跳转到内容

Grok Imagine Video 1.5 Text to Video

集成

模型 id xai/grok-imagine-video/v1.5/text-to-video
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/xai/grok-imagine-video/v1.5/text-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Three tiny anthropomorphic kittens sit on a park bench. One combs another’s fur with a tiny brush while the third stands and holds the tip jar out toward the camera, gesturing with its free paw. They suddenly all start waving and meowing excitedly as a leaf floats by. A colorful sign in front reads “Tips for cuteness overload ” Soft afternoon sunlight through trees, realistic fur and expressive faces, gentle camera push.",
    "duration": 5,
    "resolution": "480p",
    "aspect_ratio": "16:9"
  }'

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

此请求: $0.40 400 API 积分 在此页面运行

获取 API 密钥
xAI 文本生成视频 1–15 s最高 1080p #stylized#flexible-length#budget

xAI 的视频模型,时长可为 1 到 15 秒之间的任意值,分辨率为 480p 到 1080p。

示例

输出 · ~44 s

提示词Three tiny anthropomorphic kittens sit on a park bench. One combs another’s fur with a tiny brush while the third stands and holds the tip jar out toward the camera, gesturing with its free paw. They suddenly all start waving and meowing excitedly as a leaf floats by. A colorful sign in front reads “Tips for cuteness overload ” Soft afternoon sunlight through trees, realistic fur and expressive faces, gentle camera push.

5 s480p16:9$0.40 · 400 API 积分

来自 @JayKay65220066 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 424 / 4096

指定要创建的视频的描述。

resolution

输出视频的分辨率。

aspect_ratio

生成视频的宽高比。

以秒为单位的视频时长。

POST /run/xai/grok-imagine-video/v1.5/text-to-video?wait=20 报价 → $0.40
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/xai/grok-imagine-video/v1.5/text-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Three tiny anthropomorphic kittens sit on a park bench. One combs another’s fur with a tiny brush while the third stands and holds the tip jar out toward the camera, gesturing with its free paw. They suddenly all start waving and meowing excitedly as a leaf floats by. A colorful sign in front reads “Tips for cuteness overload ” Soft afternoon sunlight through trees, realistic fur and expressive faces, gentle camera push.",
    "duration": 5,
    "resolution": "480p",
    "aspect_ratio": "16:9"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://vit.doitong.com/api/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

关于 Grok Imagine Video 1.5 Text to Video

Grok Imagine Video 1.5 将提示词转换为时长为 1 到 15 秒之间任意整数的片段,动态效果适合动漫、动作、风格化画面和写实画面。支持从 9:16 到 16:9 的七种宽高比,以及 480p、720p 或 1080p;价格随时长线性变化。

参数

名称类型 默认值允许值 描述
prompt必填
类型string
≤ 4,096 个字符
指定要创建的视频的描述。
duration可选
类型integer
默认值6
1 – 15
以秒为单位的视频时长。
resolution可选
类型enum
默认值720p
480p720p1080p
输出视频的分辨率。
aspect_ratio可选
类型enum
默认值16:9
16:94:33:21:12:33:49:16
生成视频的宽高比。
必填

输出

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "xai/grok-imagine-video/v1.5/text-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": 400,
    "usd": "0.40",
    "charged": 400,
    "refunded": 0
  },
  "input": {
    "prompt": "Anime schoolgirl bursts out of her front door, cherry blossoms swirling, morning light, speed lines",
    "duration": 5,
    "resolution": "480p"
  },
  "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,
      "width": 1024,
      "height": 768,
      "fps": 1.0,
      "duration": 5,
      "num_frames": 1
    }
  },
  "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://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://vit.doitong.com/api/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, width, height, fps, duration, num_frames}模型生成的视频。

更多模型:文本生成视频

对于 AI 代理:此页面的 Markdown 版本位于 https://doitong.com/zh-CN/developers/models/xai/grok-imagine-video/v1.5/text-to-video.md. 所有模型和指南: https://doitong.com/developers/llms.txt