AI RESEARCH
AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation
arXiv CS.CV
•
ArXi:2512.01334v2 Announce Type: replace Text-guided image-to-video generation has made substantial progress, yet it still struggles to execute text-specified edits that require substantial changes to a reference image (\textit{e.g., object addition, removal, or modification}). Empirically, our analysis reveals that this stems from \textbf{visual dominance}, where the reference image causes severe attention dispersion, inhibiting the model's ability to incorporate new semantic information. To address this, we propose \textbf{AlignVid}, a.