Generate a video with multimodal image, video, and audio references. Use the library for reusable uploads. For models with direct media fields, drag assets straight into those inputs.
Generation price
19.00 credits/sec
95.00 credits total (5s)
First Frame?Optional first frame image. Leave empty if using multimodal references only.
Last Frame?Optional last frame image for first/last-frame mode.
Reference Images?Optional array of reference images. Max 7. Do not combine multimodal references with first/last frame mode.
0/7
Drop media here
Reference Videos?Optional array of reference videos. Max 3.
0/3
Drop media here
Reference Audio?Optional array of reference audio tracks. Max 3.