Models / Hailuo (MiniMax) / Start & end frame

Hailuo (MiniMax) start & end frame prompting guide

How to prompt Hailuo (MiniMax) in start/end frame mode. Every point links its source; community tips are marked. Your agent gets the same guide through the Atlas MCP (get_guide).

Prompt structure

path between frames→camera→soundscape→music

• 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

• FL2VA works best as a single shot describing the path between frames; L2VA invents a plausible earlier state and lands on the image. source ↗
• I2VA develops forward from the first frame; FL2VA describes one continuous path; prompts state how pictures align to the timeline (Picture 1 at 0.00 s). 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 .

Next

Sources

• fal.ai/models/minimax/h3/reference-to-video/api
• huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/docs/VIDEO_PROMPT_WRITING_GUIDE_base_en.md