Tạo và chỉnh sửa video bằng Gemini Omni Flash

import base64
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-omni-flash-preview",
    input="A marble rolling fast on a chain reaction style track, continuous smooth shot."
)
with open("marble.mp4", "wb") as f:
    f.write(base64.b64decode(interaction.output_video.data))

import { GoogleGenAI } from '@google/genai';
import * as fs from 'fs';
const ai = new GoogleGenAI({});

const interaction = await ai.interactions.create({  
  model: 'gemini-omni-flash-preview',  
  input: 'A marble rolling fast on a chain reaction style track, continuous smooth shot.',
});

if (interaction.output_video?.data) {
  fs.writeFileSync('marble.mp4', Buffer.from(interaction.output_video.data, 'base64'));
}

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions?key=$API_KEY" \
-H "Content-Type: application/json" \
-d '{
 "model": "gemini-omni-flash-preview",
 "input": "A marble rolling fast on a chain reaction style track, continuous smooth shot."
}'

import base64
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-omni-flash-preview",
    input="A futuristic city with neon lights and flying cars, cyberpunk style",
    response_format={
        "type": "video",  # optional
        "aspect_ratio": "9:16"  # Supported values: "9:16", "16:9"
    }
)
with open("example.mp4", "wb") as f:
    f.write(base64.b64decode(interaction.output_video.data))

import { GoogleGenAI } from '@google/genai';
import * as fs from 'fs';
const ai = new GoogleGenAI({});

const interaction = await ai.interactions.create({
  model: 'gemini-omni-flash-preview',
  input: 'A futuristic city with neon lights and flying cars, cyberpunk style',
  response_format: {
    type: 'video', // optional
    aspect_ratio: '9:16' // Supported values: '9:16', '16:9'
  },
});

if (interaction.output_video?.data) {
  fs.writeFileSync('example.mp4', Buffer.from(interaction.output_video.data, 'base64'));
}

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions?key=$API_KEY" \
-H "Content-Type: application/json" \
-d '{
 "model": "gemini-omni-flash-preview",
 "input": "A futuristic city with neon lights and flying cars, cyberpunk style",
 "response_format": {
   "type": "video",
   "aspect_ratio": "9:16"
 }
}'

import base64
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-omni-flash-preview",
    input=[
        {"type": "image", "data": base64_image, "mime_type": "image/jpeg"},
        {"type": "text", "text": "turn this into realistic footage, using the drawing only as a guide for movement, do not show the drawing in the final video"}
    ],
)
with open("clownfish.mp4", "wb") as f:
    f.write(base64.b64decode(interaction.output_video.data))

import { GoogleGenAI } from '@google/genai';
import * as fs from 'fs';
const ai = new GoogleGenAI({});

const interaction = await ai.interactions.create({
  model: 'gemini-omni-flash-preview',
  input: [
    { type: 'image', data: base64Image, mime_type: 'image/jpeg' },
    { type: 'text', text: 'turn this into realistic footage, using the drawing only as a guide for movement, do not show the drawing in the final video' }
  ]
});

if (interaction.output_video?.data) {
  fs.writeFileSync('clownfish.mp4', Buffer.from(interaction.output_video.data, 'base64'));
}

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions?key=$API_KEY" \
-H "Content-Type: application/json" \
-d '{
 "model": "gemini-omni-flash-preview",
 "input": [
   {"type": "image", "data": "'"$BASE64_IMAGE"'", "mime_type": "image/jpeg"},
   {"type": "text", "text": "turn this into realistic footage, using the drawing only as a guide for movement, do not show the drawing in the final video"}
 ]
}'

import base64
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-omni-flash-preview",
    input=[
        {"type": "image", "data": cat_b64, "mime_type": "image/png"},
        {"type": "image", "data": yarn_b64, "mime_type": "image/png"},
        {"type": "text", "text": "A cat playfully batting at a ball of yarn."}
    ],
)
with open("cat.mp4", "wb") as f:
    f.write(base64.b64decode(interaction.output_video.data))

import { GoogleGenAI } from '@google/genai';
import * as fs from 'fs';
const ai = new GoogleGenAI({});

const interaction = await ai.interactions.create({
  model: 'gemini-omni-flash-preview',
  input: [
    { type: 'image', data: catData, mime_type: 'image/png' },
    { type: 'image', data: yarnData, mime_type: 'image/png' },
    { type: 'text', text: 'A cat playfully batting at a ball of yarn.' }
  ]
});

if (interaction.output_video?.data) {
  fs.writeFileSync('cat.mp4', Buffer.from(interaction.output_video.data, 'base64'));
}

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions?key=$API_KEY" \
-H "Content-Type: application/json" \
-d '{
 "model": "gemini-omni-flash-preview",
 "input": [
   {"type": "image", "data": "'"$CAT_B64"'", "mime_type": "image/png"},
   {"type": "image", "data": "'"$YARN_B64"'", "mime_type": "image/png"},
   {"type": "text", "text": "A cat playfully batting at a ball of yarn."}
 ]
}'

import base64
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-omni-flash-preview",
    input=[
        {"type": "image", "data": base64_image, "mime_type": "image/jpeg"},
        {"type": "text", "text": "turn this into realistic footage, using the drawing only as a guide for movement, do not show the drawing in the final video"}
    ],
    generation_config={
      "video_config": {
        "task": "image_to_video",
      }
    },
)
with open("example.mp4", "wb") as f:
    f.write(base64.b64decode(interaction.output_video.data))

import { GoogleGenAI } from "@google/genai";
import * as fs from 'fs';
const ai = new GoogleGenAI({});

const interaction = await ai.interactions.create({
  model: 'gemini-omni-flash-preview',
  input: [
    { type: 'image', data: base64Image, mime_type: 'image/jpeg' },
    { type: 'text', text: 'turn this into realistic footage, using the drawing only as a guide for movement, do not show the drawing in the final video' }
  ],
  generationConfig: {
    videoConfig: {
      task: 'image_to_video',
    }
  }
});

if (interaction.output_video?.data) {
  fs.writeFileSync('example.mp4', Buffer.from(interaction.output_video.data, 'base64'));
}

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-omni-flash-preview",
    "input": [
      {
        "type": "image",
        "data": "'"$BASE64_IMAGE"'",
        "mime_type": "image/jpeg"
      },
      {
        "type": "text",
        "text": "turn this into realistic footage, using the drawing only as a guide for movement, do not show the drawing in the final video"
      }
    ],
    "generation_config": {
      "video_config": {
        "task": "image_to_video"
      }
    }
  }'

import base64
from google import genai

client = genai.Client()

# Turn 1: Generate initial video
res1 = client.interactions.create(model="gemini-omni-flash-preview", input="A woman playing violin outdoors.")

# Turn 2: Edit the previous video
res2 = client.interactions.create(
    model="gemini-omni-flash-preview",
    previous_interaction_id=res1.id,
    input="Make the violin invisible."
)
with open("example.mp4", "wb") as f:
    f.write(base64.b64decode(res2.output_video.data))

import { GoogleGenAI } from '@google/genai';
import * as fs from 'fs';
const ai = new GoogleGenAI({});

// Turn 1: Generate initial video
const res1 = await ai.interactions.create({
  model: 'gemini-omni-flash-preview',
  input: 'A woman playing violin outdoors.',
});

// Turn 2: Edit the previous video
const res2 = await ai.interactions.create({
  model: 'gemini-omni-flash-preview',
  previous_interaction_id: res1.id,
  input: 'Make the violin invisible.',
});

if (res2.output_video?.data) {
  fs.writeFileSync('example.mp4', Buffer.from(res2.output_video.data, 'base64'));
}

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions?key=$API_KEY" \
-H "Content-Type: application/json" \
-d '{
 "model": "gemini-omni-flash-preview",
 "previous_interaction_id": "'"$PREVIOUS_ID"'",
 "input": "Make the violin invisible."
}'

import time
import base64
from google import genai

client = genai.Client()

# Upload video using the file API
video_file = client.files.upload(file="Video.mp4")

while video_file.state == "PROCESSING":
    print('Waiting for video to be processed.')
    time.sleep(10)
    video_file = client.files.get(name=video_file.name)

if video_file.state == "FAILED":
  raise ValueError(video_file.state)
print(f'Video processing complete: ' + video_file.uri)

# Edit your video
interaction = client.interactions.create(
    model="gemini-omni-flash-preview",
    input=[
        {"type": "document", "uri": video_file.uri},
        {"type": "text", "text": "When the person touches the mirror, make the mirror ripple beautifully like liquid, and the person's arm turns into reflective mirror material"}
    ],
)
with open("example.mp4", "wb") as f:
    f.write(base64.b64decode(interaction.output_video.data))

import { GoogleGenAI } from '@google/genai';
import * as fs from 'fs';
const ai = new GoogleGenAI({});

// Upload video using the file API
let videoFile = await ai.files.upload({
  file: 'Video.mp4',
});

while (videoFile.state === 'PROCESSING') {
  console.log('Waiting for video to be processed.');
  await new Promise(r => setTimeout(r, 10000));
  videoFile = await ai.files.get({ name: videoFile.name });
}

if (videoFile.state === 'FAILED') {
  throw new Error(videoFile.state);
}
console.log('Video processing complete: ' + videoFile.uri);

// Edit your video
const interaction = await ai.interactions.create({
  model: 'gemini-omni-flash-preview',
  input: [
    { type: 'document', uri: videoFile.uri },
    { type: 'text', text: "When the person touches the mirror, make the mirror ripple beautifully like liquid, and the person's arm turns into reflective mirror material" }
  ],
});

if (interaction.output_video?.data) {
  fs.writeFileSync('example.mp4', Buffer.from(interaction.output_video.data, 'base64'));
}

#!/bin/bash
VIDEO_B64=$(encode_file "$VIDEO_FILE")

curl -sS -w "\n[HTTP %{http_code}]\n" "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: ${API_KEY}" \
  -H "Content-Type: application/json" \
  -d @- <<EOF > video_editing_response.json
{
  "model": "gemini-omni-flash-preview",
  "input": [
    {
      "type": "user_input",
      "content": [
        {
          "type": "video",
          "mime_type": "video/mp4",
          "data": "$VIDEO_B64"
        },
        {
          "type": "text",
          "text": "When the person touches the mirror, make the mirror ripple beautifully like liquid, and the person's arm turns into reflective mirror material"
        }
      ]
    }
  ],
  "response_format": { "type": "video" }
}
EOF

import time
from google import genai

client = genai.Client()

# 1. Request video via URI delivery
interaction = client.interactions.create(
    model="gemini-omni-flash-preview",
    input="A beautiful sunset.",
    response_format={"type": "video", "delivery": "uri"}
)

# 2. Extract file name and poll for ACTIVE state
video_output = interaction.output_video
file_name = video_output.uri.split("/")[-1] # Extract ID

print("Waiting for video processing...")
while True:
    f_info = client.files.get(name=f"files/{file_name}")
    if f_info.state.name == "ACTIVE":
        break
    elif f_info.state.name == "FAILED":
        raise RuntimeError("Generation failed.")
    time.sleep(5)

# 3. Download the final video
video_bytes = client.files.download(file=video_output.uri)
with open("output.mp4", "wb") as f:
    f.write(video_bytes)

import { GoogleGenAI } from '@google/genai';
const ai = new GoogleGenAI({});

// 1. Request video via URI delivery
const interaction = await ai.interactions.create({
  model: 'gemini-omni-flash-preview',
  input: 'A beautiful sunset.',
  response_format: { type: 'video', delivery: 'uri' },
});

// 2. Extract file name and poll for ACTIVE state
const videoOutput = interaction.output_video;
const fileId = videoOutput.uri.match(/files\/([a-zA-Z0-9]+)/)[1];
const name = `files/${fileId}`;

console.log("Waiting for video processing...");
while (true) {
  const fInfo = await ai.files.get({ name });
  if (fInfo.state.name === 'ACTIVE') break;
  if (fInfo.state.name === 'FAILED') throw new Error("Generation failed.");
  await new Promise(r => setTimeout(r, 5000));
}

// 3. Download the final video
await ai.files.download({
  file: videoOutput,
  downloadPath: 'output.mp4',
});
console.log("💾 Saved video to output.mp4");

#!/bin/bash

# 1. Initial request to generate the video
RESPONSE=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions?key=$API_KEY" \
-H "Content-Type: application/json" \
-d '{
 "model": "gemini-omni-flash-preview",
 "input": "A beautiful sunset over a calm ocean.",
 "response_format": {"type": "video", "delivery": "uri"}
}')

# Extract FILE_ID from the URI (e.g., "files/abc-123" -> "abc-123")
FILE_URI=$(echo $RESPONSE | jq -r '.output_video.uri')
FILE_ID=$(echo $FILE_URI | cut -d'/' -f2)

echo "Video requested (ID: $FILE_ID). Waiting for processing..."

# 2. Polling loop
while true; do
 # Get current file status
 STATUS_JSON=$(curl -s -X GET "https://generativelanguage.googleapis.com/v1beta/files/$FILE_ID?key=$API_KEY")
 STATE=$(echo $STATUS_JSON | jq -r '.state')

 if [ "$STATE" == "ACTIVE" ]; then
   echo "Processing complete! Downloading..."
   break
 elif [ "$STATE" == "FAILED" ]; then
   echo "Error: Generation failed."
   exit 1
 else
   echo "Current state: $STATE... (waiting 5s)"
   sleep 5
 fi
done

# 3. Final download
curl -L -X GET "https://generativelanguage.googleapis.com/v1beta/files/$FILE_ID:download?alt=media&key=$API_KEY" \
--output "output.mp4"

echo "Done! Video saved to output.mp4"