omnitransfer-all-in-one-framework-for-spatio

【效率与协作】Videos convey richer information than images or text, capturing both spatial and temporal dynamics. However, most existing video customization methods rely on reference images or task-specific temporal priors, failing to fully exploit the rich spatio-temporal information inherent in videos, thereby limiting flexibility and generalization in video gen…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准