google / veo-2

State of the art video generation model. Veo 2 can faithfully follow simple and complex instructions, and convincingly simulates real-world physics as well as a wide range of visual styles. (Updated 3 weeks, 5 days ago)

Warm

Public
79.6K runs
$0.50 per second of output video
Commercial use

Iterate in playground

Run with an API

Playground API Examples README

Prediction

google/veo-2

Official model

google/veo-2

tjqhsk4eddrma0cn7w38c91tq8

Status

Succeeded

Source

Web

Total duration

2m 30s

Created

4 months ago

Input

prompt: a dog riding a skateboard
duration: 5
aspect_ratio: 16:9
enhance_prompt

{
  "prompt": "a dog riding a skateboard",
  "duration": 5,
  "aspect_ratio": "16:9",
  "enhance_prompt": true
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run google/veo-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  prompt: "a dog riding a skateboard",
  duration: 5,
  aspect_ratio: "16:9",
  enhance_prompt: true
};

const output = await replicate.run("google/veo-2", { input });

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run google/veo-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "google/veo-2",
    input={
        "prompt": "a dog riding a skateboard",
        "duration": 5,
        "aspect_ratio": "16:9",
        "enhance_prompt": True
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run google/veo-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "input": {
      "prompt": "a dog riding a skateboard",
      "duration": 5,
      "aspect_ratio": "16:9",
      "enhance_prompt": true
    }
  }' \
  https://api.replicate.com/v1/models/google/veo-2/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Generated in

2 minutes 30 seconds

Tweak it Share Report

Want to make some of these yourself?

Run this model