FoleyGenEx: Unified Video-to-Audio Generation with Multi-Modal Control, Temporal Alignment, and Semantic Precision
FoleyGenEx creates a single framework to generate synchronized audio from video using text, audio, or visual inputs. It unifies Text-to-Audio, Audio-Controlled VTA, and Foley Extension by separating semantic and synchronization processing. This allows for precise control over the output while ensuring temporal alignment between different modalities.