您可以在 Gemini Enterprise Agent Platform 使用 Gemini Omni Flash 或 Veo,根據文字提示詞生成新影片。支援的介面包括 Cloud de Confiance 控制台和 Agent Platform API。
下列模型支援根據文字提示詞生成影片:
Gemini Omni Flash
按一下即可展開支援的模型
Veo
按一下即可展開支援的模型
如要進一步瞭解如何撰寫有效的文字提示詞來生成影片,請參閱影片生成提示詞指南。
事前準備
-
In the Cloud de Confiance console, on the project selector page, select or create a Cloud de Confiance 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 theresourcemanager.projects.createpermission. Learn how to grant roles.
Enable the Agent Platform API, if it is not already enabled.
Roles required to enable APIs
To enable APIs, you need the
serviceusage.services.enablepermission. 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.-
設定環境的驗證機制。
請根據您打算如何使用本頁範例,選取對應的分頁標籤:
控制台
使用 Cloud de Confiance 控制台存取 Cloud de Confiance by S3NS 服務和 API 時,您不需要設定驗證機制。
REST
如要在本機開發環境中使用本頁的 REST API 範例,請使用您提供給 gcloud CLI 的憑證。
安裝 Google Cloud CLI,然後 使用聯合身分登入 gcloud CLI。
詳情請參閱 Cloud de Confiance 驗證說明文件中的「使用 REST 進行驗證」一節。
使用 Gemini Omni Flash 生成影片
如要使用 Gemini Omni Flash 生成影片,請參考下列範例。雖然這些範例著重於文字轉影片,但也可以擴充至其他用途,例如提供起始圖片來引導生成。
REST
生成影片可能需要一分鐘以上。您可以根據工作流程選擇下列幾種互動模式:
- 同步:無狀態:在單一要求中生成影片,不必在伺服器上保留互動狀態。
- 同步:具狀態:將
store設為true,即可保留互動狀態,以便稍後擷取結果或參照互動 ID 進行多輪影片編輯。 - 同步:有狀態的串流:將
store和stream都設為true,即可在模型生成想法時逐步接收,然後接收輸出影片。 - 非同步:將
background設為true,即可在背景執行影片生成作業,稍後再使用互動 ID 擷取結果。
儲存的非同步互動最多會保留 7 天。
如要進一步瞭解如何使用 Gemini Omni Flash API,請參閱「Interactions API」。
同步:無狀態
使用任何要求資料之前,請先修改下列項目的值:
-
PROJECT_ID:代表 Cloud de Confiance by S3NS 專案 ID 的字串。 -
MODEL_ID:代表要使用的模型 ID 的字串。可接受的值如下:"gemini-omni-1.1-flash-preview""gemini-omni-flash-preview"
-
TEXT_PROMPT:用於引導影片生成的文字提示詞。 -
CLOUD_STORAGE_OUTPUT_URI:選用。代表 Cloud Storage bucket 的字串,用於儲存輸出影片。如未提供,回應中會傳回影片位元組。 例如:"gs://video-bucket/output/"。 -
ASPECT_RATIO: 選用:代表輸出影片預期顯示比例的字串。如未提供,系統會根據提示推斷顯示比例。 可接受的值如下:"16:9""9:16"
-
OUTPUT_RESOLUTION:選用:代表影片輸出解析度的字串。如未提供,輸出內容預設為 720p。
gemini-omni-1.1-flash-preview支援下列值:"360p""720p""1080p""4k"
gemini-omni-flash-preview僅支援"720p"。 -
DURATION:代表生成影片檔案長度的字串。允許的字串為3至10之間的整數,後接「s」代表秒。例如"10s"。
HTTP 方法和網址:
POST https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions
JSON 要求內文:
{
"model": "MODEL_ID",
"input": [
{
"type": "text",
"text": "TEXT_PROMPT"
}
],
"response_format": [
{
"type": "video",
"delivery": "uri",
"gcs_uri": "CLOUD_STORAGE_OUTPUT_URI",
"aspect_ratio": "ASPECT_RATIO",
"resolution": "OUTPUT_RESOLUTION",
"duration": "DURATION"
}
],
"generation_config": {
"video_config": {
"task": "text_to_video"
}
}
}
如要傳送要求,請選擇以下其中一個選項:
curl
將要求主體儲存在名為 request.json 的檔案中,然後執行下列指令:
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
將要求主體儲存在名為 request.json 的檔案中,然後執行下列指令:
$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
{
"id":"INTERACTION_ID",
"model":"gemini-omni-flash-preview",
"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":"thought",
"summary":[
{
"type":"text",
"text":"MODEL THOUGHTS"
}
],
},
{
"type":"model_output",
"content":[
{
"type":"video",
"uri":"gs://some/output_path/123.mp4",
"mime_type":"video/mp4"
}
]
}
],
"object":"interaction"
"role":"model",
"created":"2026-05-29T02:17:56Z",
"updated":"2026-05-29T02:17:56Z",
}
同步:有狀態
使用任何要求資料之前,請先修改下列項目的值:
-
PROJECT_ID:代表 Cloud de Confiance by S3NS 專案 ID 的字串。 -
MODEL_ID:代表要使用的模型 ID 的字串。可接受的值如下:"gemini-omni-1.1-flash-preview"
-
TEXT_PROMPT:用於引導影片生成的文字提示詞。 -
CLOUD_STORAGE_OUTPUT_URI:選用。代表 Cloud Storage bucket 的字串,用於儲存輸出影片。如未提供,回應中會傳回影片位元組。 例如:"gs://video-bucket/output/"。 -
ASPECT_RATIO: 選用:代表輸出影片預期顯示比例的字串。如未提供,系統會根據提示推斷顯示比例。 可接受的值如下:"16:9""9:16"
-
DURATION:代表生成影片檔案長度的字串。允許的字串為3到10之間的整數,後接「s」代表秒數。例如:"10s"
HTTP 方法和網址:
POST https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions
JSON 要求內文:
{
"model": "MODEL_ID",
"background": false,
"store": true,
"stream": false,
"input": [
{
"type": "user_input",
"content": [
{
"type": "text",
"text": "TEXT_PROMPT"
}
]
}
],
"response_format": [
{
"type": "video",
"delivery": "uri",
"gcs_uri": "CLOUD_STORAGE_OUTPUT_URI",
"aspect_ratio": "ASPECT_RATIO",
"duration": "DURATION"
}
],
}
如要傳送要求,請選擇以下其中一個選項:
curl
將要求主體儲存在名為 request.json 的檔案中,然後執行下列指令:
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
將要求主體儲存在名為 request.json 的檔案中,然後執行下列指令:
$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
{
"id":"INTERACTION_ID",
"status":"completed",
"usage":{
"total_tokens":17615,
"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":218
},
"created":"2026-08-12T21:28:40Z",
"updated":"2026-08-12T21:28:40Z",
"event_id":"EVENT_ID",
"steps":[
{
"signature":"...",
"summary":[
{
"text":"MODEL THOUGHTS",
"type":"text"
},
{
"text":"MODEL THOUGHTS",
"type":"text"
}
],
"type":"thought"
},
{
"content":[
{
"mime_type":"video/mp4",
"uri":"gs://some/output_path/123.mp4",
"type":"video"
}
],
"type":"model_output"
}
],
"object":"interaction",
"model":"gemini-omni-flash-preview"
}
使用任何要求資料之前,請先修改下列項目的值:
-
PROJECT_ID:代表 Cloud de Confiance by S3NS 專案 ID 的字串。 -
INTERACTION_ID:非同步要求的互動 ID。
HTTP 方法和網址:
GET https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions/INTERACTION_ID
如要傳送要求,請選擇以下其中一個選項:
curl
執行下列指令:
curl -X GET \
-H "Authorization: Bearer TOKEN" \
"https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions/INTERACTION_ID"
PowerShell
執行下列指令:
$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
{
"id":"INTERACTION_ID",
"model":"gemini-omni-flash-preview",
"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:有狀態的串流
使用任何要求資料之前,請先修改下列項目的值:
-
PROJECT_ID:代表 Cloud de Confiance by S3NS 專案 ID 的字串。 -
MODEL_ID:代表要使用的模型 ID 的字串。可接受的值如下:"gemini-omni-1.1-flash-preview"
-
TEXT_PROMPT:用於引導影片生成的文字提示詞。 -
CLOUD_STORAGE_OUTPUT_URI:選用。代表 Cloud Storage bucket 的字串,用於儲存輸出影片。如未提供,回應中會傳回影片位元組。 例如:"gs://video-bucket/output/"。 -
ASPECT_RATIO: 選用:代表輸出影片預期顯示比例的字串。如未提供,系統會根據提示推斷顯示比例。 可接受的值如下:"16:9""9:16"
-
DURATION:代表生成影片檔案長度的字串。允許的字串為3到10之間的整數,後接「s」代表秒數。例如:"10s"
HTTP 方法和網址:
POST https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions
JSON 要求內文:
{
"model": "MODEL_ID",
"background": false,
"store": true,
"stream": true,
"input": [
{
"type": "user_input",
"content": [
{
"type": "text",
"text": "TEXT_PROMPT"
}
]
}
],
"response_format": [
{
"type": "video",
"delivery": "uri",
"gcs_uri": "CLOUD_STORAGE_OUTPUT_URI",
"aspect_ratio": "ASPECT_RATIO",
"duration": "DURATION"
}
],
}
如要傳送要求,請選擇以下其中一個選項:
curl
將要求主體儲存在名為 request.json 的檔案中,然後執行下列指令:
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
將要求主體儲存在名為 request.json 的檔案中,然後執行下列指令:
$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
event: interaction.created
data: {"interaction":{"id":"INTERACTION_ID","status":"in_progress","object":"interaction","model":"gemini-omni-flash-preview"},"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":{"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":17812,"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":415},"created":"2026-08-12T21:26:20Z","updated":"2026-08-12T21:26:20Z","event_id":"EVENT_ID","object":"interaction","model":"gemini-omni-flash-preview"},"event_id":"EVENT_ID","event_type":"interaction.completed"}
event: done
data: [DONE]
使用任何要求資料之前,請先修改下列項目的值:
-
PROJECT_ID:代表 Cloud de Confiance by S3NS 專案 ID 的字串。 -
INTERACTION_ID: 要求中的互動 ID。
HTTP 方法和網址:
GET https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions/INTERACTION_ID?stream=true
如要傳送要求,請選擇以下其中一個選項:
curl
執行下列指令:
curl -X GET \
-H "Authorization: Bearer TOKEN" \
"https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions/INTERACTION_ID?stream=true"
PowerShell
執行下列指令:
$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
event: interaction.created
data: {"interaction":{"id":"INTERACTION_ID","status":"in_progress","object":"interaction","model":"gemini-omni-flash-preview"},"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-flash-preview"},"event_id":"EVENT_ID","event_type":"interaction.completed"}
event: done
data: [DONE]
非同步
使用任何要求資料之前,請先修改下列項目的值:
-
PROJECT_ID:代表 Cloud de Confiance by S3NS 專案 ID 的字串。 -
MODEL_ID:代表要使用的模型 ID 的字串。可接受的值如下:"gemini-omni-flash-preview""gemini-omni-1.1-flash-preview"
-
TEXT_PROMPT:用於引導影片生成的文字提示詞。 -
CLOUD_STORAGE_OUTPUT_URI:選用。代表 Cloud Storage bucket 的字串,用於儲存輸出影片。如未提供,回應中會傳回影片位元組。 例如:"gs://video-bucket/output/"。 -
ASPECT_RATIO: 選用:代表輸出影片預期顯示比例的字串。如未提供,系統會根據提示推斷顯示比例。 可接受的值如下:"16:9""9:16"
-
OUTPUT_RESOLUTION:選用:代表影片輸出解析度的字串。如未提供,輸出內容預設為 720p。
gemini-omni-1.1-flash-preview支援下列值:"360p""720p""1080p""4k"
gemini-omni-flash-preview僅支援"720p"。 -
DURATION:代表生成影片檔案長度的字串。允許的字串為3至10之間的整數,後接「s」代表秒。例如"10s"。
HTTP 方法和網址:
POST https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions
JSON 要求內文:
{
"model": "MODEL_ID",
"input": [
{
"background": true,
"type": "text",
"text": "TEXT_PROMPT"
}
],
"response_format": [
{
"type": "video",
"delivery": "uri",
"gcs_uri": "CLOUD_STORAGE_OUTPUT_URI",
"aspect_ratio": "ASPECT_RATIO",
"output": "OUTPUT_RESOLUTION",
"duration": "DURATION"
}
],
"generation_config": {
"video_config": {
"task": "text_to_video"
}
}
}
如要傳送要求,請選擇以下其中一個選項:
curl
將要求主體儲存在名為 request.json 的檔案中,然後執行下列指令:
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
將要求主體儲存在名為 request.json 的檔案中,然後執行下列指令:
$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
{
"id":"INTERACTION_ID",
"status":"in_progress",
"object":"interaction"
}
使用任何要求資料之前,請先修改下列項目的值:
-
PROJECT_ID:代表 Cloud de Confiance by S3NS 專案 ID 的字串。 -
INTERACTION_ID: 非同步要求的互動 ID。
HTTP 方法和網址:
GET https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions/INTERACTION_ID
如要傳送要求,請選擇以下其中一個選項:
curl
執行下列指令:
curl -X GET \
-H "Authorization: Bearer TOKEN" \
"https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions/INTERACTION_ID"
PowerShell
執行下列指令:
$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
{
"id":"INTERACTION_ID",
"model":"gemini-omni-flash-preview",
"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",
}
使用 Veo 生成影片
以下範例說明如何使用文字提示詞,透過 Veo 生成影片:
控制台
在 Cloud de Confiance 控制台中,依序前往 「Agent Platform」 > 「Media Studio」頁面。
按一下「影片」。
在「Task」選單中,選取「Text-to-video」。
從「Model」(模型) 選單中,選取顯示的任一選項。
在提示詞輸入框中,輸入描述要生成影片的文字提示詞。
選用:調整下列參數:
顯示比例:選擇 16:9 或 9:16。
結果數量:調整滑桿或輸入介於 1 至 4 的值。
影片長度:從選單中選取影片長度。
輸出目錄:按一下「瀏覽」,建立或選取Cloud Storage bucket,用來儲存產生的檔案。
按一下「執行」。
Python
安裝
pip install --upgrade google-genai
詳情請參閱 SDK 參考文件。
設定環境變數,以便透過 Vertex AI 使用 Google Gen AI SDK:
# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values # with appropriate values for your project. export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT export GOOGLE_CLOUD_LOCATION=global export GOOGLE_GENAI_USE_ENTERPRISE=True
Go
詳情請參閱 SDK 參考文件。
設定環境變數,以便透過 Vertex AI 使用 Google Gen AI SDK:
# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values # with appropriate values for your project. export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT export GOOGLE_CLOUD_LOCATION=global export GOOGLE_GENAI_USE_ENTERPRISE=True
Node.js
安裝
npm install @google/genai
詳情請參閱 SDK 參考文件。
設定環境變數,透過 Vertex AI 使用 Google Gen AI SDK:
# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values # with appropriate values for your project. export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT export GOOGLE_CLOUD_LOCATION=global export GOOGLE_GENAI_USE_ENTERPRISE=True
Java
詳情請參閱 SDK 參考說明文件。
設定環境變數,以便透過 Vertex AI 使用 Google Gen AI SDK:
# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values # with appropriate values for your project. export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT export GOOGLE_CLOUD_LOCATION=global export GOOGLE_GENAI_USE_ENTERPRISE=True
REST
如要進一步瞭解 Veo API,請參閱下列內容:
- 方法:
endpoints.predict VideoGenerationModelInstanceVideoGenerationModelParamsVideoGenerationModelResult
使用下列指令傳送影片生成要求。這項要求會啟動長時間執行的作業,並將輸出內容儲存至您指定的 Cloud Storage bucket。
使用任何要求資料之前,請先修改下列項目的值:
-
PROJECT_ID:代表 Cloud de Confiance by S3NS 專案 ID 的字串。 -
MODEL_ID:代表要使用的模型 ID 的字串。可接受的值如下:- Veo 2:
"veo-2.0-generate-001" - Veo 3:
"veo-3.0-generate-001" - Veo 3:
"veo-3.0-fast-generate-001" - Veo 3:
"veo-3.0-generate-preview"(預先發布版) - Veo 3:
"veo-3.0-fast-generate-preview"(預先發布版) - Veo 3.1:
"veo-3.1-generate-001" - Veo 3.1:
"veo-3.1-fast-generate-001"
- Veo 2:
-
TEXT_PROMPT:用於引導影片生成的文字提示詞。 -
OUTPUT_STORAGE_URI:選用:代表 Cloud Storage bucket 的字串,用於儲存輸出影片。如未提供,回應中會傳回影片位元組。例如:"gs://video-bucket/output/"。 -
RESPONSE_COUNT: 要生成的影片檔案數量。可接受的值範圍為1-4。 -
DURATION:代表生成影片檔案長度的整數。以下是各模型可接受的值:- Veo 2 模型:
5-8。預設為8。 - Veo 3 模型:
4、6或8。預設值為8。
- Veo 2 模型:
-
其他選用參數
視用途而定,使用下列選用變數。在
"parameters": {}物件中加入下列部分或所有參數。"parameters": { "aspectRatio": "ASPECT_RATIO", "negativePrompt": "NEGATIVE_PROMPT", "personGeneration": "PERSON_SAFETY_SETTING", // "resolution": RESOLUTION, // Veo 3 models only "sampleCount": RESPONSE_COUNT, "seed": SEED_NUMBER }-
ASPECT_RATIO: 選用:描述生成影片顯示比例的字串值。您可以使用下列值:"16:9"橫向"9:16"個直向媒體
預設值為
"16:9" -
NEGATIVE_PROMPT:選用:字串值,說明您要禁止模型生成哪些內容。 -
PERSON_SAFETY_SETTING: 選用:字串值,可控制生成人物或臉部的安全設定。您可以使用下列值:-
"allow_adult":只允許生成成人人物和臉孔。 -
"disallow":不會生成人物或臉孔。
預設值為
"allow_adult"。 -
-
RESOLUTION: 選用:控制生成影片解析度的字串值。僅支援 Veo 3 模型。您可以使用下列值:"720p""1080p""4k"(僅限 Veo 3.1 預先發布版模型)
預設值為
"720p"。 -
RESPONSE_COUNT: 選用。整數值,說明要生成的影片數量。 可接受的值範圍為1-4。 -
SEED_NUMBER:選用。模型用來生成確定性影片的 uint32 值。在要求中指定種子編號,但不變更其他參數,模型就會生成相同的影片。可接受的值範圍為0-4294967295。
-
HTTP 方法和網址:
POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MODEL_ID:predictLongRunning
JSON 要求內文:
{ "instances": [ { "prompt": "TEXT_PROMPT" } ], "parameters": { "storageUri": "OUTPUT_STORAGE_URI", "sampleCount": "RESPONSE_COUNT" } }如要傳送要求,請選擇以下其中一個選項:
這項要求會傳回完整的作業名稱,其中包含專屬作業 ID。使用這個完整的作業名稱,輪詢影片生成要求的狀態。curl
將要求主體儲存在名為
request.json的檔案中,然後執行下列指令:curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MODEL_ID:predictLongRunning"PowerShell
將要求主體儲存在名為
request.json的檔案中,然後執行下列指令:$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }
Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MODEL_ID:predictLongRunning" | Select-Object -Expand Content{ "name": "projects/PROJECT_ID/locations/us-central1/publishers/google/models/MODEL_ID/operations/a1b07c8e-7b5a-4aba-bb34-3e1ccb8afcc8" }-
選用:檢查影片生成長時間執行的作業狀態。
使用任何要求資料之前,請先修改下列項目的值:
- PROJECT_ID:您的 Cloud de Confiance by S3NS 專案 ID。
- MODEL_ID:要使用的模型 ID。
- OPERATION_ID:原始生成影片要求中傳回的專屬作業 ID。
HTTP 方法和網址:
POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MODEL_ID:fetchPredictOperation
JSON 要求內文:
{ "operationName": "projects/PROJECT_ID/locations/us-central1/publishers/google/models/MODEL_ID/operations/OPERATION_ID" }如要傳送要求,請選擇以下其中一個選項:
這項要求會傳回作業相關資訊,包括作業是否仍在執行或已完成。curl
將要求主體儲存在名為
request.json的檔案中,然後執行下列指令:curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MODEL_ID:fetchPredictOperation"PowerShell
將要求主體儲存在名為
request.json的檔案中,然後執行下列指令:$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }
Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MODEL_ID:fetchPredictOperation" | Select-Object -Expand Content