Happy Horse 1.0 is now on ModelsLab

Try Now
Skip to main content
Available now on ModelsLab · Video Generation

VEO 3.1 Lite Image To VideoImage to video. Instant motion.

Generate Videos From Static Images

Built-in Audio

Synchronized Sound Generation

Creates audio automatically matched to video motion, including lip-sync for dialogue and character animation.

Flexible Control

Multiple Aspect Ratios

Support for 16:9 landscape and 9:16 portrait formats with 720p or 1080p resolution options.

Cost Efficient

50% Less Than Fast

Generate high-volume video applications at under 50% cost of Veo 3.1 Fast with identical speed.

Examples

See what VEO 3.1 Lite Image To Video can create

Copy any prompt below and try it yourself in the playground.

Urban Timelapse

A static photograph of a city skyline at dusk transforms into a dynamic timelapse with clouds drifting across the sky, city lights gradually illuminating, and subtle traffic movement below, maintaining photorealistic quality throughout the 6-second transition.

Ocean Waves

A serene beach photograph animates with gentle waves rolling onto shore, foam washing across sand, and soft golden sunlight reflecting off the water surface, creating a calming 8-second loop with natural ocean ambience.

Talking Head

A portrait photograph of a person animates with natural mouth movements and facial expressions synchronized to generated speech, creating a professional talking-head video suitable for presentations or educational content.

Product Showcase

A product photograph rotates smoothly through 360 degrees with subtle lighting reflections, showcasing all angles in a polished 6-second video loop ideal for e-commerce and social media platforms.

For Developers

A few lines of code.
Still image. Animated video.

ModelsLab handles the infrastructure: fast inference, auto-scaling, and a developer-friendly API. No GPU management needed.

  • Serverless: scales to zero, scales to millions
  • Pay per second, no minimums
  • Python and JavaScript SDKs, plus REST API
import requests
response = requests.post(
"https://modelslab.com/api/v7/video-fusion/image-to-video",
json={
"key": "YOUR_API_KEY",
"prompt": "In a frozen, ancient Nordic valley, the shamanic warrior—cloaked in fur, wearing a skull mask with curled horns—stands at the edge of a glacier lake. The wind howls violently, whipping up snow around him as he slams his staff into the icy ground, causing the earth to tremble. Blue runes glow across his mask as magic awakens. A storm brews above as shadowy enemies rise from the snow-covered mountains.",
"init_image": "https://assets.modelslab.ai/generations/3d43311f-116b-4255-a8d8-40862f695359.png"
}
)
print(response.json())

FAQ

Common questions about VEO 3.1 Lite Image To Video

Read the docs

Veo 3.1 Lite Image to Video transforms static images into dynamic animated videos using text descriptions to guide motion. It supports both text-to-video and image-to-video generation with optional synchronized audio generation.

Veo 3.1 Lite costs $0.05 per 720p video and slightly more for 1080p output, making it over 50% cheaper than Veo 3.1 Fast while maintaining the same generation speed.

The model supports 720p and 1080p resolutions at 24 FPS in both 16:9 landscape and 9:16 portrait aspect ratios. Video duration is customizable at 4, 6, or 8 seconds.

Yes, Veo 3.1 Lite includes built-in audio generation that creates synchronized sound by default. You can disable this feature if you prefer silent clips or plan to add your own soundtrack in post-production.

Yes, the model excels at lip-sync applications, animating faces and mouths in sync with generated audio. This makes it ideal for dialogue scenes, character animations, and talking-head content.

You can access Veo 3.1 Lite through Google AI Studio or directly via the API. Both endpoints support the same generation capabilities with flexible duration and resolution options.

Ready to create?

Start generating with VEO 3.1 Lite Image To Video on ModelsLab.