Skip to main content

Overview

Image to Video converts static images into dynamic video content with AI-generated motion and cinematic effects. The API analyzes images and creates realistic movement, camera motion, and environmental effects to bring still photos to life. Processing: See recent typical API-job times. Jobs run asynchronously, and duration varies with the input, selected settings, and queue load.

How It Works

  1. Provide a source image - Upload the image you want to animate
  2. Add a prompt to guide movement, or let the model choose.
  3. API generates the video - AI creates natural motion and effects
  4. Download the result - Retrieve your animated video

Use Cases

For a complete product demo workflow, follow the product video starter recipe. It covers image preparation, video generation, and downloading the result.
  • Social media content - Turn photos into engaging video posts
  • Marketing videos - Create dynamic content from product photos
  • Storytelling - Bring static images to life for narratives
  • Real estate - Animate property photos for virtual tours
  • E-commerce - Dynamic product showcases

Best Practices

Source Image Quality

Use high-quality images with clear subjects - Better images produce smoother, more realistic animations.
  • High resolution - At least 720p for best results
  • Clear subjects - Well-defined elements animate better
  • Good composition - Leave “room” for motion in your frame
  • Appropriate content - Images with implied motion work well

Motion Prompts

The motion prompt is optional. Use it to describe the movement you want: ✅ Good prompts:
  • “Camera slowly panning right, leaves gently swaying in wind”
  • “Zoom in on the subject with slight parallax effect”
  • “Water rippling, clouds moving slowly across the sky”
  • “Person walking forward, hair blowing in breeze”
❌ Avoid:
  • No motion description: “A beautiful landscape”
  • Impossible physics: “Person flying through wall”
  • Conflicting motions: “Zoom in and zoom out simultaneously”

Image Types That Animate Well

Model selection

model="default" currently selects kling-3.0 on paid tiers and ltx-2.5 on the free tier. Set a model explicitly when your workflow needs a fixed duration and resolution combination. The examples use ltx-2.5, which supports five-second clips at 480p; the paid default does not support 480p. Other current options include gemini-omni-1.1, minimax-h3, seedance-2.0-mini, seedance-2.5, and veo3.1-lite. Check the API reference for each model’s supported durations, resolutions, and audio settings. Audio is disabled by default and is unavailable on some models. For a final reference frame, set assets.end_image_file_path on a supported model. End-frame support can depend on resolution and duration; for example, Veo 3.1 variants require a duration of eight seconds or less.

Code Examples

Basic Image to Video

Pricing

Image to Video pricing depends on the model, resolution, and duration you choose. You pay for the frames that render. The create response estimates credits_charged; read the completed job for the final cost.

Resolution Limits

Supported resolutions are 360p, 480p, 720p, 1080p, and 4k, depending on the model and your subscription tier. For example, kling-3.0 supports 4k. Output defaults to 720p on paid tiers and 480p on the free tier. See Resolution Limits for tier details.
Try this in our Google Colab Cookbook: Run this API with sample code. Just add your API key.

API Reference

Image to Video API Reference

View full API specification

Product Video Recipe

Generate one product clip, compare model costs, and plan a catalog workflow

Text to Video

Generate videos from text descriptions

Animation

Create animated videos with motion effects