Tag
UnityShots is a memory-driven multi-shot audio-video generation system that maintains consistent subject appearance and audio across video cuts using fixed-size long-term and short-term memory slots with boundary-conditioned gates and discrete cut-type priors. It outperforms open-source baselines on cross-shot coherence metrics and matches closed-source systems.
Published a custom kernel to further optimize LTX-2.3 from Lightricks, achieving 1.52x speedup on GB10, building upon previous torch.compile and cuDNN attention optimizations.