MiniMax H3 Singularity LoRA reference-to-video mixes up to nine images, three clips and three audio clips with up to three LoRAs on a community H3 fine-tune. Shots run 3 to 15 seconds at 480p to 1080p with stereo sound, in seven aspect ratios.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- Output7s
singer-on-stage-named-refs A portrait and an empty stage. The platinum waves and the silver sequinned gown come from <Picture 1>; the red curtain, the big band, the chandeliers and the spotlights come from <Picture 2>, which the prompt also describes so the whole room carries through. The glide in from the tables, the hand down the gown and the first sung line come from the prompt.
- 331207
- 540p
- 16:9
- Output7s
singer-on-the-stage A portrait and an empty stage. The walk-out, the spin and the first sung line come from the prompt; the face and the dress come from Picture 1.
- 42
- 540p
- 16:9
- Output7s
rooftop-sparring One still per character and no LoRA. Both people keep their look through a fast exchange and end the shot laughing.
- 42
- 540p
- 16:9
This example starts at $0.06 per output second. The Playground updates the estimate when you change the settings.