FlowSonic: Stable Zero-Shot Music Editing via High-Order Trajectory Integration
2026-07-20 • Sound
SoundMachine Learning
AI summaryⓘ
The authors introduce FlowSonic, a tool that can edit real music recordings by changing things like style or instrument sounds without losing the original musical feel. Their method works by converting the music into a special code (latent space), carefully preserving its structure using a technique called cross-attention. They also develop a new mathematical solver to keep the editing process stable and reliable. Tests show FlowSonic does better than previous methods at maintaining the original music's harmony and quality while making the changes requested.
Diffusion TransformerRectified FlowZero-shot EditingLatent SpaceCross-attentionODE SolverNumerical IntegrationSemantic ModificationMusic Structure PreservationTimbre Transfer
Authors
Ali Boudaghi, Hadi Zare
Abstract
Zero-shot text-guided editing of real-world music recordings requires balancing semantic modification with faithful preservation of the original musical structure. Although recent diffusion transformers trained with rectified flow have achieved remarkable success in text-to-music generation, extending them to edit existing recordings remains challenging because editing requires accurate deterministic inversion, reliable structural preservation, and numerically stable integration throughout the inversion and generation processes. We present FlowSonic, a zero-shot music editing framework built upon a pretrained diffusion transformer trained with rectified flow. FlowSonic first deterministically inverts a real-world recording into the latent space and preserves its musical structure during editing by reusing cross-attention representations extracted during inversion. To improve the numerical reliability of inversion-based editing, we introduce a high-order ODE solver and systematically investigate how different numerical integration schemes influence trajectory stability, structural preservation, and semantic controllability. Comprehensive experiments on timbre-transfer and genre-modification tasks demonstrate that FlowSonic consistently outperforms existing music editing methods across semantic alignment, harmonic preservation, structural consistency, and perceptual audio quality. We further provide geometric and empirical analyses showing how the proposed numerical integration strategy improves latent trajectory stability and leads to more reliable music editing.