{"id":46147178,"url":"https://github.com/ace-step/awesome-ace-step","last_synced_at":"2026-03-02T07:35:31.916Z","repository":{"id":340955352,"uuid":"1168337151","full_name":"ace-step/awesome-ace-step","owner":"ace-step","description":null,"archived":false,"fork":false,"pushed_at":"2026-02-27T12:18:02.000Z","size":30,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-02-27T14:55:43.585Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"cc0-1.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ace-step.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-02-27T09:17:31.000Z","updated_at":"2026-02-27T13:49:15.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/ace-step/awesome-ace-step","commit_stats":null,"previous_names":["ace-step/awesome-ace-step"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/ace-step/awesome-ace-step","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ace-step%2Fawesome-ace-step","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ace-step%2Fawesome-ace-step/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ace-step%2Fawesome-ace-step/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ace-step%2Fawesome-ace-step/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ace-step","download_url":"https://codeload.github.com/ace-step/awesome-ace-step/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ace-step%2Fawesome-ace-step/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29995108,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-02T01:47:34.672Z","status":"online","status_checked_at":"2026-03-02T02:00:07.342Z","response_time":60,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-03-02T07:35:28.657Z","updated_at":"2026-03-02T07:35:31.909Z","avatar_url":"https://github.com/ace-step.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Awesome ACE-Step [![Awesome](https://awesome.re/badge.svg)](https://awesome.re)\n\n\u003e A curated list of projects, tools, models, UIs, and resources for [ACE-Step](https://github.com/ace-step/ACE-Step) — the open-source music generation foundation model by ACE Studio and StepFun.\n\nACE-Step is a hybrid architecture combining a Language Model planner with a Diffusion Transformer to generate commercial-grade music from text prompts and lyrics. It runs locally on consumer hardware with as little as 4 GB VRAM, generating a full song in under 2 seconds on A100 or under 10 seconds on RTX 3090.\n\n---\n\n## Contents\n\n- [Official Resources](#official-resources)\n- [Models](#models)\n- [UIs and Studios](#uis-and-studios)\n- [ComfyUI](#comfyui)\n- [Training and Fine-tuning](#training-and-fine-tuning)\n- [Data Annotation](#data-annotation)\n- [Integrations and Extensions](#integrations-and-extensions)\n- [Open-Source Music Generation Landscape](#open-source-music-generation-landscape)\n- [Tutorials and Guides](#tutorials-and-guides)\n- [Papers](#papers)\n\n---\n\n## Official Resources\n\n| Resource | Description |\n|----------|-------------|\n| [GitHub Repository (v1.5)](https://github.com/ace-step/ACE-Step-1.5) | Latest codebase with Gradio UI, REST API, CLI, LoRA training. Mac, AMD, Intel, CUDA. |\n| [GitHub Repository (v1.0)](https://github.com/ace-step/ACE-Step) | Original v1.0 codebase. |\n| [Project Page (v1.0)](https://ace-step.github.io/) | Architecture overview, demos, and benchmarks. |\n| [Project Page (v1.5)](https://ace-step.github.io/ace-step-v1.5.github.io/) | Hybrid LM + DiT architecture, new capabilities. |\n| [HuggingFace Space](https://huggingface.co/spaces/ACE-Step/ACE-Step) | Interactive online demo on HuggingFace Zero GPU. |\n| [HuggingFace Models](https://huggingface.co/ACE-Step) | All official model weights, LoRAs, and spaces. |\n| [Discord](https://discord.gg/PeWDxrkdj7) | Community chat and support. |\n\n## Models\n\n### DiT Models (Diffusion Transformer)\n\n| Model | Steps | Quality | Speed | Features | Link |\n|-------|:-----:|---------|-------|----------|------|\n| **acestep-v15-turbo** | 8 | Very High | Very Fast | text2music, cover, repaint | [HF](https://huggingface.co/ACE-Step/acestep-v15-turbo) |\n| acestep-v15-turbo-continuous | 8 | Very High | Very Fast | Optimized for streaming | [HF](https://huggingface.co/ACE-Step/acestep-v15-turbo-continuous) |\n| acestep-v15-sft | 50 | High | Medium | All features | [HF](https://huggingface.co/ACE-Step/acestep-v15-sft) |\n| acestep-v15-base | 50 | Medium | Medium | All features, best for fine-tuning | [HF](https://huggingface.co/ACE-Step/acestep-v15-base) |\n\n### Language Models (Planner)\n\n| Model | Base | VRAM | Capability | Link |\n|-------|------|------|------------|------|\n| acestep-5Hz-lm-0.6B | Qwen3-0.6B | 6-8 GB | Lightweight | [HF](https://huggingface.co/ACE-Step) |\n| **acestep-5Hz-lm-1.7B** | Qwen3-1.7B | 8-16 GB | Default, full features | [HF](https://huggingface.co/ACE-Step) |\n| acestep-5Hz-lm-4B | Qwen3-4B | 16+ GB | Best quality, audio understanding | [HF](https://huggingface.co/ACE-Step) |\n\n### LoRA Adapters and Quantized Models\n\n| Model | Type | Description | Link |\n|-------|------|-------------|------|\n| ACE-Step-v1.5-chinese-new-year-LoRA | LoRA | Chinese folk instruments (dizi, erhu), festive style. Trained on 12 songs | [HF](https://huggingface.co/ACE-Step/ACE-Step-v1.5-chinese-new-year-LoRA) |\n| Serveurperso/ACE-Step-1.5-GGUF | GGUF | Full quantization suite (Q4-Q8, BF16) for acestep.cpp | [HF](https://huggingface.co/Serveurperso/ACE-Step-1.5-GGUF) |\n\n## UIs and Studios\n\n| Project | Tech Stack | Highlights | Link |\n|---------|-----------|------------|------|\n| **ace-step-ui** (fspecii) | Node.js + Python | Spotify-inspired, dark/light modes, audio editor, stem extraction, video gen | [GitHub](https://github.com/fspecii/ace-step-ui) |\n| **ace-step-studio** (roblaughter) | React + FastAPI | Suno-style studio, create/library/player workflow, OpenAI-compatible LLM for lyrics, cover art gen | [GitHub](https://github.com/roblaughter/ace-step-studio) |\n| **Tadpole Studio** | Next.js + FastAPI | AI DJ, Radio, Library, Playlists, LoRA training, HeartMuLa backend, 11 themes | [GitHub](https://github.com/proximasan/tadpole-studio) |\n| **Ace-Step-Wrangler** | Python + HTML/JS | DAW-inspired dark UI for musicians. Friendly sliders (Creativity, Strictly follow lyrics) instead of raw model params | [GitHub](https://github.com/tsondo/Ace-Step-Wrangler) |\n| ace-step-ui.pinokio | Pinokio | One-click launcher for ace-step-ui (v1.5), auto backend + frontend | [GitHub](https://github.com/cocktailpeanut/ace-step-ui.pinokio) |\n| **ACE-Step-1.5-for-windows** (sdbds) | Python + Windows | 936 Suno style tags with search/select; song parameter history; 4-language UI (EN/ZH/JA/KO); LoRA/LoKR training with GPU memory optimization | [GitHub](https://github.com/sdbds/ACE-Step-1.5-for-windows/tree/qinglong) |\n\n## ComfyUI\n\n| Project | Description | Link |\n|---------|-------------|------|\n| **ComfyUI Native Support** | ACE-Step 1.5 built into ComfyUI core. AIO and split model workflows | [Docs](https://docs.comfy.org/tutorials/audio/ace-step/ace-step-v1-5) |\n| **ComfyUI-AceMusic** | 15-node full-featured integration: generation, cover, repaint, extend, edit, LoRA, HeartMuLa compatible | [GitHub](https://github.com/hiroki-abe-58/ComfyUI-AceMusic) |\n| **ComfyUI_RH_ACE-Step** | ComfyUI plugin for ACE-Step 1.5 generation | [GitHub](https://github.com/HM-RunningHub/ComfyUI_RH_ACE-Step) |\n| **scromfyUI-AceStep** | 30+ specialized nodes: audio KSamplers with shift control, multi-API lyrics gen (Gemini/Groq/OpenAI/Claude), masking \u0026 inpainting | [GitHub](https://github.com/scruffynerf/scromfyUI-AceStep) |\n| **ComfyUI-FL-AceStep-Training** | LoRA training pipeline in ComfyUI: auto-label, tiled VAE, real-time loss charts | [GitHub](https://github.com/filliptm/ComfyUI-FL-AceStep-Training) |\n| Comfyui_SN_AceStepTrainer | LoRA training nodes for ACE-Step 1.5 inside ComfyUI | [GitHub](https://github.com/Starnodes2024/Comfyui_SN_AceStepTrainer) |\n\n## Training and Fine-tuning\n\n| Project | Description | Link |\n|---------|-------------|------|\n| **Side-Step** | Standalone LoRA/LoKR toolkit for v1.5. Auto-detects variant, 8 GB VRAM training, interactive wizard + CLI | [GitHub](https://github.com/koda-dernet/Side-Step) |\n| **ACE-Step-1.5-for-windows** (sdbds) | LoRA and LoKR training with GPU memory offloading optimizations; integrated Gradio UI with style management and 4-language support | [GitHub](https://github.com/sdbds/ACE-Step-1.5-for-windows/tree/qinglong) |\n| **ComfyUI-FL-AceStep-Training** | End-to-end LoRA training inside ComfyUI with auto-labeling and live monitoring | [GitHub](https://github.com/filliptm/ComfyUI-FL-AceStep-Training) |\n| Ace-Step-1.5-Dataset-Manager | Desktop tool (Qt/C++) for editing LoRA training datasets: per-track caption, lyrics, BPM, key, audio preview | [GitHub](https://github.com/Neyroslav/Ace-Step-1.5-Dataset-Manager) |\n\n## Data Annotation\n\n| Project | Description | Link |\n|---------|-------------|------|\n| **acestep-captioner** | 11B music captioning model (Qwen2.5 Omni). 1000+ instruments, timbre, structure analysis. Accuracy surpasses Gemini Pro 2.5 | [HF](https://huggingface.co/ACE-Step/acestep-captioner) |\n| **acestep-transcriber** | Qwen2.5 Omni-based music transcription. Structure annotation, lyrics transcription, 50+ languages | [HF](https://huggingface.co/ACE-Step/acestep-transcriber) |\n\n## Integrations and Extensions\n\n| Project | Description | Link |\n|---------|-------------|------|\n| **acestep.cpp** | Portable C++17 / GGML implementation of ACE-Step 1.5. CPU, CUDA, Metal, Vulkan. Stereo 48 kHz WAV output | [GitHub](https://github.com/ServeurpersoCom/acestep.cpp) |\n| **ace-step-1.5 Docker** | Docker image with models pre-baked (~15 GB). REST API server, RunPod template, CLI generation tool | [GitHub](https://github.com/ValyrianTech/ace-step-1.5) |\n| **Generative Radio** | Fully local AI radio station. Qwen3 generates prompts, ACE-Step 1.5 generates songs. Multi-listener, Apple Silicon optimized | [GitHub](https://github.com/scramblerlab/generative-radio) |\n\n## Open-Source Music Generation Landscape\n\nA comparison of notable open-source music generation projects alongside ACE-Step.\n\n| Project | Architecture | Capability | License | Link |\n|---------|-------------|------------|---------|------|\n| **ACE-Step** | LM + DiT | Text/lyrics → full song (vocal + BGM), cover, repaint, LoRA. \u003c4 GB VRAM | Apache-2.0 | [GitHub](https://github.com/ace-step/ACE-Step) |\n| **YuE** | LLaMA2 autoregressive | Lyrics → full song, multi-genre, multi-lingual, voice cloning, style transfer | Apache-2.0 | [GitHub](https://github.com/multimodal-art-projection/YuE) |\n| **AudioCraft / MusicGen** | Autoregressive transformer | Text → music/audio, melody conditioning, style conditioning (JASCO) | MIT | [GitHub](https://github.com/facebookresearch/audiocraft) |\n| **Amphion** | Multiple (SVC, TTS, TTA) | Singing voice conversion, text-to-audio, vocoders, research toolkit | MIT | [GitHub](https://github.com/open-mmlab/Amphion) |\n| **Riffusion** | Stable Diffusion (spectrograms) | Real-time text → music via spectrogram diffusion | MIT | [GitHub](https://github.com/riffusion/riffusion) |\n| **Stable Audio Tools** | DiT + flow matching | Text → variable-length stereo audio (up to 47 s) | MIT | [GitHub](https://github.com/Stability-AI/stable-audio-tools) |\n| **DiffRhythm** | Latent diffusion (DiT + VAE) | Lyrics → full-length song (up to 4 min 45 s) in ~10 s | Apache-2.0 | [GitHub](https://github.com/ASLP-lab/DiffRhythm) |\n| **HeartMuLa** | LLM-based codec | Song gen, lyric recognition, audio codec, audio-text alignment | Apache-2.0 | [GitHub](https://github.com/HeartMuLa/heartlib) |\n\n## Tutorials and Guides\n\n| Title | Topic | Link |\n|-------|-------|------|\n| ACE-Step Prompt Guide | Detailed prompting tips: tags, lyrics structure, genre control | [Ambience AI](https://www.ambienceai.com/tutorials/ace-step-music-prompting-guide) |\n| Generate AI Music with ACE-Step 1.5 | Installation, generation, LoRA customization | [DigitalOcean](https://www.digitalocean.com/community/tutorials/ace-step-music-ai) |\n| ComfyUI ACE-Step 1.5 Guide | Official ComfyUI v1.5 workflow tutorial | [Comfy.org](https://docs.comfy.org/tutorials/audio/ace-step/ace-step-v1-5) |\n| AMD ACE-Step 1.5 Local Guide | Running ACE-Step on AMD GPUs | [PromptGalaxy](https://promptgalaxyai.com/blog/amd-ace-step-local-music-ai) |\n| Running ACE-Step 1.5 on M2 Mac | Apple Silicon setup, MPS memory workarounds | [BioErrorLog](https://en.bioerrorlog.work/entry/ace-step-15-local-m2-macbook) |\n| Install ACE-Step 1.5 with UV | Git + UV package manager setup | [PandaiTech](https://pandaitech.my/alpha/how-to-install-ace-step-15-using-git-and-the-uv-pa-ef9fe2df) |\n| ACE-Step 1.5 DeepWiki | Architecture deep-dive, code walkthrough, Gradio UI internals | [DeepWiki](https://deepwiki.com/ace-step/ACE-Step-1.5) |\n| ACE Studio | Professional AI music production suite | [acestudio.ai](https://docs.acestudio.ai/) |\n\n## Papers\n\n| Paper | Version | Key Contribution | Link |\n|-------|---------|-----------------|------|\n| ACE-Step: A Step Towards Music Generation Foundation Model | v1.0 | DCAE + linear transformer, REPA training | [arXiv](https://arxiv.org/abs/2506.00045) |\n| ACE-Step 1.5: Pushing the Boundaries of Open-Source Music Generation | v1.5 | Hybrid LM + DiT, intrinsic RL, comprehensive evaluation | [arXiv](https://arxiv.org/abs/2602.00744) |\n\n---\n\n## Contributing\n\nContributions welcome! Please read the [contributing guidelines](CONTRIBUTING.md) first.\n\n## License\n\n[![CC0](https://licensebuttons.net/p/zero/1.0/88x31.png)](https://creativecommons.org/publicdomain/zero/1.0/)\n\nTo the extent possible under law, the authors have waived all copyright and related or neighboring rights to this work.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Face-step%2Fawesome-ace-step","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Face-step%2Fawesome-ace-step","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Face-step%2Fawesome-ace-step/lists"}