You can add up to 3 images per scene (12 in total). Your image is used as the visual of the scene; if you add several, the scene's narration time is split between them in order. The AI writes the script to match your images. Scenes without images are generated by AI.

Each scene's image (your own photo or the AI-generated one) becomes a 10-second moving video clip. Each scene costs an extra 10 credits; on Pro and Business your monthly video allowance is used first. Scenes where you add more than one image are not animated and are not charged. If a scene cannot be animated, it stays as a still image and its credits are refunded. Production takes longer.