Membuat video dari gambar

REST

Pembuatan video dapat memerlukan waktu lebih dari satu menit hingga selesai. Anda dapat memilih dari beberapa mode interaksi, bergantung pada alur kerja Anda:

• Sinkron: stateless: Buat video dalam satu permintaan tanpa menyimpan status interaksi di server.
• Sinkron: stateful: Tetapkan store ke true untuk mempertahankan status interaksi, yang memungkinkan Anda mengambil hasil nanti atau merujuk ID interaksi untuk pengeditan video multi-turn.
• Sinkron: streaming stateful: Tetapkan store dan stream ke true untuk menerima pemikiran model secara inkremental saat dibuat, diikuti dengan video output.
• Asinkron: Tetapkan background ke true untuk menjalankan pembuatan video di latar belakang dan mengambil hasilnya nanti menggunakan ID interaksi.

Interaksi tersimpan dan asinkron dipertahankan hingga 14 hari.

Untuk mengetahui informasi selengkapnya tentang cara menggunakan Gemini Omni Flash API, lihat Interactions API.

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

{
  "model": "MODEL_ID",
  "input": [
    {
      "type": "text",
      "text": "TEXT_PROMPT"
    },
    {
      "type": "image",
      "uri": "CLOUD_STORAGE_INPUT_URI",
      "mime_type": "image/png"
    }
  ],
  "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": "image_to_video"
    }
  }
}

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"

$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",
}

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

{
  "model": "MODEL_ID",
  "background": false,
  "store": true,
  "stream": false,
  "input": [
    {
      "type": "user_input",
      "content": [
        {
          "type": "text",
          "text": "TEXT_PROMPT"
        },
        {
          "type": "image",
          "uri": "CLOUD_STORAGE_INPUT_URI",
          "mime_type": "image/png"
        }
      ]
    }
  ],
  "response_format": [
    {
      "type": "video",
      "delivery": "uri",
      "gcs_uri": "CLOUD_STORAGE_OUTPUT_URI",
      "aspect_ratio": "ASPECT_RATIO",
      "resolution": "OUTPUT_RESOLUTION",
      "duration": "DURATION"
    }
  ]
}

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"

$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",
}

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

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

$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",
}

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

{
  "model": "MODEL_ID",
  "background": false,
  "store": true,
  "stream": true,
  "input": [
    {
      "type": "user_input",
      "content": [
        {
          "type": "text",
          "text": "TEXT_PROMPT"
        },
        {
          "type": "image",
          "uri": "CLOUD_STORAGE_INPUT_URI",
          "mime_type": "image/png"
        }
      ]
    }
  ],
  "response_format": [
    {
      "type": "video",
      "delivery": "uri",
      "gcs_uri": "CLOUD_STORAGE_OUTPUT_URI",
      "aspect_ratio": "ASPECT_RATIO",
      "resolution": "OUTPUT_RESOLUTION",
      "duration": "DURATION"
    }
  ]
}

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"

$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":{"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]

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

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

$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]

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

{
  "model": "MODEL_ID",
  "input": [
    {
      "background": true,
      "type": "text",
      "text": "TEXT_PROMPT"
    },
    {
      "type": "image",
      "uri": "CLOUD_STORAGE_INPUT_URI",
      "mime_type": "image/png"
    }
  ],
  "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": "image_to_video"
    }
  }
}

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"

$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"
}

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

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

$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",
}

Konsol

1. Di konsol Cloud de Confiance , buka halaman Agent Platform > Media Studio.

   Media Studio

2. Klik Video.

3. Di menu Task, pilih Image-to-video.

4. Dari menu Model, pilih model dari opsi yang ditampilkan.

5. Di kotak Prompt, masukkan perintah teks yang menjelaskan video yang akan dibuat.

6. Di bagian Input images, klik Start untuk mengupload gambar untuk bingkai pertama.

7. Opsional: klik Akhiri untuk mengupload gambar untuk frame terakhir.

8. Opsional: Sesuaikan Parameter berikut:

   • Rasio aspek: pilih 16:9 atau 9:16.

   • Number of results: sesuaikan penggeser atau masukkan nilai antara 1 dan 4.

   • Durasi video: pilih durasi video dari menu.

   • Direktori output: klik Jelajahi untuk membuat atau memilih bucket Cloud Storage untuk menyimpan file yang dihasilkan.

9. Klik Run.

Python

Instal

pip install --upgrade google-genai

Untuk mempelajari lebih lanjut, lihat dokumentasi referensi SDK.

Tetapkan variabel lingkungan untuk menggunakan Google Gen AI SDK dengan Vertex AI:

# 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

import time
from google import genai
from google.genai.types import GenerateVideosConfig, Image

client = genai.Client()

# TODO(developer): Update and un-comment below line
# output_gcs_uri = "gs://your-bucket/your-prefix"

operation = client.models.generate_videos(
    model="veo-3.1-generate-001",
    prompt="Extreme close-up of a cluster of vibrant wildflowers swaying gently in a sun-drenched meadow.",
    image=Image(
        gcs_uri="gs://cloud-samples-data/generative-ai/image/flowers.png",
        mime_type="image/png",
    ),
    config=GenerateVideosConfig(
        aspect_ratio="16:9",
        output_gcs_uri=output_gcs_uri,
    ),
)

while not operation.done:
    time.sleep(15)
    operation = client.operations.get(operation)
    print(operation)

if operation.response:
    print(operation.result.generated_videos[0].video.uri)

# Example response:
# gs://your-bucket/your-prefix

Go

Pelajari cara menginstal atau mengupdate Go.

Untuk mempelajari lebih lanjut, lihat dokumentasi referensi SDK.

Tetapkan variabel lingkungan untuk menggunakan Google Gen AI SDK dengan Vertex AI:

# 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

import (
	"context"
	"fmt"
	"io"
	"time"

	"google.golang.org/genai"
)

// generateVideoFromImage shows how to gen video from img.
func generateVideoFromImage(w io.Writer, outputGCSURI string) error {
	//outputGCSURI = "gs://your-bucket/your-prefix"
	ctx := context.Background()

	client, err := genai.NewClient(ctx, &genai.ClientConfig{
		HTTPOptions: genai.HTTPOptions{APIVersion: "v1"},
	})
	if err != nil {
		return fmt.Errorf("failed to create genai client: %w", err)
	}

	image := &genai.Image{
		GCSURI:   "gs://cloud-samples-data/generative-ai/image/flowers.png",
		MIMEType: "image/png",
	}

	config := &genai.GenerateVideosConfig{
		AspectRatio:  "16:9",
		OutputGCSURI: outputGCSURI,
	}

	modelName := "veo-3.0-generate-preview"
	prompt := "Extreme close-up of a cluster of vibrant wildflowers swaying gently in a sun-drenched meadow."
	operation, err := client.Models.GenerateVideos(ctx, modelName, prompt, image, config)
	if err != nil {
		return fmt.Errorf("failed to start video generation: %w", err)
	}

	// Polling until the operation is done
	for !operation.Done {
		time.Sleep(15 * time.Second)
		operation, err = client.Operations.GetVideosOperation(ctx, operation, nil)
		if err != nil {
			return fmt.Errorf("failed to get operation status: %w", err)
		}
	}

	if operation.Response != nil && len(operation.Response.GeneratedVideos) > 0 {
		videoURI := operation.Response.GeneratedVideos[0].Video.URI
		fmt.Fprintln(w, videoURI)
		return nil
	}

	// Example response:
	// gs://your-bucket/your-prefix/videoURI

	return fmt.Errorf("video generation failed or returned no results")
}

Node.js

Instal

npm install @google/genai

Untuk mempelajari lebih lanjut, lihat dokumentasi referensi SDK.

Tetapkan variabel lingkungan untuk menggunakan Google Gen AI SDK dengan Vertex AI:

# 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

const {GoogleGenAI} = require('@google/genai');

const GOOGLE_CLOUD_PROJECT = process.env.GOOGLE_CLOUD_PROJECT;
const GOOGLE_CLOUD_LOCATION = process.env.GOOGLE_CLOUD_LOCATION || 'global';

async function generateVideo(
  outputGcsUri,
  projectId = GOOGLE_CLOUD_PROJECT,
  location = GOOGLE_CLOUD_LOCATION
) {
  const client = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
  });

  let operation = await client.models.generateVideos({
    model: 'veo-3.1-fast-generate-001',
    prompt:
      'Extreme close-up of a cluster of vibrant wildflowers swaying gently in a sun-drenched meadow',
    image: {
      gcsUri: 'gs://cloud-samples-data/generative-ai/image/flowers.png',
      mimeType: 'image/png',
    },
    config: {
      aspectRatio: '16:9',
      outputGcsUri: outputGcsUri,
    },
  });

  while (!operation.done) {
    await new Promise(resolve => setTimeout(resolve, 15000));
    operation = await client.operations.get({operation: operation});
    console.log(operation);
  }

  if (operation.response) {
    console.log(operation.response.generatedVideos[0].video.uri);
  }
  return operation;
}

Java

Pelajari cara menginstal atau mengupdate Java.

Untuk mempelajari lebih lanjut, lihat dokumentasi referensi SDK.

Tetapkan variabel lingkungan untuk menggunakan Google Gen AI SDK dengan Vertex AI:

# 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

import com.google.genai.Client;
import com.google.genai.types.GenerateVideosConfig;
import com.google.genai.types.GenerateVideosOperation;
import com.google.genai.types.GenerateVideosResponse;
import com.google.genai.types.GeneratedVideo;
import com.google.genai.types.GetOperationConfig;
import com.google.genai.types.Image;
import com.google.genai.types.Video;
import java.util.concurrent.TimeUnit;

public class VideoGenWithImg {

  public static void main(String[] args) throws InterruptedException {
    // TODO(developer): Replace these variables before running the sample.
    String modelId = "veo-3.1-generate-001";
    String outputGcsUri = "gs://your-bucket/your-prefix";
    generateContent(modelId, outputGcsUri);
  }

  // Generates a video with an image and a text prompt.
  public static String generateContent(String modelId, String outputGcsUri)
      throws InterruptedException {
    // Client Initialization. Once created, it can be reused for multiple requests.
    try (Client client = Client.builder().location("global").vertexAI(true).build()) {

      GenerateVideosOperation operation =
          client.models.generateVideos(
              modelId,
              "Extreme close-up of a cluster of vibrant wildflowers"
                  + " swaying gently in a sun-drenched meadow.",
              Image.builder()
                  .gcsUri("gs://cloud-samples-data/generative-ai/image/flowers.png")
                  .mimeType("image/png")
                  .build(),
              GenerateVideosConfig.builder()
                  .aspectRatio("16:9")
                  .outputGcsUri(outputGcsUri)
                  .build());

      while (!operation.done().orElse(false)) {
        TimeUnit.SECONDS.sleep(15);
        operation =
            client.operations.getVideosOperation(operation, GetOperationConfig.builder().build());
      }

      String generatedVideoUri =
          operation
              .response()
              .flatMap(GenerateVideosResponse::generatedVideos)
              .flatMap(videos -> videos.stream().findFirst())
              .flatMap(GeneratedVideo::video)
              .flatMap(Video::uri)
              .orElseThrow(
                  () ->
                      new IllegalStateException(
                          "Could not get the URI from the generated video"));

      System.out.println("Generated video URI: " + generatedVideoUri);
      // Example response:
      // Generated video URI: gs://your-bucket/your-prefix/generated-video-123.mp4
      return generatedVideoUri;
    }
  }
}

REST

Untuk mengetahui informasi selengkapnya tentang Veo API, lihat bagian berikut:

• Metode: endpoints.predict
• VideoGenerationModelInstance
• VideoGenerationModelParams
• VideoGenerationModelResult

1. Gunakan perintah berikut untuk mengirim permintaan pembuatan video. Permintaan ini memulai operasi yang berjalan lama dan menyimpan output ke bucket Cloud Storage yang Anda tentukan.

   Sebelum menggunakan salah satu data permintaan, lakukan penggantian berikut:

   • PROJECT_ID: String yang mewakili Cloud de Confiance by S3NS project ID Anda.
   • MODEL_ID: String yang mewakili ID model yang akan digunakan. Berikut adalah nilai yang diterima:
     • Veo 2:veo-2.0-generate-001
     • Veo 3:veo-3.0-generate-001
     • Veo 3.1:veo-3.1-generate-001
     • Veo 3.1:veo-3.1-fast-generate-001
   • TEXT_PROMPT: Perintah teks yang digunakan untuk memandu pembuatan video.
   • INPUT_IMAGE: String berenkode base64 yang mewakili gambar input. Untuk kualitas terbaik, sebaiknya resolusi gambar input adalah 720p (1280 x 720 piksel) atau lebih tinggi, dan memiliki rasio aspek 16:9 atau 9:16. Gambar dengan rasio aspek atau ukuran lain dapat diubah ukurannya atau dipangkas di bagian tengah saat gambar diupload.
   • MIME_TYPE: String yang merepresentasikan jenis MIME gambar input. Hanya gambar dengan jenis MIME berikut yang didukung:
     • "image/jpeg"
     • "image/png"
   • OUTPUT_STORAGE_URI: Opsional: String yang merepresentasikan bucket Cloud Storage untuk menyimpan video output. Jika tidak diberikan, byte video akan ditampilkan dalam respons. Contoh: "gs://video-bucket/output/".
   • RESIZE_MODE: String yang mewakili mode pengubahan ukuran yang akan digunakan. Berikut adalah nilai yang diterima:
     • "crop": Pangkas video agar sesuai dengan ukuran baru.
     • "pad": Beri padding pada video agar sesuai dengan ukuran baru.
   • RESPONSE_COUNT: Jumlah file video yang akan dibuat. Rentang nilai yang diterima adalah 1-4.
   • DURATION: Bilangan bulat yang mewakili durasi file video yang dihasilkan. Berikut adalah nilai yang diterima untuk setiap model:
     • Model Veo 2: 5-8. Defaultnya adalah 8.
     • Model Veo 3: 4, 6, atau 8. Defaultnya adalah 8.

   • Parameter opsional tambahan

     Gunakan variabel opsional berikut bergantung pada kasus penggunaan Anda. Tambahkan beberapa atau semua parameter berikut dalam objek "parameters": {}.

     "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: Opsional: Nilai string yang menjelaskan rasio aspek video yang dibuat. Anda dapat menggunakan nilai berikut:
       • "16:9" untuk lanskap
       • "9:16" untuk potret

       Nilai defaultnya adalah "16:9"

     • NEGATIVE_PROMPT: Opsional: Nilai string yang menjelaskan konten yang tidak ingin Anda hasilkan oleh model.
     • PERSON_SAFETY_SETTING: Opsional: Nilai string yang mengontrol setelan keamanan untuk pembuatan orang atau pembuatan wajah. Anda dapat menggunakan nilai berikut:
       • "allow_adult": Hanya mengizinkan pembuatan orang dan wajah dewasa.
       • "disallow": Tidak menghasilkan orang atau wajah.

       Nilai defaultnya adalah "allow_adult".

     • RESOLUTION: Opsional: Nilai string yang mengontrol resolusi video yang dihasilkan. Didukung oleh model Veo 3 saja. Anda dapat menggunakan nilai berikut:
       • "720p"
       • "1080p"
       • "4k" (Khusus model Pratinjau Veo 3.1)

       Nilai defaultnya adalah "720p".

     • RESPONSE_COUNT: Opsional. Nilai bilangan bulat yang menjelaskan jumlah video yang akan dibuat. Rentang nilai yang diterima adalah 1-4.
     • SEED_NUMBER: Opsional. Nilai uint32 yang digunakan model untuk membuat video deterministik. Menentukan nomor seed dengan permintaan Anda tanpa mengubah parameter lain akan memandu model untuk menghasilkan video yang sama. Rentang nilai yang diterima adalah 0-4294967295.

   Metode HTTP dan URL:

   POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MODEL_ID:predictLongRunning

   Meminta isi JSON:

   {
     "instances": [
       {
         "prompt": "TEXT_PROMPT",
         "image": {
           "bytesBase64Encoded": "INPUT_IMAGE",
           "mimeType": "MIME_TYPE"
         }
       }
     ],
     "parameters": {
       "storageUri": "OUTPUT_STORAGE_URI",
       "sampleCount": RESPONSE_COUNT
       "resizeMode": "RESIZE_MODE"
     }
   }
   

   Untuk mengirim permintaan Anda, pilih salah satu opsi berikut:

   curl

   Simpan isi permintaan dalam file bernama request.json, dan jalankan perintah berikut:

   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

   Simpan isi permintaan dalam file bernama request.json, dan jalankan perintah berikut:

   $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

   Permintaan ini menampilkan nama operasi lengkap dengan ID operasi yang unik. Gunakan nama operasi lengkap ini untuk melakukan polling status permintaan pembuatan video.
   {
     "name": "projects/PROJECT_ID/locations/us-central1/publishers/google/models/MODEL_ID/operations/a1b07c8e-7b5a-4aba-bb34-3e1ccb8afcc8"
   }
   

2. Opsional: Periksa status operasi yang berjalan lama pembuatan video.

   Sebelum menggunakan salah satu data permintaan, lakukan penggantian berikut:

   • PROJECT_ID: Project ID Cloud de Confiance by S3NS Anda.
   • MODEL_ID: ID model yang akan digunakan.
   • OPERATION_ID: ID operasi unik yang ditampilkan dalam permintaan pembuatan video asli.

   Metode HTTP dan URL:

   POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MODEL_ID:fetchPredictOperation

   Meminta isi JSON:

   {
     "operationName": "projects/PROJECT_ID/locations/us-central1/publishers/google/models/MODEL_ID/operations/OPERATION_ID"
   }
   

   Untuk mengirim permintaan Anda, pilih salah satu opsi berikut:

   curl

   Simpan isi permintaan dalam file bernama request.json, dan jalankan perintah berikut:

   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

   Simpan isi permintaan dalam file bernama request.json, dan jalankan perintah berikut:

   $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

   Permintaan ini menampilkan informasi tentang operasi, termasuk apakah operasi masih berjalan atau sudah selesai.

   Respons

   {
     "name": "projects/PROJECT_ID/locations/us-central1/publishers/google/models/MODEL_ID/operations/OPERATION_ID",
     "done": true,
     "response": {
       "raiMediaFilteredCount": 0,
       "@type": "type.googleapis.com/cloud.ai.large_models.vision.GenerateVideoResponse",
       "videos": [
         {
           "gcsUri":"gs://BUCKET_NAME/TIMESTAMPED_FOLDER/sample_0.mp4",
           "mimeType": "video/mp4"
         }
       ]
     }
   }