Grok Imagine Video API

Grok Imagine Video 支持娱乐创意视频、图片驱动视频、视频编辑和视频延展工作流。

模型 key

  • gork/grok-imagine-video — Grok Imagine Video

支持的 mode 与输入

模型 Mode 名称 输入要求
gork/grok-imagine-video text_to_video 文生视频 Prompt max 2000 chars
gork/grok-imagine-video frames_to_video 首帧生成视频 Prompt max 2000 chars
Images start_frame: 1-1 files, 10 MB, formats jpg, jpeg, png, webp
gork/grok-imagine-video reference_to_video 参考图生成视频 Prompt max 2000 chars
Images reference: 1-7 files, 10 MB, formats jpg, jpeg, png, webp
gork/grok-imagine-video video_edit 视频编辑 Prompt max 2000 chars
Videos: 1-1 files, 100 MB, max 8.7s, formats mp4, mov, webm
gork/grok-imagine-video video_extension 视频扩展 Prompt max 2000 chars
Videos: 1-1 files, 100 MB, max 15s, formats mp4

参数

模型 参数 默认值 可选值 适用 mode
gork/grok-imagine-video duration 5s 1s, 2s, 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s text_to_video, frames_to_video, video_edit
gork/grok-imagine-video reference_to_video_durationduration 5s 1s, 2s, 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s reference_to_video
gork/grok-imagine-video video_extension_durationduration 5s 2s, 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s video_extension
gork/grok-imagine-video aspect_ratio 16:9 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3 text_to_video, frames_to_video, video_edit, reference_to_video
gork/grok-imagine-video resolution 480p 480p, 720p text_to_video, frames_to_video, video_edit, reference_to_video

价格

模型 价格
gork/grok-imagine-video 每秒 4 credits

生产建议

  • 显式传入 mode
  • 只使用上表列出的参数值。
  • 媒体输入类 mode 请先用 POST /api/v1/files 上传素材。
  • 如果页面包含多个变体,请使用你真正需要的模型 key。

示例:文生视频

curl https://img2vid.net/api/v1/generations \
  -H "Authorization: Bearer $BUBLE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gork/grok-imagine-video",
    "mode": "text_to_video",
    "prompt": "A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion",
    "duration": "5s",
    "aspect_ratio": "16:9",
    "resolution": "480p"
  }'

示例:素材驱动视频

curl https://img2vid.net/api/v1/generations \
  -H "Authorization: Bearer $BUBLE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gork/grok-imagine-video",
    "mode": "reference_to_video",
    "prompt": "Animate the source into a polished cinematic motion shot with natural camera movement",
    "image_urls": ["https://example.com/reference.png"],
    "duration": "5s",
    "aspect_ratio": "16:9",
    "resolution": "480p"
  }'

SDK 示例

下面的示例使用本页的公开模型 key、mode 和参数值。片段假设你已经按快速开始初始化了 SDK client,并引入了对应语言需要的 SDK 类型。媒体输入类 mode 仍然需要先上传本地文件,再把返回的 URL 放入 image_urlsstart_framevideo_urls 等公开字段。

JavaScript / TypeScript

const task = await buble.generations.create({
  model: 'gork/grok-imagine-video',
  mode: 'text_to_video',
  prompt:
    'A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion',
  duration: '5s',
  aspect_ratio: '16:9',
  resolution: '480p',
});

const result = await buble.generations.wait(task.data.id);
console.log(result.data.result?.videos?.[0]?.url);

Python

task = client.generations.create(
    model="gork/grok-imagine-video",
    mode="text_to_video",
    prompt="A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion",
    duration="5s",
    aspect_ratio="16:9",
    resolution="480p",
)

result = client.generations.wait(task["data"]["id"])
print(result["data"]["result"]["videos"][0]["url"])

Go

task, err := client.Generations.Create(ctx, &buble.CreateGenerationRequest{
	Model:  "gork/grok-imagine-video",
	Mode:   "text_to_video",
	Prompt: "A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion",
	Params: map[string]any{
		"duration": "5s",
		"aspect_ratio": "16:9",
		"resolution": "480p",
	},
})
if err != nil {
	return err
}

result, err := client.Generations.Wait(ctx, task.Data.ID)
if err != nil {
	return err
}
fmt.Println(result.Data.Result.Videos[0].URL)

Rust

let task = client.generations().create(
    CreateGenerationRequest::new("gork/grok-imagine-video")
        .mode("text_to_video")
        .prompt("A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion")
        .param("duration", "5s")?
        .param("aspect_ratio", "16:9")?
        .param("resolution", "480p")?,
).await?;

let result = client
    .generations()
    .wait(&task.data.id, WaitOptions::default())
    .await?;

Swift

let task = try await client.generations.create(
    try CreateGenerationRequest(model: "gork/grok-imagine-video")
        .mode("text_to_video")
        .prompt("A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion")
        .param("duration", "5s")
        .param("aspect_ratio", "16:9")
        .param("resolution", "480p")
)

let result = try await client.generations.wait(task.data.id)
print(result.data.result?.videos?.first?.url.absoluteString ?? "")

Dart / Flutter

final task = await client.generations.create(
  CreateGenerationRequest(
    model: 'gork/grok-imagine-video',
    mode: 'text_to_video',
    prompt: 'A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion',
  ).withParam('duration', '5s').withParam('aspect_ratio', '16:9').withParam('resolution', '480p'),
);

final result = await client.generations.wait(task.data.id);
print(result.data.result?.videos.firstOrNull?.url);

Elixir

{:ok, task} =
  Buble.Generations.create(client, %{
    model: "gork/grok-imagine-video",
    mode: "text_to_video",
    prompt: "A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion",
    duration: "5s",
    aspect_ratio: "16:9",
    resolution: "480p"
  })

{:ok, result} = Buble.Generations.wait(client, task["data"]["id"])
IO.puts(result["data"]["result"]["videos"] |> List.first() |> Map.fetch!("url"))

Java

Envelope<GenerationTask> task = client.generations().create(
        CreateGenerationRequest.builder()
                .model("gork/grok-imagine-video")
                .mode("text_to_video")
                .prompt("A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion")
                .param("duration", "5s")
                .param("aspect_ratio", "16:9")
                .param("resolution", "480p")
                .build());

Envelope<GenerationTask> result = client.generations().wait(task.getData().getId());

.NET

var task = await client.Generations.CreateAsync(new CreateGenerationRequest
{
    Model = "gork/grok-imagine-video",
    Mode = "text_to_video",
    Prompt = "A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion"
}.WithParam("duration", "5s").WithParam("aspect_ratio", "16:9").WithParam("resolution", "480p"));

var result = await client.Generations.WaitAsync(task!.Data!.Id!);

PHP

$task = $client->generations()->create(
    CreateGenerationRequest::make(
        model: 'gork/grok-imagine-video',
        mode: 'text_to_video',
        prompt: 'A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion',
    )
    ->withParam('duration', '5s')
    ->withParam('aspect_ratio', '16:9')
    ->withParam('resolution', '480p')
);

$result = $client->generations()->wait($task['data']['id']);

Ruby

task = client.generations.create(
  model: "gork/grok-imagine-video",
  mode: "text_to_video",
  prompt: "A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion",
  duration: "5s",
  aspect_ratio: "16:9",
  resolution: "480p"
)

result = client.generations.wait(task.dig("data", "id"))
puts result.dig("data", "result", "videos", 0, "url")