AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation

Jun 1, 2025·
Wenjie Shu
Wenjie Shu
· 1 min read
Abstract
Training-free attention scaling method to improve semantic fidelity in text-to-video generation.
Type
Publication
Under review

Under review.

Video Generation Attention
Wenjie Shu
Authors
Wenjie Shu (he/him)
Research Asistant