acestep 5Hz lm 0.6B

par ACE-Step

Open source · 5k downloads · 12 likes

1.4

(12 avis)AudioAPI & Local

À propos

ACE-Step 5Hz LM 0.6B est un modèle de génération musicale open-source conçu pour produire des compositions de qualité professionnelle directement sur du matériel grand public. Il se distingue par sa rapidité exceptionnelle, capable de générer une chanson complète en quelques secondes sur des cartes graphiques standard, tout en restant accessible avec moins de 4 Go de VRAM. Le modèle excelle dans le contrôle stylistique précis et offre des fonctionnalités d'édition avancées comme la création de reprises ou la conversion voix-en-musique, le tout en respectant strictement les consignes fournies dans plus de 50 langues. Contrairement à beaucoup de solutions concurrentes, il est spécifiquement entraîné sur des données légalement sécurisées, incluant des musiques sous licence professionnelle, des œuvres libres de droits et des contenus synthétiques de haute qualité, garantissant une utilisation commerciale sans restriction. Son architecture innovante combine un modèle de langage comme planificateur omnipotent et un transformateur de diffusion pour la synthèse audio, le rendant particulièrement adapté aux artistes, producteurs et créateurs de contenu cherchant à intégrer l'IA dans leur workflow créatif.

Documentation

ACE-Step 1.5

Pushing the Boundaries of Open-Source Music Generation

Project | Hugging Face | ModelScope | Space Demo | Discord Tech Report

Model Details

🚀 ACE-Step v1.5 is a highly efficient open-source music foundation model designed to bring commercial-grade music generation to consumer hardware.

Key Features

💰 Commercial-Ready: Unlike many models trained on ambiguous datasets, ACE-Step v1.5 is designed for creators. You can strictly use the generated music for commercial purposes.
📚 Safe & Robust Training Data: The model is trained on a massive, legally compliant dataset consisting of:
- Licensed Data: Professionally licensed music tracks.
- Royalty-Free / No-Copyright Data: A vast collection of public domain and royalty-free music.
- Synthetic Data: High-quality audio generated via advanced MIDI-to-Audio conversion.
⚡ Extreme Speed: Generates a full song in under 2 seconds on an A100 and under 10 seconds on an RTX 3090.
🖥️ Consumer Hardware Friendly: Runs locally with less than 4GB of VRAM.

Technical Capabilities

🌉 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. 🎸

Developed by: [ACE-STEP]
Model type: [Text2Music]
Language(s): [50+ languages]
License: [MIT]

Evaluation

🏗️ Architecture

🦁 Model Zoo

DiT Models

DiT Model	Pre-Training	SFT	RL	CFG	Step	Refer audio	Text2Music	Cover	Repaint	Extract	Lego	Complete	Quality	Diversity	Fine-Tunability	Hugging Face
`acestep-v15-base`	✅	❌	❌	✅	50	✅	✅	✅	✅	✅	✅	✅	Medium	High	Easy	Link
`acestep-v15-sft`	✅	✅	❌	✅	50	✅	✅	✅	✅	❌	❌	❌	High	Medium	Easy	Link
`acestep-v15-turbo`	✅	✅	❌	❌	8	✅	✅	✅	✅	❌	❌	❌	Very High	Medium	Medium	Link
`acestep-v15-turbo-rl`	✅	✅	✅	❌	8	✅	✅	✅	✅	❌	❌	❌	Very High	Medium	Medium	To be released

LM Models

LM Model	Pretrain from	Pre-Training	SFT	RL	CoT metas	Query rewrite	Audio Understanding	Composition Capability	Copy Melody	Hugging Face
`acestep-5Hz-lm-0.6B`	Qwen3-0.6B	✅	✅	✅	✅	✅	Medium	Medium	Weak	✅
`acestep-5Hz-lm-1.7B`	Qwen3-1.7B	✅	✅	✅	✅	✅	Medium	Medium	Medium	✅
`acestep-5Hz-lm-4B`	Qwen3-4B	✅	✅	✅	✅	✅	Strong	Strong	Strong	✅

🙏 Acknowledgements

This project is co-led by ACE Studio and StepFun.

📖 Citation

If you find this project useful for your research, please consider citing:

BibTeX

@misc{gong2026acestep,
	title={ACE-Step 1.5: Pushing the Boundaries of Open-Source Music Generation},
	author={Junmin Gong, Yulin Song, Wenxiao Zhao, Sen Wang, Shengyuan Xu, Jing Guo}, 
	howpublished={\url{https://github.com/ace-step/ACE-Step-1.5}},
	year={2026},
	note={GitHub repository}
}

Liens & Ressources