Reference to Video AI (Multimodal)

Multimodal video generation using reference images, videos, and audio to guide consistency, motion, and style.

Add reference images, videos, or audio, then type @ to insert them and describe the scene, action, and camera motion...
49 credits

Recent Creations

No recent creations yet

Select one of the studio launchers above to create your first AI image, cinematic video, or audio track.

Create Video

Inspiration

Explore AI creative examples and find inspiration for your next project with AI Kenerate.

MiniMax-H3

Multi-reference Cinematic Motion

“Character consistent camera tracking shot through misty cyberpunk alleyway”

Seedance 2.5

Dynamic Subject Reference Transition

“Seamless dynamic lighting transformation respecting subject identity and atmosphere”

Frequently Asked Questions

  • Reference to Video allows you to supply multiple reference images (up to 9) and videos (up to 3) as conditioning inputs to guide character consistency, camera motion, and action style.

  • Currently, MiniMax-H3 and Seedance 2.5 support multimodal reference-based video generation. Unsupported models are automatically hidden on this page.