H3 Prompt Writing
Workflow
- Identify the input mode: T2VA, I2VA, FL2VA, L2VA, or full-reference Ref2VA.
- For base text/keyframe modes, read
references/base-en.txt and follow its final prompt structure.
- For full-reference mode, read
references/ref-en.txt and follow its six-section rewrite format.
- Preserve the exact field names, section order, labels, and timing notation from the selected guide.
Base Modes
- T2VA: build the full audiovisual timeline from text.
- I2VA: start from the first frame and develop forward from it.
- FL2VA: describe the continuous path between the first and last frames.
- L2VA: infer a plausible opening and converge to the supplied last frame.
Use integrated_multimodal_description, overall_soundscape, and non_diegetic_music in the order shown in references/base-en.txt.
Full-Reference Mode
Ref2VA rewrites use subject_definitions, summary, retention_analysis, detailed_description, overall_soundscape, and non_diegetic_music in that order. Reference labels stay consistent across all sections.
Read references/ref-en.txt for label rules, retention analysis, and complete examples.
Output Rules
- Write rewrite sections in English; preserve dialogue, lyrics, and visible scene text in their original language.
- Describe each shot by composition, subjects, environment, actions, camera, sound, and the exact point where referenced content appears.
- Avoid plot summaries, unresolved reference labels, and timing that does not match the requested duration.
Tips for Better Results
- Always match the total duration of the description to the requested video length (4–15 seconds).
- Keep reference labels consistent (e.g.
<Picture 1>, <Video 1>, <Audio 1>) across every section.
- Prefer concrete visual and audio details over abstract words like "cinematic" or "beautiful".
- When using keyframes (I2VA / FL2VA / L2VA), clearly state how the first and/or last frame connects to the timeline.
1---
2name: h3-prompt-writing
3description: Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal requests into H3 prompt structures, composing integrated_multimodal_description, overall_soundscape, and non_diegetic_music, aligning keyframes, or defining reference labels for images, videos, and audio.
4compatibility: Portable to any agent that can read local files — no external API calls, MiniMax Hub tools, or proprietary runtime required. The agents/openai.yaml file only adds optional ChatGPT/Codex UI metadata; it does not restrict the skill to OpenAI agents.
5metadata:
6 source: https://skillmd.com/skills/minimax-ai/h3-prompt-writing
7---
8
9# H3 Prompt Writing
10
11## Workflow
12
131. Identify the input mode: T2VA, I2VA, FL2VA, L2VA, or full-reference Ref2VA.
142. For base text/keyframe modes, read `references/base-en.txt` and follow its final prompt structure.
153. For full-reference mode, read `references/ref-en.txt` and follow its six-section rewrite format.
164. Preserve the exact field names, section order, labels, and timing notation from the selected guide.
17
18## Base Modes
19
20- T2VA: build the full audiovisual timeline from text.
21- I2VA: start from the first frame and develop forward from it.
22- FL2VA: describe the continuous path between the first and last frames.
23- L2VA: infer a plausible opening and converge to the supplied last frame.
24
25Use `integrated_multimodal_description`, `overall_soundscape`, and `non_diegetic_music` in the order shown in `references/base-en.txt`.
26
27## Full-Reference Mode
28
29Ref2VA rewrites use `subject_definitions`, `summary`, `retention_analysis`, `detailed_description`, `overall_soundscape`, and `non_diegetic_music` in that order. Reference labels stay consistent across all sections.
30
31Read `references/ref-en.txt` for label rules, retention analysis, and complete examples.
32
33## Output Rules
34
35- Write rewrite sections in English; preserve dialogue, lyrics, and visible scene text in their original language.
36- Describe each shot by composition, subjects, environment, actions, camera, sound, and the exact point where referenced content appears.
37- Avoid plot summaries, unresolved reference labels, and timing that does not match the requested duration.
38## Tips for Better Results
39- Always match the total duration of the description to the requested video length (4–15 seconds).
40- Keep reference labels consistent (e.g. `<Picture 1>`, `<Video 1>`, `<Audio 1>`) across every section.
41- Prefer concrete visual and audio details over abstract words like "cinematic" or "beautiful".
42- When using keyframes (I2VA / FL2VA / L2VA), clearly state how the first and/or last frame connects to the timeline.