高清重塑视频

您可以使用 Gemini Omni 1.2 Flash,通过 Agent Platform API 将视频从较低分辨率(360p 或 720p)提升到较高分辨率(720p、1080p 或 4K)。借助独立视频放大功能,您可以先以较低分辨率迭代提示,然后仅放大最终选定的视频,该视频可以来自上一轮对话,也可以来自之前生成并存储在 Cloud Storage 中的视频。

以下模型支持视频放大:

点击即可展开支持的模型

支持的分辨率和规格

独立视频高清重塑支持以下分辨率转换和输入限制:

  • 360p 输入视频:升频至 720p 或 1080p。不支持在单个请求中直接从 360p 扩容到 4k。
  • 720p 输入视频:升频至 1080p 或 4k。不支持从 1080p 扩容到 4k。
  • 宽高比:16:9(横向)或 9:16(纵向)。
  • 帧速率:每秒 24 帧(在输出视频中保留)。
  • 时长:最长 15 秒。
  • Token 用量和价格:独立视频放大功能会绕过文本推理,并且始终不会产生输入 token (total_input_tokens: 0)。输出视频 token 的价格与所有其他 Omni 1.2 Flash 任务的输出视频 token 价格相同,具体取决于源分辨率和目标分辨率对(360p 到 720p 以及 720p 到 1080p 为每秒 2,896 个输出视频 token,360p 到 1080p 为每秒 5,792 个输出视频 token,720p 到 4k 为每秒 11,584 个输出视频 token)。

请求要求

发送独立的视频放大请求时,请确保您的请求符合以下要求:

  • 指定 task: "upscale":您必须将 generation_config.video_config.task 设置为 "upscale"。如果您省略 task: "upscale",API 会将请求解释为视频编辑 ("edit") 操作。
  • 指定目标 resolution:您必须在 response_format 中指定目标 resolution("720p"、"1080p" 或 "4k")。省略目标 resolution 会返回错误。
  • 提供视频来源:在 input ("type": "video") 中提供输入视频,或设置 previous_interaction_id 以放大在紧邻的前一个有状态轮次中生成的视频。在多轮互动中,系统在定位要放大的视频时,只会考虑紧邻的前一轮互动。
  • 可选参数:您可以指定 generation_config.seed 以获得可重现的输出,并附加自定义元数据标签 (labels) 来整理请求和跟踪已出账单费用。

在 Colab 中试用 Gemini Omni

准备工作

  1. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

    Roles required to select or create a project

    • Select a project: Selecting a project doesn't require a specific IAM role—you can select any project that you've been granted a role on.
    • Create a project: To create a project, you need the Project Creator role (roles/resourcemanager.projectCreator), which contains the resourcemanager.projects.create permission. Learn how to grant roles.

    Go to project selector

  2. Enable the Agent Platform API, if it is not already enabled.

    Roles required to enable APIs

    To enable APIs, you need the serviceusage.services.enable permission. If you created the project, then you likely already have this permission through the Owner role (roles/owner). Otherwise, you can get this permission through the Service Usage Admin role (roles/serviceusage.serviceUsageAdmin). Learn how to grant roles.

    Enable the API

  3. 为您的环境设置身份验证。

    选择标签页以了解您打算如何使用本页面上的示例:

    控制台

    当您使用 Google Cloud 控制台访问 Google Cloud 服务和 API 时,无需设置身份验证。

    REST

    如需在本地开发环境中使用本页面上的 REST API 示例,请使用您提供给 gcloud CLI 的凭证。

      安装 Google Cloud CLI,然后 使用联合身份登录 gcloud CLI。

    如需了解详情,请参阅 Google Cloud 身份验证文档中的使用 REST 时进行身份验证。

使用 Omni 1.2 Flash 提高视频分辨率

如需使用 Omni 1.2 Flash 提升视频分辨率,请选择以下互动模式之一:

REST

视频放大可能需要超过一分钟才能完成。您可以根据工作流从多种交互模式中进行选择:

  • 同步:无状态(上传的视频):将 store 设置为 false,以便在单个请求中对 Cloud Storage 中的 360p 或 720p 视频进行放大,而无需在服务器上保留互动状态。
  • 同步:有状态(上一轮):引用紧邻的前一轮有状态对话中的 previous_interaction_id,以放大之前生成的 360p 或 720p 视频。
  • 同步:有状态流式传输:将 store 和 stream 都设置为 true,以流式传输互动状态更新和输出视频。
  • 异步:将 background 设置为 true,以便在后台运行视频放大,并在稍后使用互动 ID 检索结果。

存储的互动和异步互动最长会保留 7 天。

如需详细了解如何将 Gemini Omni 模型与 Interactions API 搭配使用,请参阅 Interactions API。

同步:无状态

在使用任何请求数据之前,请先进行以下替换:

  • PROJECT_ID:表示您的 Google Cloud 项目 ID 的字符串。
  • MODEL_ID:表示要使用的模型 ID 的字符串。接受的值如下:
    • "gemini-omni-1.2-flash"
  • CLOUD_STORAGE_VIDEO_URI:一个字符串,表示包含输入视频(360p 或 720p,最长 15 秒)的 Cloud Storage URI。例如:"gs://video-bucket/input/video.mp4"
  • VIDEO_MIME:表示视频 MIME 类型的字符串。接受的值如下:
    • video/3gpp
    • video/mp4
    • video/mpeg
    • video/quicktime
    • video/webm
    • video/x-flv
    • video/x-ms-wmv
  • CLOUD_STORAGE_OUTPUT_URI:(可选)一个字符串,表示用于存储放大视频的 Cloud Storage 存储桶。如果未提供,则回答中会返回视频字节。 例如:"gs://video-bucket/output/"。
  • OUTPUT_RESOLUTION:必需:表示目标输出分辨率的字符串。支持的值取决于输入视频分辨率:
    • 对于 360p 输入视频:"720p" 或 "1080p"
    • 对于 720p 输入视频:"1080p" 或 "4k"

HTTP 方法和网址:

POST https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions

请求 JSON 正文:

{
  "model": "MODEL_ID",
  "store": false,
  "input": [
    {
      "type": "video",
      "uri": "CLOUD_STORAGE_VIDEO_URI",
      "mime_type": "VIDEO_MIME"
    }
  ],
  "response_format": [
    {
      "type": "video",
      "delivery": "uri",
      "gcs_uri": "CLOUD_STORAGE_OUTPUT_URI",
      "resolution": "OUTPUT_RESOLUTION"
    }
  ],
  "generation_config": {
    "video_config": {
      "task": "upscale"
    }
  }
}

如需发送请求,请选择以下方式之一:

curl

将请求正文保存在名为 request.json 的文件中,然后执行以下命令:

curl -X POST \
-H "Authorization: Bearer TOKEN" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions"

PowerShell

将请求正文保存在名为 request.json 的文件中,然后执行以下命令:

$headers = @{ "Authorization" = "Bearer TOKEN" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions" | Select-Object -Expand Content
回答包含与放大后的输出视频的互动,并且输入 token 数量为零。
{
  "id": "INTERACTION_ID",
  "model": "gemini-omni-1.2-flash",
  "status": "completed",
  "usage": {
    "total_tokens": 28960,
    "total_input_tokens": 0,
    "output_tokens_by_modality": [
      {
        "modality": "video",
        "tokens": 28960
      }
    ],
    "total_output_tokens": 28960
  },
  "steps": [
    { 
      "type": "model_output",
      "content": [
        {
          "type": "video",
          "uri": "gs://some/output_path/123.mp4",
          "mime_type": "video/mp4" 
        }
      ]
    }
  ],
  "object": "interaction",
  "role": "model",
  "created": "2026-11-05T02:17:56Z",
  "updated": "2026-11-05T02:17:56Z"
}

同步:有状态

在使用任何请求数据之前,请先进行以下替换:

  • PROJECT_ID:表示您的 Google Cloud 项目 ID 的字符串。
  • MODEL_ID:表示要使用的模型 ID 的字符串。接受的值如下:
    • "gemini-omni-1.2-flash"
  • PREVIOUS_INTERACTION_ID:紧邻的前一个生成 360p 或 720p 视频(最长 15 秒)的有状态轮次的互动 ID。
  • CLOUD_STORAGE_OUTPUT_URI:(可选)一个字符串,表示用于存储放大视频的 Cloud Storage 存储桶。如果未提供,则回答中会返回视频字节。 例如:"gs://video-bucket/output/"。
  • OUTPUT_RESOLUTION:必需:表示目标输出分辨率的字符串。支持的值取决于上一轮的视频分辨率:
    • 对于 360p 视频:"720p" 或 "1080p"
    • 对于 720p 视频:"1080p" 或 "4k"

HTTP 方法和网址:

POST https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions

请求 JSON 正文:

{
  "model": "MODEL_ID",
  "previous_interaction_id": "PREVIOUS_INTERACTION_ID",
  "background": false,
  "store": true,
  "stream": false,
  "input": [
    {
      "type": "user_input",
      "content": [
        {
          "type": "text",
          "text": "Upsample video."
        }
      ]
    }
  ],
  "response_format": [
    {
      "type": "video",
      "delivery": "uri",
      "gcs_uri": "CLOUD_STORAGE_OUTPUT_URI",
      "resolution": "OUTPUT_RESOLUTION"
    }
  ],
  "generation_config": {
    "video_config": {
      "task": "upscale"
    }
  }
}

如需发送请求,请选择以下方式之一:

curl

将请求正文保存在名为 request.json 的文件中,然后执行以下命令:

curl -X POST \
-H "Authorization: Bearer TOKEN" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions"

PowerShell

将请求正文保存在名为 request.json 的文件中,然后执行以下命令:

$headers = @{ "Authorization" = "Bearer TOKEN" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions" | Select-Object -Expand Content
回答包含与放大后的输出视频的互动,并且输入 token 数量为零。
{
  "id": "INTERACTION_ID",
  "previous_interaction_id": "PREVIOUS_INTERACTION_ID",
  "model": "gemini-omni-1.2-flash",
  "status": "completed",
  "usage": {
    "total_tokens": 28960,
    "total_input_tokens": 0,
    "output_tokens_by_modality": [
      {
        "modality": "video",
        "tokens": 28960
      }
    ],
    "total_output_tokens": 28960
  },
  "steps": [
    { 
      "type": "model_output",
      "content": [
        {
          "type": "video",
          "uri": "gs://some/output_path/123.mp4",
          "mime_type": "video/mp4" 
        }
      ]
    }
  ],
  "object": "interaction",
  "role": "model",
  "created": "2026-11-05T02:17:56Z",
  "updated": "2026-11-05T02:17:56Z"
}
使用 INTERACTION_ID 获取提高分辨率后的视频:

在使用任何请求数据之前,请先进行以下替换:

  • PROJECT_ID:表示您的 Google Cloud 项目 ID 的字符串。
  • INTERACTION_ID:异步请求中的互动 ID。

HTTP 方法和网址:

GET https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions/INTERACTION_ID

如需发送请求,请选择以下方式之一:

curl

执行以下命令:

curl -X GET \
-H "Authorization: Bearer TOKEN" \
"https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions/INTERACTION_ID"

PowerShell

执行以下命令:

$headers = @{ "Authorization" = "Bearer TOKEN" }

Invoke-WebRequest `
-Method GET `
-Headers $headers `
-Uri "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions/INTERACTION_ID" | Select-Object -Expand Content
响应采用类似于以下内容的格式:
{
  "id":"INTERACTION_ID",
  "model":"gemini-omni-1.2-flash",
  "status":"completed",
  "usage":{
    "total_tokens":479,
    "total_input_tokens":26,
    "input_tokens_by_modality":[
      {
        "modality":"text",
        "tokens":26
      },
      {
        "modality":"image",
        "tokens":124
      }
    ],
    "output_tokens_by_modality": [
      {
        "modality": "video",
        "tokens": 28832
      }
    ],
    "total_output_tokens":28832,
    "total_thought_tokens":453
  },
  "steps":[
    {
      "type": "user_input",
      "content": [
        {
          "type": "text",
          "text": "5 second, 9:16 video. Use the image as the first frame."
        },
        {
          "type": "image",
          "uri": "gs://some/path",
          "mime_type": "image/png"
        }
      ]
    },
    {
      "type":"thought",
      "summary":[
        {
          "type":"text",
          "text":"MODEL THOUGHTS"
        }
      ]
    },
    { 
      "type":"model_output",
      "content":[
        {
          "type":"video",
          "data":"VIDEO DATA",
          "mime_type":"video/mp4" 
        }
      ]
    }
  ],
  "object":"interaction",
  "role":"model",
  "created":"2026-05-29T02:17:56Z",
  "updated":"2026-05-29T02:17:56Z"
}

同步:有状态流式传输

在使用任何请求数据之前,请先进行以下替换:

  • PROJECT_ID:表示您的 Google Cloud 项目 ID 的字符串。
  • MODEL_ID:表示要使用的模型 ID 的字符串。接受的值如下:
    • "gemini-omni-1.2-flash"
  • CLOUD_STORAGE_VIDEO_URI:一个字符串,表示包含输入视频(360p 或 720p,最长 15 秒)的 Cloud Storage URI。例如:"gs://video-bucket/input/video.mp4"
  • VIDEO_MIME:表示视频 MIME 类型的字符串。接受的值如下:
    • video/3gpp
    • video/mp4
    • video/mpeg
    • video/quicktime
    • video/webm
    • video/x-flv
    • video/x-ms-wmv
  • CLOUD_STORAGE_OUTPUT_URI:(可选)一个字符串,表示用于存储放大视频的 Cloud Storage 存储桶。如果未提供,则回答中会返回视频字节。 例如:"gs://video-bucket/output/"。
  • OUTPUT_RESOLUTION:必需:表示目标输出分辨率的字符串。支持的值取决于输入视频分辨率:
    • 对于 360p 输入视频:"720p" 或 "1080p"
    • 对于 720p 输入视频:"1080p" 或 "4k"

HTTP 方法和网址:

POST https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions

请求 JSON 正文:

{
  "model": "MODEL_ID",
  "background": false,
  "store": true,
  "stream": true,
  "input": [
    {
      "type": "user_input",
      "content": [
        {
          "type": "video",
          "uri": "CLOUD_STORAGE_VIDEO_URI",
          "mime_type": "VIDEO_MIME"
        }
      ]
    }
  ],
  "response_format": [
    {
      "type": "video",
      "delivery": "uri",
      "gcs_uri": "CLOUD_STORAGE_OUTPUT_URI",
      "resolution": "OUTPUT_RESOLUTION"
    }
  ],
  "generation_config": {
    "video_config": {
      "task": "upscale"
    }
  }
}

如需发送请求,请选择以下方式之一:

curl

将请求正文保存在名为 request.json 的文件中,然后执行以下命令:

curl -X POST \
-H "Authorization: Bearer TOKEN" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions"

PowerShell

将请求正文保存在名为 request.json 的文件中,然后执行以下命令:

$headers = @{ "Authorization" = "Bearer TOKEN" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions" | Select-Object -Expand Content
响应是包含放大输出视频的服务器发送事件 (SSE) 流。
event: interaction.created
data: {"interaction":{"id":"INTERACTION_ID","status":"in_progress","object":"interaction","model":"gemini-omni-1.2-flash"},"event_type":"interaction.created"}

event: interaction.status_update
data: {"interaction_id":"INTERACTION_ID","status":"in_progress","event_type":"interaction.status_update"}

event: step.start
data: {"index":0,"step":{"type":"model_output"},"event_type":"step.start"}

event: step.delta
data: {"index":0,"delta":{"mime_type":"video/mp4","uri":"gs://some/output_path/123.mp4","type":"video"},"event_id":"EVENT_ID","event_type":"step.delta"}

event: step.stop
data: {"index":0,"event_type":"step.stop"}

event: interaction.completed
data: {"interaction":{"id":"INTERACTION_ID","status":"completed","usage":{"total_tokens":28960,"total_input_tokens":0,"total_output_tokens":28960,"output_tokens_by_modality":[{"modality":"video","tokens":28960}]},"created":"2026-11-05T21:26:20Z","updated":"2026-11-05T21:26:20Z","event_id":"EVENT_ID","object":"interaction","model":"gemini-omni-1.2-flash"},"event_id":"EVENT_ID","event_type":"interaction.completed"}

event: done
data: [DONE]
使用带有 `?stream=true` 的 INTERACTION_ID 流式传输存储的互动和放大后的视频:

在使用任何请求数据之前,请先进行以下替换:

  • PROJECT_ID:表示您的 Google Cloud 项目 ID 的字符串。
  • INTERACTION_ID:请求中的互动 ID。

HTTP 方法和网址:

GET https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions/INTERACTION_ID?stream=true

如需发送请求,请选择以下方式之一:

curl

执行以下命令:

curl -X GET \
-H "Authorization: Bearer TOKEN" \
"https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions/INTERACTION_ID?stream=true"

PowerShell

执行以下命令:

$headers = @{ "Authorization" = "Bearer TOKEN" }

Invoke-WebRequest `
-Method GET `
-Headers $headers `
-Uri "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions/INTERACTION_ID?stream=true" | Select-Object -Expand Content
响应是服务器发送事件 (SSE) 流,格式类似于以下内容:
event: interaction.created
data: {"interaction":{"id":"INTERACTION_ID","status":"in_progress","object":"interaction","model":"gemini-omni-1.2-flash"},"event_type":"interaction.created"}

event: interaction.status_update
data: {"interaction_id":"INTERACTION_ID","status":"in_progress","event_type":"interaction.status_update"}

event: step.start
data: {"index":0,"step":{"type":"thought"},"event_type":"step.start"}

event: step.delta
data: {"index":0,"delta":{"content":{"text":"MODEL THOUGHTS","type":"text"},"type":"thought_summary"},"event_id":"EVENT_ID","event_type":"step.delta"}

event: step.delta
data: {"index":0,"delta":{"content":{"text":"MODEL THOUGHTS","type":"text"},"type":"thought_summary"},"event_id":"EVENT_ID","event_type":"step.delta"}

event: step.delta
data: {"index":0,"delta":{"signature":"...","type":"thought_signature"},"event_type":"step.delta"}

event: step.stop
data: {"index":0,"event_type":"step.stop"}

event: step.start
data: {"index":1,"step":{"type":"model_output"},"event_type":"step.start"}

event: step.delta
data: {"index":1,"delta":{"mime_type":"video/mp4","uri":"gs://some/output_path/123.mp4","type":"video"},"event_id":"EVENT_ID","event_type":"step.delta"}

event: step.stop
data: {"index":1,"event_type":"step.stop"}

event: interaction.completed
data: {"interaction":{"id":"INTERACTION_ID","status":"completed","usage":{"total_tokens":17664,"total_input_tokens":21,"input_tokens_by_modality":[{"modality":"text","tokens":21}],"total_output_tokens":17376,"output_tokens_by_modality":[{"modality":"video","tokens":17376}],"total_thought_tokens":267},"created":"2026-08-12T21:33:08Z","updated":"2026-08-12T21:33:08Z","event_id":"EVENT_ID","object":"interaction","model":"gemini-omni-1.2-flash"},"event_id":"EVENT_ID","event_type":"interaction.completed"}

event: done
data: [DONE]

异步

在使用任何请求数据之前,请先进行以下替换:

  • PROJECT_ID:表示您的 Google Cloud 项目 ID 的字符串。
  • MODEL_ID:表示要使用的模型 ID 的字符串。接受的值如下:
    • "gemini-omni-1.2-flash"
  • CLOUD_STORAGE_VIDEO_URI:一个字符串,表示包含输入视频(360p 或 720p,最长 15 秒)的 Cloud Storage URI。例如:"gs://video-bucket/input/video.mp4"
  • VIDEO_MIME:表示视频 MIME 类型的字符串。接受的值如下:
    • video/3gpp
    • video/mp4
    • video/mpeg
    • video/quicktime
    • video/webm
    • video/x-flv
    • video/x-ms-wmv
  • CLOUD_STORAGE_OUTPUT_URI:(可选)一个字符串,表示用于存储放大视频的 Cloud Storage 存储桶。如果未提供,则回答中会返回视频字节。 例如:"gs://video-bucket/output/"。
  • OUTPUT_RESOLUTION:必需:表示目标输出分辨率的字符串。支持的值取决于输入视频分辨率:
    • 对于 360p 输入视频:"720p" 或 "1080p"
    • 对于 720p 输入视频:"1080p" 或 "4k"

HTTP 方法和网址:

POST https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions

请求 JSON 正文:

{
  "model": "MODEL_ID",
  "background": true,
  "input": [
    {
      "type": "video",
      "uri": "CLOUD_STORAGE_VIDEO_URI",
      "mime_type": "VIDEO_MIME"
    }
  ],
  "response_format": [
    {
      "type": "video",
      "delivery": "uri",
      "gcs_uri": "CLOUD_STORAGE_OUTPUT_URI",
      "resolution": "OUTPUT_RESOLUTION"
    }
  ],
  "generation_config": {
    "video_config": {
      "task": "upscale"
    }
  }
}

如需发送请求,请选择以下方式之一:

curl

将请求正文保存在名为 request.json 的文件中,然后执行以下命令:

curl -X POST \
-H "Authorization: Bearer TOKEN" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions"

PowerShell

将请求正文保存在名为 request.json 的文件中,然后执行以下命令:

$headers = @{ "Authorization" = "Bearer TOKEN" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions" | Select-Object -Expand Content
响应包含一个互动 ID,您可以使用该 ID 检索放大后的视频。
{
  "id": "INTERACTION_ID",
  "status": "in_progress",
  "object": "interaction"
}
稍后,使用 INTERACTION_ID 获取提高分辨率后的视频:

在使用任何请求数据之前,请先进行以下替换:

  • PROJECT_ID:表示您的 Google Cloud 项目 ID 的字符串。
  • INTERACTION_ID:异步请求中的互动 ID。

HTTP 方法和网址:

GET https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions/INTERACTION_ID

如需发送请求,请选择以下方式之一:

curl

执行以下命令:

curl -X GET \
-H "Authorization: Bearer TOKEN" \
"https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions/INTERACTION_ID"

PowerShell

执行以下命令:

$headers = @{ "Authorization" = "Bearer TOKEN" }

Invoke-WebRequest `
-Method GET `
-Headers $headers `
-Uri "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions/INTERACTION_ID" | Select-Object -Expand Content
响应采用类似于以下内容的格式:
{
  "id":"INTERACTION_ID",
  "model":"gemini-omni-1.2-flash",
  "status":"completed",
  "usage":{
    "total_tokens":479,
    "total_input_tokens":26,
    "input_tokens_by_modality":[
      {
        "modality":"text",
        "tokens":26
      },
      {
        "modality":"image",
        "tokens":124
      }
    ],
    "output_tokens_by_modality": [
      {
        "modality": "video",
        "tokens": 28832
      }
    ],
    "total_output_tokens":28832,
    "total_thought_tokens":453
  },
  "steps":[
    {
      "type": "user_input",
      "content": [
        {
          "type": "text",
          "text": "5 second, 9:16 video. Use the image as the first frame."
        },
        {
          "type": "image",
          "uri": "gs://some/path",
          "mime_type": "image/png"
        }
      ]
    },
    {
      "type":"thought",
      "summary":[
        {
          "type":"text",
          "text":"MODEL THOUGHTS"
        }
      ]
    },
    { 
      "type":"model_output",
      "content":[
        {
          "type":"video",
          "data":"VIDEO DATA",
          "mime_type":"video/mp4" 
        }
      ]
    }
  ],
  "object":"interaction",
  "role":"model",
  "created":"2026-05-29T02:17:56Z",
  "updated":"2026-05-29T02:17:56Z"
}

后续步骤