VIBE: Video Instruction-aligned Background music gEneration
VIBE is introduced, a novel text-and-video-to-music (T+V2M) generation model that leverages a depth-wise cross-layer conditioning mechanism that dynamically bridges the planning and diffusion refinement heads and a comprehensive reward modeling taxonomy, optimizing for both hard, verifiable constraints and soft, subjective qualities with a structured 5-stage training curriculum.
Aryan Vijay Bhosale, Vaibhavi Lokegaonkar, Vishnu Raj et al.
· 0 citations