跳转到内容

MiniMax H3 Image to Video

集成

模型 id minimax/h3/image-to-video
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/minimax/h3/image-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Ultra cinematic wide shot: A vast field of burning embers stretches into darkness. Suddenly, an enormous wall of fire races across the ground, sending billions of glowing sparks into the air. The flames twist into a gigantic rotating fire vortex hundreds of feet high. Molten embers, smoke, and liquid fire spiral together, naturally forging the word \"IGNITE\" from blazing flames. The letters burn brighter and brighter before erupting into a colossal shockwave that fills the screen with fire and incandescent particles. Hollywood fire simulation, ultra-realistic VFX, blockbuster title reveal.",
    "duration": 5,
    "resolution": "480P",
    "image": "https://content.doitong.com/dev-api/2026/10/21/req_j9dik7xsuoammbgw6brdgafv/0-YyIruCJVEfXsz3wKufKD7_kmRHee8d.png"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

此请求: $0.25 250 API 积分 · ≈ ₽26.87 在此页面运行

获取 API 密钥
MiniMax 图像生成视频 4K 输出5–15 s最高 4K #motion#first-last-frame

将首帧、尾帧或两者制作成 5 到 15 秒的 MiniMax H3 视频片段,最高 4K。

示例

输入
输出 · ~36 s

提示词Ultra cinematic wide shot: A vast field of burning embers stretches into darkness. Suddenly, an enormous wall of fire races across the ground, sending billions of glowing sparks into the air. The flames twist into a gigantic rotating fire vortex hundreds of feet high. Molten embers, smoke, and liquid fire spiral together, naturally forging the word "IGNITE" from blazing flames. The letters burn brighter and brighter before erupting into a colossal shockwave that fills the screen with fire and incandescent particles. Hollywood fire simulation, ultra-realistic VFX, blockbuster title reveal.

5 s480P$0.25 · 250 API 积分

来自 @CharaspowerAI 在 X 上的提示词

构建请求

控件根据模型架构生成。修改控件时,代码和价格会同步更新。

•必填 595 / 50000

用于生成视频的文本说明。

image_url
拖放文件,或

定义开场帧和输出画布的可选图像 URL。如果仅提供 end_image_url,则改用其结束帧确定画布。若两者都未提供,生成将使用文本生成视频,默认宽高比为 16:9。

resolution

选择生成视频的分辨率,其中 2K 和 4K 通过放大 768P 基础视频获得。选择 480P 或 768P 则使用原生生成。

视频长度,以秒为单位。

高级 prompt_expansion_mode · target_audio_url · end_image · seed
默认 balanced

生成前的提示词改写强度:选择 'quality' 以获得更丰富的提示词,耗时最长约 30 秒;选择 'fast' 可在约一秒内返回结果。使用 'balanced' 时按请求决定;'disabled' 会关闭扩展。

拖放文件,或

通过 HTTP(S) URL 或 base64 数据 URI 提供的可选替换音轨;片段时长至少为 2 秒,且不超过 15 MB。提供的音频会以不变的播放速度替换生成的音轨:多余时长从末尾移除,较短片段则以静音补齐至与视频相同的时长。对于异常高的采样率,可能会重采样为 96 kHz。

end_image_url
拖放文件,或

可选的末帧图像 URL,即使没有起始图像也可使用。在仅使用结束关键帧的模式下,该图像决定输出画布。

随机生成的种子;省略时会随机选择。

POST /run/minimax/h3/image-to-video?wait=20 报价 → $0.25
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/minimax/h3/image-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Ultra cinematic wide shot: A vast field of burning embers stretches into darkness. Suddenly, an enormous wall of fire races across the ground, sending billions of glowing sparks into the air. The flames twist into a gigantic rotating fire vortex hundreds of feet high. Molten embers, smoke, and liquid fire spiral together, naturally forging the word \"IGNITE\" from blazing flames. The letters burn brighter and brighter before erupting into a colossal shockwave that fills the screen with fire and incandescent particles. Hollywood fire simulation, ultra-realistic VFX, blockbuster title reveal.",
    "duration": 5,
    "resolution": "480P",
    "image": "https://content.doitong.com/dev-api/2026/10/21/req_j9dik7xsuoammbgw6brdgafv/0-YyIruCJVEfXsz3wKufKD7_kmRHee8d.png"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

运行此请求

你的密钥会保留在此浏览器中:仅发送到 Doitong API;只有勾选“记住”后才会保存到 localStorage。 获取 API 密钥

在 Doitong 上制作

Doitong 社区使用 MiniMax H3 制作的公开作品。一键复用提示词。

显示的公开作品数:16
Close-up shot of a striking model with piercing eyes and flawless skin, a white snake elegantly c... 视频

Close-up shot of a striking model with piercing eyes and flawless skin, a white snake elegantly coiled around her head and neck, its scales glistening in soft, diffused light. The camera gently zooms in, emphasizing the intricate texture of the snake’s scales and the model’s striking facial...

Animate the stickman drawings into a smooth dance animation. The simple black stick figure perfor... 视频

Animate the stickman drawings into a smooth dance animation. The simple black stick figure performs fun rhythmic dance moves — waving its arms, bending knees, jumping lightly, spinning, and swaying side to side in time with upbeat music. Keep the white background clean and minimal. The motion...

A hyper-realistic, cinematic transformation sequence of the man in the uploaded image, sitting in... 视频

A hyper-realistic, cinematic transformation sequence of the man in the uploaded image, sitting in meditation inside a traditional Japanese room. The atmosphere begins to tremble slightly as soft blue light flows around him. From the ground, thousands of magnetic nano-particles rise, shimmering...

A cinematic transformation video of the man. The scene begins with him standing naturally, then l... 视频

A cinematic transformation video of the man. The scene begins with him standing naturally, then looking down at his hands as glowing holographic projections appear around his body. Mechanical parts of the Iron Man armor start assembling piece by piece with smooth animation: chest plate forming,...

An ultra-epic anime cinematic of Luffy’s greatest enemy unleashing a terrifying blind rage, rampa... 视频

An ultra-epic anime cinematic of Luffy’s greatest enemy unleashing a terrifying blind rage, rampaging uncontrollably against nature itself. His gigantic body is surrounded by a storm of black and crimson energy, crackling with lightning that scorches the ground. His roar shakes the heavens,...

A fair-skinned red-haired woman with freckles tightly embraces a majestic white tiger with faint ... 视频

A fair-skinned red-haired woman with freckles tightly embraces a majestic white tiger with faint reddish stripes. They remain close, perfectly synchronized in stillness. The woman blinks slowly, slightly tilting her head with a serious and intense expression. The tiger breathes gently — its...

The snowboarder is riding across massive, fluffy white clouds as if they were snow-covered mounta... 视频

The snowboarder is riding across massive, fluffy white clouds as if they were snow-covered mountains, with dramatic lighting and deep shadows adding volume and realism. The background shows a stunning blue sky with scattered soft clouds and subtle light rays. crisp cinematic quality, vivid...

视频

Используй это изображение как точный референс. Вертикальное реалистичное видео 9:16, тёплая кинематографичная ночная сцена в спальне. Полностью сохранить лица Ани и Павла, их внешность, причёски, одежду, освещение, кровать, панорамные окна и ночной город. Камера статичная, средний крупный план....

关于 MiniMax H3 Image to Video

MiniMax H3 图生视频接收首帧、尾帧或两者,并补充生动、富有表现力的动作; 画布会遵循所提供图像。原生支持 480P 或 768P,2K 和 4K 选项会将 768P 结果放大,时长为 5 到 15 秒,可选提示词改写,也可选定一条音频作为音轨。

参数

发送规范名称或原生名称之一,不要同时发送两者。 规范名称

名称类型 默认值允许值 描述
prompt必填
类型string
≤ 50,000 个字符
用于生成视频的文本说明。
duration可选
类型integer
默认值5
5 – 15
视频长度,以秒为单位。
resolution可选
类型enum
默认值2K
480P768P2K4K
选择生成视频的分辨率,其中 2K 和 4K 通过放大 768P 基础视频获得。选择 480P 或 768P 则使用原生生成。
seed可选
类型integer | null
随机生成的种子;省略时会随机选择。
prompt_expansion_mode可选
类型string | null
默认值balanced
生成前的提示词改写强度:选择 'quality' 以获得更丰富的提示词,耗时最长约 30 秒;选择 'fast' 可在约一秒内返回结果。使用 'balanced' 时按请求决定;'disabled' 会关闭扩展。
target_audio_url可选
类型url · audio
通过 HTTP(S) URL 或 base64 数据 URI 提供的可选替换音轨;片段时长至少为 2 秒,且不超过 15 MB。提供的音频会以不变的播放速度替换生成的音轨:多余时长从末尾移除,较短片段则以静音补齐至与视频相同的时长。对于异常高的采样率,可能会重采样为 96 kHz。
image_url可选 image
类型url · image
定义开场帧和输出画布的可选图像 URL。如果仅提供 end_image_url,则改用其结束帧确定画布。若两者都未提供,生成将使用文本生成视频,默认宽高比为 16:9。
end_image_url可选 end_image
类型url · image
可选的末帧图像 URL,即使没有起始图像也可使用。在仅使用结束关键帧的模式下,该图像决定输出画布。
必填 规范名称,也可接受

文件参数接受公开的 https:// URL、最大 10 MB 的 data: URI,或上传文件的 file_url。 文件

输出

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "minimax/h3/image-to-video",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 250,
    "usd": "0.25",
    "charged": 250,
    "refunded": 0
  },
  "input": {
    "prompt": "The camera slowly pulls back as the fox runs off the path into the misty forest, fireflies scatter",
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "duration": 6,
    "resolution": "768P"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    },
    "expanded_prompt": "string"
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
文件由你选择每个 outputs[].url 都是我们存储中的副本:可永久保存(按 GB-月付费),也可免费保存 7 天,由账户设置或 ?storage= 决定。
所有模型的结构一致图像、视频和音频的字段均为 type、url、content_type、width、height 和 duration。output 是模型自身的结果对象。
输出字段
video
object {url, content_type, file_name, file_size}模型生成的视频。
expanded_prompt
string | null适用于模型的扩展提示词;如果没有可用的扩展文本则为 null。出现 null 的情况包括禁用扩展、扩展未产生变化,以及扩展由模型托管的 API 内部处理。

更多模型:图像生成视频

对于 AI 代理:此页面的 Markdown 版本位于 https://doitong.com/zh-CN/developers/models/minimax/h3/image-to-video.md. 所有模型和指南: https://doitong.com/developers/llms.txt