Multimodal Reference Singing Shot
Watch an official MiniMax H3 multimodal-reference example that combines camera movement, character appearance, and an audio vocal reference in one short singing shot.
What this example shows
MiniMax Research publishes this sample with an exact prompt linking movement from Video 1, the character from Image 2, and vocals from Audio 3. It is useful for studying how multiple references are described, but it does not establish which reference controls are available from every provider.
Original prompt status
The original source published this prompt:
Reference the Hitchcock camera movement from Video 1, have the character in Image 2 sing, with the vocals matching Audio 3.
Source and independence notes
This page documents a public source example. minimax3.com did not create the source video and is not affiliated with, endorsed by, authorized by, or operated by MiniMax or Hailuo.
Related MiniMax H3 examples
Continue with other source-verified examples from this gallery.
Turn the reference into your own shot plan
Start with a text brief on the homepage, or switch to image-to-video when you already have a first frame. Check the displayed model and provider settings before generating.
Start from text

