# DiffRhythm+: Controllable and Flexible Full-Length Song Generation with Preference Optimization

arXiv: https://arxiv.org/abs/2507.12890 · HTML: https://mlsanity.com/paper/2507.12890/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2025.

## Built on by (most cited first, 12 of 12)

- [JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation](https://mlsanity.com/paper/2602.19163/) (2026)
- [DiffRhythm 2: Efficient and High Fidelity Song Generation via Block Flow Matching](https://mlsanity.com/paper/2510.22950/) (2025)
- [JAM: A Tiny Flow-based Song Generator with Fine-grained Controllability and Aesthetic Alignment](https://mlsanity.com/paper/2507.20880/) (2025)
- [Muse: Towards Reproducible Long-Form Song Generation with Fine-Grained Style Control](https://mlsanity.com/paper/2601.03973/) (2026)
- [MM-Sonate: Multimodal Controllable Audio-Video Generation with Zero-Shot Voice Cloning](https://mlsanity.com/paper/2601.01568/) (2026)
- [LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training](https://mlsanity.com/paper/2606.30642/) (2026)
- [InstructAudio: Unified speech and music generation with natural language instruction](https://mlsanity.com/paper/2511.18487/) (2025)
- [UniSonate: A Unified Model for Speech, Music, and Sound Effect Generation with Text Instructions](https://mlsanity.com/paper/2604.22209/) (2026)
- [Aligning Generative Music AI with Human Preferences: Methods and Challenges](https://mlsanity.com/paper/2511.15038/) (2025)
- [S2Accompanist: A Semantic-Aware and Structure-Guided Diffusion Model for Music Accompaniment Generation](https://mlsanity.com/paper/2605.17414/) (2026)
- [SegTune: Structured and Fine-Grained Control for Song Generation](https://mlsanity.com/paper/2606.02638/) (2026)
- [Towards Unified Song Generation and Singing Voice Conversion with Accompaniment Co-Generation](https://mlsanity.com/paper/2606.07015/) (2026)

## Abstract (arXiv)

Songs, as a central form of musical art, exemplify the richness of human intelligence and creativity. While recent advances in generative modeling have enabled notable progress in long-form song generation, current systems for full-length song synthesis still face major challenges, including data imbalance, insufficient controllability, and inconsistent musical quality. DiffRhythm, a pioneering diffusion-based model, advanced the field by generating full-length songs with expressive vocals and accompaniment. However, its performance was constrained by an unbalanced model training dataset and limited controllability over musical style, resulting in noticeable quality disparities and restricted creative flexibility. To address these limitations, we propose DiffRhythm+, an enhanced diffusion-based framework for controllable and flexible full-length song generation. DiffRhythm+ leverages a substantially expanded and balanced training dataset to mitigate issues such as repetition and omission of lyrics, while also fostering the emergence of richer musical skills and expressiveness. The framework introduces a multi-modal style conditioning strategy, enabling users to precisely specify musical styles through both descriptive text and reference audio, thereby significantly enhancing creative control and diversity. We further introduce direct performance optimization aligned with user preferences, guiding the model toward consistently preferred outputs across evaluation metrics. Extensive experiments demonstrate that DiffRhythm+ achieves significant improvements in naturalness, arrangement complexity, and listener satisfaction over previous systems.