Img2Vid

Veo 3.1 API

Img2Vid 上的 Veo 3.1 提供 Fast 与 Quality 变体，适合电影感文生视频、参考图视频和帧控制视频生成。

模型 key

  • google/veo3.1-fast — Veo3.1 Fast
  • google/veo3.1-quality — Veo3.1 Quality

支持的 mode 与输入

模型 Mode 名称 输入要求
google/veo3.1-fast text_to_video 文生视频 Prompt max 2000 chars
google/veo3.1-fast reference_to_video 参考图生成视频 Prompt max 2000 chars
Images reference: 1-3 files, 10 MB, formats jpg, png, webp
google/veo3.1-fast frames_to_video 首尾帧生成视频 Prompt max 2000 chars
Images start_frame,end_frame: 1-2 files, 10 MB, formats jpg, png, webp
google/veo3.1-quality text_to_video 文生视频 Prompt max 2000 chars
google/veo3.1-quality reference_to_video 参考图生成视频 Prompt max 2000 chars
Images reference: 1-3 files, 10 MB, formats jpg, png, webp
google/veo3.1-quality frames_to_video 首尾帧生成视频 Prompt max 2000 chars
Images start_frame,end_frame: 1-2 files, 10 MB, formats jpg, png, webp

参数

模型 参数 默认值 可选值 适用 mode
google/veo3.1-fast duration 8s 8s 全部 mode
google/veo3.1-fast resolution 720p 720p, 1080p, 4k 全部 mode
google/veo3.1-fast aspect_ratio 16:9 16:9, 9:16 全部 mode
google/veo3.1-quality duration 8s 8s 全部 mode
google/veo3.1-quality resolution 720p 720p, 1080p, 4k 全部 mode
google/veo3.1-quality aspect_ratio 16:9 16:9, 9:16 全部 mode

价格

模型 价格
google/veo3.1-fast 每秒 5 credits；参数倍率：resolution={"4k":3,"720p":1,"1080p":1}
google/veo3.1-quality 每秒 1 credit；参数倍率：resolution={"4k":80,"720p":26,"1080p":26}

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": "google/veo3.1-fast",
    "mode": "text_to_video",
    "prompt": "A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion",
    "duration": "8s",
    "resolution": "720p",
    "aspect_ratio": "16:9"
  }'

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": "google/veo3.1-fast",
    "mode": "frames_to_video",
    "prompt": "Animate the source into a polished cinematic motion shot with natural camera movement",
    "start_frame": "https://example.com/start.png",
    "duration": "8s",
    "resolution": "720p",
    "aspect_ratio": "16:9"
  }'

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_urls、start_frame、video_urls 等公开字段。

JavaScript / TypeScript

const task = await buble.generations.create({
  model: 'google/veo3.1-fast',
  mode: 'text_to_video',
  prompt:
    'A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion',
  duration: '8s',
  resolution: '720p',
  aspect_ratio: '16:9',
});

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

Python

task = client.generations.create(
    model="google/veo3.1-fast",
    mode="text_to_video",
    prompt="A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion",
    duration="8s",
    resolution="720p",
    aspect_ratio="16:9",
)

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

Go

task, err := client.Generations.Create(ctx, &buble.CreateGenerationRequest{
	Model:  "google/veo3.1-fast",
	Mode:   "text_to_video",
	Prompt: "A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion",
	Params: map[string]any{
		"duration": "8s",
		"resolution": "720p",
		"aspect_ratio": "16:9",
	},
})
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("google/veo3.1-fast")
        .mode("text_to_video")
        .prompt("A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion")
        .param("duration", "8s")?
        .param("resolution", "720p")?
        .param("aspect_ratio", "16:9")?,
).await?;

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

Swift

let task = try await client.generations.create(
    try CreateGenerationRequest(model: "google/veo3.1-fast")
        .mode("text_to_video")
        .prompt("A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion")
        .param("duration", "8s")
        .param("resolution", "720p")
        .param("aspect_ratio", "16:9")
)

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: 'google/veo3.1-fast',
    mode: 'text_to_video',
    prompt: 'A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion',
  ).withParam('duration', '8s').withParam('resolution', '720p').withParam('aspect_ratio', '16:9'),
);

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

Elixir

{:ok, task} =
  Buble.Generations.create(client, %{
    model: "google/veo3.1-fast",
    mode: "text_to_video",
    prompt: "A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion",
    duration: "8s",
    resolution: "720p",
    aspect_ratio: "16:9"
  })

{: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("google/veo3.1-fast")
                .mode("text_to_video")
                .prompt("A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion")
                .param("duration", "8s")
                .param("resolution", "720p")
                .param("aspect_ratio", "16:9")
                .build());

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

.NET

var task = await client.Generations.CreateAsync(new CreateGenerationRequest
{
    Model = "google/veo3.1-fast",
    Mode = "text_to_video",
    Prompt = "A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion"
}.WithParam("duration", "8s").WithParam("resolution", "720p").WithParam("aspect_ratio", "16:9"));

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

PHP

$task = $client->generations()->create(
    CreateGenerationRequest::make(
        model: 'google/veo3.1-fast',
        mode: 'text_to_video',
        prompt: 'A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion',
    )
    ->withParam('duration', '8s')
    ->withParam('resolution', '720p')
    ->withParam('aspect_ratio', '16:9')
);

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

Ruby

task = client.generations.create(
  model: "google/veo3.1-fast",
  mode: "text_to_video",
  prompt: "A cinematic product launch shot with slow camera movement, premium lighting, and realistic motion",
  duration: "8s",
  resolution: "720p",
  aspect_ratio: "16:9"
)

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

On this page

模型 key
支持的 mode 与输入
参数
价格
生产建议
示例：文生视频
示例：素材驱动视频
SDK 示例
JavaScript / TypeScript
Python
Go
Rust
Swift
Dart / Flutter
Elixir
Java
.NET
PHP
Ruby