{"ID":2891542,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.17963","arxiv_id":"2507.17963","title":"Zero-Shot Dynamic Concept Personalization with Grid-Based LoRA","abstract":"Recent advances in text-to-video generation have enabled high-quality synthesis from text and image prompts. While the personalization of dynamic concepts, which capture subject-specific appearance and motion from a single video, is now feasible, most existing methods require per-instance fine-tuning, limiting scalability. We introduce a fully zero-shot framework for dynamic concept personalization in text-to-video models. Our method leverages structured 2x2 video grids that spatially organize input and output pairs, enabling the training of lightweight Grid-LoRA adapters for editing and composition within these grids. At inference, a dedicated Grid Fill module completes partially observed layouts, producing temporally coherent and identity preserving outputs. Once trained, the entire system operates in a single forward pass, generalizing to previously unseen dynamic concepts without any test-time optimization. Extensive experiments demonstrate high-quality and consistent results across a wide range of subjects beyond trained concepts and editing scenarios.","short_abstract":"Recent advances in text-to-video generation have enabled high-quality synthesis from text and image prompts. While the personalization of dynamic concepts, which capture subject-specific appearance and motion from a single video, is now feasible, most existing methods require per-instance fine-tuning, limiting scalabil...","url_abs":"https://arxiv.org/abs/2507.17963","url_pdf":"https://arxiv.org/pdf/2507.17963v1","authors":"[\"Rameen Abdal\",\"Or Patashnik\",\"Ekaterina Deyneka\",\"Hao Chen\",\"Aliaksandr Siarohin\",\"Sergey Tulyakov\",\"Daniel Cohen-Or\",\"Kfir Aberman\"]","published":"2025-07-23T22:09:38Z","proceeding":"cs.GR","tasks":"[\"cs.GR\",\"cs.CV\",\"cs.LG\"]","methods":"[\"LoRA\",\"Generative Adversarial Network\"]","has_code":false}