
Use Image 1 as a locked identity and wardrobe reference for the man. Use Image 2 for the location, the wet ground, and the light. 16:9, one continuous handheld shot, no cuts. The camera follows him from behind at shoulder height as he walks the length of the loading dock away from us, then he stops, turns his head to look back over his left shoulder, and holds. Preserve his face, beard, and the olive canvas jacket exactly as in Image 1 ... Audio: boots on wet concrete, the sodium ballast humming, distant dock machinery, one gull. No music.
Next
All Hailuo (MiniMax) modesHailuo (MiniMax) model, prices & shotsFrom $0.1/s · pricesSeedance reference to videoKling reference to videoVeo reference to videoWan reference to video