AI拍视频终于能记住主角长啥样了
现在的AI视频生成，每次镜头切换主角就变脸、声音也换人，因为模型没有「跨镜头记忆」。UnityShots给视频模型装了两个固定大小的记忆槽：一个存开场镜头（长期记忆），一个存上一镜结尾（短期记忆），每次切镜头时用「边界门控」自动决定该忘掉什么、记住什么。音频也单独注入一个参考说话人音色，不会因为镜头切换就变声。它还能让你在生成时手动控制转场强度。在200个多文化多语言片段测试中，跨镜头一致性全面超过开源方案，追平最强闭源系统。这不是你明天就能用的工具，但它解决了AI视频生成从「单镜头」到「多镜头叙事」的关键一步。
📄 原文摘要(英文)
Generating a coherent multi-shot video requires structured cross-shot memory. Subject appearance, scene context, and speaker identity must persist across cuts. Existing approaches either train end-to-end over fixed-length sequences and cannot scale, generate shot-by-shot with memory banks that grow linearly, or orchestrate pretrained generators under an LLM planner without a multi-shot-aware backbone. We present UnityShots, a memory-driven multi-shot audio-video generation system built on LTX-2.3, trained on annotated cinematic and music-video shots. The video stream maintains two fixed-size slots, a long-term memory (LTM) slot anchored to the opening shot and a short-term memory (STM) slot holding the immediately preceding tail, both updated at every cut by a boundary-conditioned gate that fuses visual cut probability and beat-tracker signals. The audio stream injects a reference speaker token at every shot to preserve vocal timbre without a sliding audio bank. A discrete cut-type prior, learned through AdaLN, becomes an inference-time control knob over transition strength. We release a benchmark of 200 multi-cultural multi-shot sequences spanning six ethnic regions and ten or more languages, with per-shot reference identities, reference audio, and per-boundary transition labels. Evaluated across I2V, T2V, and R2V conditioning modes, UnityShots leads open-source baselines on every cross-shot coherence metric and matches the strongest closed-source system on the multi-shot axes.