LightX2V Studio
MiniMax-H3
Text, first/last-frame and multi-reference audio-video model for synchronized clips from a prompt plus a first frame, last frame, or both; ref2av additionally accepts several reference images, videos and audios at once, suited to 5-15s concepts.
Create with LightX2V
- Choose a focused video, image, Avatar, or voice creation task.
- Control the available model and generation settings.
- Review, reuse, download, or share completed work.