# ACE-Step 1.5: Pushing the Boundaries of Open-Source Music Generation

arXiv: https://arxiv.org/abs/2602.00744 · HTML: https://mlsanity.com/paper/2602.00744/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2026.

## Built on by (most cited first, 26 of 26)

- [SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessment](https://mlsanity.com/paper/2604.25937/) (2026)
- [Stable Audio 3](https://mlsanity.com/paper/2605.17991/) (2026)
- [LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training](https://mlsanity.com/paper/2606.30642/) (2026)
- [TADA! Tuning Audio Diffusion Models through Activation Steering](https://mlsanity.com/paper/2602.11910/) (2026)
- [Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering](https://mlsanity.com/paper/2607.20253/) (2026)
- [SAME: A Semantically-Aligned Music Autoencoder](https://mlsanity.com/paper/2605.18613/) (2026)
- [What's a Credit Worth? A Market Framework for Attribution-Aware Compensation in Generative Music](https://mlsanity.com/paper/2607.00641/) (2026)
- [Anysynth:Zero-Shot Instrument Cloning via In-Context Learning and Asymmetric Hierarchical Guidance](https://mlsanity.com/paper/2607.11143/) (2026)
- [StepAudio 3 Music Technical Report](https://mlsanity.com/paper/2609.16034/) (2026)
- [S2Accompanist: A Semantic-Aware and Structure-Guided Diffusion Model for Music Accompaniment Generation](https://mlsanity.com/paper/2605.17414/) (2026)
- [HAIM: Human-AI Music Datasets for AI Music Production Tracking Benchmark](https://mlsanity.com/paper/2606.01686/) (2026)
- [SketchSong: Hierarchical Song Generation with Sketch Planning and Fine-Grained Multi-Track Modeling](https://mlsanity.com/paper/2606.03169/) (2026)
- [Making the Most of Limited Data: Score-Aware Training for Text-to-Music Generation](https://mlsanity.com/paper/2606.07387/) (2026)
- [Beyond Artifacts: Towards Generalizable Synthetic Song Detection via Music-Intrinsic Features](https://mlsanity.com/paper/2606.16612/) (2026)
- [Real-Time Interactive Music Generation via Data-Free Streaming Consistency Distillation](https://mlsanity.com/paper/2606.24307/) (2026)
- [A Quantized Native Runtime for On-Device Semantic Audio Generation](https://mlsanity.com/paper/2607.08526/) (2026)
- [WanSong v1.0 Technical Report](https://mlsanity.com/paper/2607.14749/) (2026)
- [TORUS: A Test of Rendering-Understanding Self-Coherence for Unified Audio Models](https://mlsanity.com/paper/2607.28896/) (2026)
- [MusicLayout: Explicit Structural Planning for Controllable Text-to-Music Generation](https://mlsanity.com/paper/2608.09035/) (2026)
- [DiffSynth-Music: Audio-Conditioned KV-Cache Adapters for Controllable Music Generation](https://mlsanity.com/paper/2609.12774/) (2026)
- [Open-Qwen-Music: An Auditable Framework for LLM-Based Music Composition and Diffusion Rendering](https://mlsanity.com/paper/2609.31652/) (2026)
- [YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality](https://mlsanity.com/paper/2609.33757/) (2026)
- [Ghost in the Encoder: Decodable Artist Identity Representations in Lyrics-to-Song Generation](https://mlsanity.com/paper/2609.39552/) (2026)
- [Tracing Inputs, Verifying Outputs: Validating Attribution in Music Generation](https://mlsanity.com/paper/2610.09637/) (2026)
- [MIRA: A Musical Intent Refinement Agent for Aligning Text-to-Music Generation with User Intent](https://mlsanity.com/paper/2610.10355/) (2026)
- [Harmonic Representations in Symbolic Music Transformers are Localized and Controllable](https://mlsanity.com/paper/2610.15957/) (2026)

## Abstract (arXiv)

We present ACE-Step v1.5, a highly efficient open-source music foundation model that brings commercial-grade generation to consumer hardware. On commonly used evaluation metrics, ACE-Step v1.5 achieves quality beyond most commercial music models while remaining extremely fast -- under 2 seconds per full song on an A100 and under 10 seconds on an RTX 3090. The model runs locally with less than 4GB of VRAM, and supports lightweight personalization: users can train a LoRA from just a few songs to capture their own style. At its core lies a novel hybrid architecture where the Language Model (LM) functions as an omni-capable planner: it transforms simple user queries into comprehensive song blueprints -- scaling from short loops to 10-minute compositions -- while synthesizing metadata, lyrics, and captions via Chain-of-Thought to guide the Diffusion Transformer (DiT). Uniquely, this alignment is achieved through intrinsic reinforcement learning relying solely on the model's internal mechanisms, thereby eliminating the biases inherent in external reward models or human preferences. Beyond standard synthesis, ACE-Step v1.5 unifies precise stylistic control with versatile editing capabilities -- such as cover generation, repainting, and vocal-to-BGM conversion -- while maintaining strict adherence to prompts across 50+ languages. This paves the way for powerful tools that seamlessly integrate into the creative workflows of music artists, producers, and content creators. The code, the model weights and the demo are available at: https://ace-step.github.io/ace-step-v1.5.github.io/