Grok Imagine 1.5 Preview

xAI's latest image-to-video model, grok-imagine-video-1.5-preview, is available as a preview through the xAI API. This model transforms a single still image into fluid, cinematic video.

When a user inputs a starting frame along with a prompt describing the motion, the model generates animation—including camera movement, mood, and physics effects—while preserving the details and lighting of the original image. Clips can be generated at up to 720p resolution.

Key features are as follows:

• Natural language prompt control: Camera movement, pacing, sound design, and more can be directed using natural language.
• Sequence consistency: Rather than reinterpreting the original image, it preserves existing details, making it well-suited for connecting multiple shots into longer scenes with a consistent style.