LoVoRA

LoVoRA Dataset: Text-guided and Mask-free Video Object Removal and Addition Authors: Zhihan Xiao, Lin Liu, Yixin Gao, Xiaopeng Zhang, Haoxuan Che, Songping Mai, Qi Tian Links 🧩 Dataset 📘 Project Page 📄 Paper 💻 GitHub Dataset Overview The LoVoRA Dataset is a high-quality benchmark designed for text-guided, mask-free video object removal and addition. Built from high-fidelity image editing pairs and synthesized into coherent video sequences, it… See the full description on the dataset page:

Source: Hugging Face Hub (cz-5f/LoVoRA). Metadata imported from the dataset’s Hub tags.