MiniMax H3 reference-conditioned video (Ref2VA): up to 9 image, 3 video, 3 audio refs, cited as <Picture N>/<Video N>/<Audio N>.
MiniMax H3 reference-conditioned video (Ref2VA): up to 9 image, 3 video, 3 audio refs, cited as <Picture N>/<Video N>/<Audio N>.