MiniMax H3 提示词怎么写

cURL

# 8 seconds, 768p, text only. In JSON the blank line between fields is \n\n.
curl -X POST https://api.apimodels.app/v1/video/generations \
  -H "Authorization: Bearer $APIMODELS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-h3",
    "duration": 8,
    "resolution": "768p",
    "ratio": "16:9",
    "prompt": "integrated_multimodal_description: [Shot 1] Live-action, cinematic, a medium shot frames a narrow late-night ramen bar where a cook in his fifties wipes the wooden counter as steam rises from the pots behind him. The camera pushes in with small amplitude at slow speed as the cook, a man with a low, gravelly voice (S1), looks up toward the door and says: <d>[Chinese] 最后一碗,给你留着呢。</d> [Shot 2] At 00:05.000, the camera cuts to a close-up of a bowl of ramen set down on the counter, chopsticks resting across the rim, with a handwritten sign reading \"营业到两点\" on the wall behind it.\n\noverall_soundscape: Broth bubbles in the pots under a low kitchen hum. The ceramic bowl clinks against the wood, and rain patters faintly outside the door.\n\nnon_diegetic_music: N/A"
  }'
# → { "code": 200, "data": { "taskId": "...", "state": "pending" } }; poll GET /v1/video/generations?task_id=...

Python

import os, requests

prompt = """integrated_multimodal_description: [Shot 1] Live-action, cinematic, a medium shot frames a narrow late-night ramen bar where a cook in his fifties wipes the wooden counter as steam rises from the pots behind him. The camera pushes in with small amplitude at slow speed as the cook, a man with a low, gravelly voice (S1), looks up toward the door and says: <d>[Chinese] 最后一碗,给你留着呢。</d> [Shot 2] At 00:05.000, the camera cuts to a close-up of a bowl of ramen set down on the counter, chopsticks resting across the rim, with a handwritten sign reading "营业到两点" on the wall behind it.

overall_soundscape: Broth bubbles in the pots under a low kitchen hum. The ceramic bowl clinks against the wood, and rain patters faintly outside the door.

non_diegetic_music: N/A"""

r = requests.post(
    "https://api.apimodels.app/v1/video/generations",
    headers={"Authorization": f"Bearer {os.environ['APIMODELS_API_KEY']}"},
    json={"model": "minimax-h3", "duration": 8, "resolution": "768p", "ratio": "16:9", "prompt": prompt},
)
print(r.json())  # then poll GET /v1/video/generations?task_id=...

MiniMax H3 提示词要用英文写吗?

MiniMax 官方指南里,结构化提示词用英文写,但台词、歌词和画面里出现的文字保留原文。所以中文台词在 <d> 里照写中文,中文招牌在双引号里照写中文。

H3 怎么控制第几秒切镜头?

从第二个镜头开始,在开头写切镜时间,例如「[Shot 2] At 00:05.000, the camera cuts to …」。第一个镜头不写时间,切镜时间要递增,而且都要落在你请求的 duration 之内。

怎么让 H3 里的角色说指定的台词?

给角色一个说话人编号,<d> 里只放语言标签和原话:The woman (S1) says: <d>[English] I get off at the next station.</d>。嗓音和语气写在标记外面,同一个角色在每个镜头里都用同一个编号。

在 apimodels.app 上调用必须写成这种结构吗?

不必须。普通描述在每个 H3 模型名上都能用,这套结构是在需要精确控制时间点、台词和声音时用的。想让短提示词被自动扩写,可以用 minimax-h3-max-turbo 的 prompt_expansion_mode。

MiniMax 官方的 H3 提示词指南在哪?

在 GitHub 仓库 MiniMax-AI/MiniMax-H3 的 h3-prompt-writing 技能里,有两份:一份讲文字和关键帧模式,一份讲全参考模式。本页把两份的要点整理出来,并对应到 apimodels.app 上的模型名和字段。