Add ACE-Step music generator with simplified UI and LFS images

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,202 @@
+*.pt
+*.ckpt
+*.onnx
+t5_g2p_model/
+embeddings/
+checkpoints/
+
+val_images/
+val_audios/
+lightning_logs/
+lightning_logs_/
+train_images/
+train_audios/
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.idea/
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+*.txt
+!requirements.txt
+*.log
+*.flac
+minio_config.yaml
+.history/*
+__pycache__/*
+train.log
+*.mp3
+*.tar.gz
+__pycache__/
+demo_examples/
+nohup.out
+test_results/*
+nohup.out
+text_audio_align/*
+remote/*
+MG2P/*
+audio_getter.py
+refiner_loss_debug/
+outputs/*
+!outputs/
+save_checkpoint.ipynb
+repos/*
+app_demo.py
+ui/components_demo.py
+data_sampler_demo.py
+pipeline_ace_step_demo.py

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [2025] Timedomain Inc. and stepfun
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -1,14 +1,245 @@
 ---
-title: ACE Music Generator
-emoji: 💻
-colorFrom: green
-colorTo: purple
+title: ACE Step
+emoji: 😻
+colorFrom: blue
+colorTo: pink
 sdk: gradio
-sdk_version: 5.44.1
+sdk_version: 5.27.0
 app_file: app.py
 pinned: false
 license: apache-2.0
-short_description: Generate full-length songs easy! With ACE
+short_description: A Step Towards Music Generation Foundation Model
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+<h1 align="center">✨ ACE-Step ✨</h1>
+<h1 align="center">🎵 A Step Towards Music Generation Foundation Model 🎵</h1>
+<p align="center">
+    <a href="https://ace-step.github.io/">Project</a> |
+    <a href="https://github.com/ace-step/ACE-Step">Code</a> |
+    <a href="https://huggingface.co/ACE-Step/ACE-Step-v1-3.5B">Checkpoints</a> |
+    <a href="https://huggingface.co/spaces/ACE-Step/ACE-Step">Space Demo</a>
+</p>
+
+---
+<p align="center">
+    <img src="./fig/orgnization_logos.png" width="100%" alt="Org Logo">
+</p>
+
+## Table of Contents
+
+- [Features](#-features)
+- [Installation](#-installation)
+- [Usage](#-user-interface-guide)
+
+## 📢 News and Updates
+
+- 🚀 2025.05.06: Open source demo code and model
+
+## TODOs📋
+- [ ] 🔁 Release training code
+- [ ] 🔄 Release LoRA training code & 🎤 RapMachine lora
+- [ ] 🎮 Release ControlNet training code & 🎤 Singing2Accompaniment controlnet
+
+## 🏗️ Architecture
+
+<p align="center">
+    <img src="./fig/ACE-Step_framework.png" width="100%" alt="ACE-Step Framework">
+</p>
+
+
+## 📝 Abstract
+
+We introduce ACE-Step, a novel open-source foundation model for music generation that overcomes key limitations of existing approaches and achieves state-of-the-art performance through a holistic architectural design. Current methods face inherent trade-offs between generation speed, musical coherence, and controllability. For instance, LLM-based models (e.g., Yue, SongGen) excel at lyric alignment but suffer from slow inference and structural artifacts. Diffusion models (e.g., DiffRhythm), on the other hand, enable faster synthesis but often lack long-range structural coherence.
+
+ACE-Step bridges this gap by integrating diffusion-based generation with Sana’s Deep Compression AutoEncoder (DCAE) and a lightweight linear transformer. It further leverages MERT and m-hubert to align semantic representations (REPA) during training, enabling rapid convergence. As a result, our model synthesizes up to 4 minutes of music in just 20 seconds on an A100 GPU—15× faster than LLM-based baselines—while achieving superior musical coherence and lyric alignment across melody, harmony, and rhythm metrics. Moreover, ACE-Step preserves fine-grained acoustic details, enabling advanced control mechanisms such as voice cloning, lyric editing, remixing, and track generation (e.g., lyric2vocal, singing2accompaniment).
+
+Rather than building yet another end-to-end text-to-music pipeline, our vision is to establish a foundation model for music AI: a fast, general-purpose, efficient yet flexible architecture that makes it easy to train sub-tasks on top of it. This paves the way for developing powerful tools that seamlessly integrate into the creative workflows of music artists, producers, and content creators. In short, we aim to build the Stable Diffusion moment for music.
+
+## ✨ Features
+
+<p align="center">
+    <img src="./fig/application_map.png" width="100%" alt="ACE-Step Framework">
+</p>
+
+### 🎯 Baseline Quality
+
+#### 🌈 Diverse Styles & Genres
+- 🎸 Supports all mainstream music styles with various description formats including short tags, descriptive text, or use-case scenarios
+- 🎷 Capable of generating music across different genres with appropriate instrumentation and style
+
+#### 🌍 Multiple Languages
+- 🗣️ Supports 19 languages with top 10 well-performing languages including:
+  - 🇺🇸 English, 🇨🇳 Chinese, 🇷🇺 Russian, 🇪🇸 Spanish, 🇯🇵 Japanese, 🇩🇪 German, 🇫🇷 French, 🇵🇹 Portuguese, 🇮🇹 Italian, 🇰🇷 Korean
+- ⚠️ Due to data imbalance, less common languages may underperform
+
+#### 🎻 Instrumental Styles
+- 🎹 Supports various instrumental music generation across different genres and styles
+- 🎺 Capable of producing realistic instrumental tracks with appropriate timbre and expression for each instrument
+- 🎼 Can generate complex arrangements with multiple instruments while maintaining musical coherence
+
+#### 🎤 Vocal Techniques
+- 🎙️ Capable of rendering various vocal styles and techniques with good quality
+- 🗣️ Supports different vocal expressions including various singing techniques and styles
+
+### 🎛️ Controllability
+
+#### 🔄 Variations Generation
+- ⚙️ Implemented using training-free, inference-time optimization techniques
+- 🌊 Flow-matching model generates initial noise, then uses trigFlow's noise formula to add additional Gaussian noise
+- 🎚️ Adjustable mixing ratio between original initial noise and new Gaussian noise to control variation degree
+
+#### 🎨 Repainting
+- 🖌️ Implemented by adding noise to the target audio input and applying mask constraints during the ODE process
+- 🔍 When input conditions change from the original generation, only specific aspects can be modified while preserving the rest
+- 🔀 Can be combined with Variations Generation techniques to create localized variations in style, lyrics, or vocals
+
+#### ✏️ Lyric Editing
+- 💡 Innovatively applies flow-edit technology to enable localized lyric modifications while preserving melody, vocals, and accompaniment
+- 🔄 Works with both generated content and uploaded audio, greatly enhancing creative possibilities
+- ℹ️ Current limitation: can only modify small segments of lyrics at once to avoid distortion, but multiple edits can be applied sequentially
+
+### 🚀 Applications
+
+#### 🎤 Lyric2Vocal (LoRA)
+- 🔊 Based on a LoRA fine-tuned on pure vocal data, allowing direct generation of vocal samples from lyrics
+- 🛠️ Offers numerous practical applications such as vocal demos, guide tracks, songwriting assistance, and vocal arrangement experimentation
+- ⏱️ Provides a quick way to test how lyrics might sound when sung, helping songwriters iterate faster
+
+#### 📝 Text2Samples (LoRA)
+- 🎛️ Similar to Lyric2Vocal, but fine-tuned on pure instrumental and sample data
+- 🎵 Capable of generating conceptual music production samples from text descriptions
+- 🧰 Useful for quickly creating instrument loops, sound effects, and musical elements for production
+
+### 🔮 Coming Soon
+
+#### 🎤 RapMachine
+- 🔥 Fine-tuned on pure rap data to create an AI system specialized in rap generation
+- 🏆 Expected capabilities include AI rap battles and narrative expression through rap
+- 📚 Rap has exceptional storytelling and expressive capabilities, offering extraordinary application potential
+
+#### 🎛️ StemGen
+- 🎚️ A controlnet-lora trained on multi-track data to generate individual instrument stems
+- 🎯 Takes a reference track and specified instrument (or instrument reference audio) as input
+- 🎹 Outputs an instrument stem that complements the reference track, such as creating a piano accompaniment for a flute melody or adding jazz drums to a lead guitar
+
+#### 🎤 Singing2Accompaniment
+- 🔄 The reverse process of StemGen, generating a mixed master track from a single vocal track
+- 🎵 Takes a vocal track and specified style as input to produce a complete vocal accompaniment
+- 🎸 Creates full instrumental backing that complements the input vocals, making it easy to add professional-sounding accompaniment to any vocal recording
+
+## 💻 Installation
+
+```bash
+conda create -n ace_step python==3.10
+conda activate ace_step
+pip install -r requirements.txt
+conda install ffmpeg
+```
+
+## 🖥️ Hardware Performance
+
+We've tested ACE-Step on various hardware configurations with the following throughput results:
+
+| Device | 27 Steps | 60 Steps |
+|--------|-------------------------|-------------------------|
+| NVIDIA A100 | 0.036675| 0.0815 |
+| MacBook M2 Max | | 0.44 | 0.97 |
+| NVIDIA RTX 4090 | 0.029 | 0.064 |
+
+seconds cost per generated audio (seconds/audio)
+For example, to generate a 180-second song, multiply 180 by the seconds cost per generated audio (seconds/audio) for the desired device and step count. This will give you the total time required for the generation process.
+
+## 🚀 Usage
+
+![Demo Interface](fig/demo_interface.png)
+
+### 🔍 Basic Usage
+
+```bash
+python app.py
+```
+
+### ⚙️ Advanced Usage
+
+```bash
+python app.py --checkpoint_path /path/to/checkpoint --port 7865 --device_id 0 --share --bf16
+```
+
+#### 🛠️ Command Line Arguments
+
+- `--checkpoint_path`: Path to the model checkpoint (default: downloads automatically)
+- `--port`: Port to run the Gradio server on (default: 7865)
+- `--device_id`: GPU device ID to use (default: 0)
+- `--share`: Enable Gradio sharing link (default: False)
+- `--bf16`: Use bfloat16 precision for faster inference (default: True)
+
+## 📱 User Interface Guide
+
+The ACE-Step interface provides several tabs for different music generation and editing tasks:
+
+### 📝 Text2Music Tab
+
+1. **📋 Input Fields**:
+   - **🏷️ Tags**: Enter descriptive tags, genres, or scene descriptions separated by commas
+   - **📜 Lyrics**: Enter lyrics with structure tags like [verse], [chorus], and [bridge]
+   - **⏱️ Audio Duration**: Set the desired duration of the generated audio (-1 for random)
+
+2. **⚙️ Settings**:
+   - **🔧 Basic Settings**: Adjust inference steps, guidance scale, and seeds
+   - **🔬 Advanced Settings**: Fine-tune scheduler type, CFG type, ERG settings, and more
+
+3. **🚀 Generation**: Click "Generate" to create music based on your inputs
+
+### 🔄 Retake Tab
+
+- 🎲 Regenerate music with slight variations using different seeds
+- 🎚️ Adjust variance to control how much the retake differs from the original
+
+### 🎨 Repainting Tab
+
+- 🖌️ Selectively regenerate specific sections of the music
+- ⏱️ Specify start and end times for the section to repaint
+- 🔍 Choose the source audio (text2music output, last repaint, or upload)
+
+### ✏️ Edit Tab
+
+- 🔄 Modify existing music by changing tags or lyrics
+- 🎛️ Choose between "only_lyrics" mode (preserves melody) or "remix" mode (changes melody)
+- 🎚️ Adjust edit parameters to control how much of the original is preserved
+
+### 📏 Extend Tab
+
+- ➕ Add music to the beginning or end of an existing piece
+- 📐 Specify left and right extension lengths
+- 🔍 Choose the source audio to extend
+
+## Examples
+
+The `examples/input_params` directory contains sample input parameters that can be used as references for generating music.
+
+## 📜 License&Disclaimer
+
+This project is licensed under [Apache License 2.0](./LICENSE)
+
+ACE-Step enables original music generation across diverse genres, with applications in creative production, education, and entertainment. While designed to support positive and artistic use cases, we acknowledge potential risks such as unintentional copyright infringement due to stylistic similarity, inappropriate blending of cultural elements, and misuse for generating harmful content. To ensure responsible use, we encourage users to verify the originality of generated works, clearly disclose AI involvement, and obtain appropriate permissions when adapting protected styles or materials. By using ACE-Step, you agree to uphold these principles and respect artistic integrity, cultural diversity, and legal compliance. The authors are not responsible for any misuse of the model, including but not limited to copyright violations, cultural insensitivity, or the generation of harmful content.
+
+## 🙏 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{gong2025acestep,
+  title={ACE-Step: A Step Towards Music Generation Foundation Model},
+  author={Junmin Gong, Wenxiao Zhao, Sen Wang, Shengyuan Xu, Jing Guo}, 
+  howpublished={\url{https://github.com/ace-step/ACE-Step}},
+  year={2025},
+  note={GitHub repository}
+}
+```

apg_guidance.py

@@ -0,0 +1,95 @@
+import torch
+
+
+class MomentumBuffer:
+    def __init__(self, momentum: float = -0.75):
+        self.momentum = momentum
+        self.running_average = 0
+
+    def update(self, update_value: torch.Tensor):
+        new_average = self.momentum * self.running_average
+        self.running_average = update_value + new_average
+
+
+def project(
+    v0: torch.Tensor,  # [B, C, H, W]
+    v1: torch.Tensor,  # [B, C, H, W]
+    dims=[-1, -2],
+):
+    dtype = v0.dtype
+    device_type = v0.device.type
+    if device_type == "mps":
+        v0, v1 = v0.cpu(), v1.cpu()
+
+    v0, v1 = v0.double(), v1.double()
+    v1 = torch.nn.functional.normalize(v1, dim=dims)
+    v0_parallel = (v0 * v1).sum(dim=dims, keepdim=True) * v1
+    v0_orthogonal = v0 - v0_parallel
+    return v0_parallel.to(dtype).to(device_type), v0_orthogonal.to(dtype).to(device_type)
+
+
+def apg_forward(
+    pred_cond: torch.Tensor,  # [B, C, H, W]
+    pred_uncond: torch.Tensor,  # [B, C, H, W]
+    guidance_scale: float,
+    momentum_buffer: MomentumBuffer = None,
+    eta: float = 0.0,
+    norm_threshold: float = 2.5,
+    dims=[-1, -2],
+):
+    diff = pred_cond - pred_uncond
+    if momentum_buffer is not None:
+        momentum_buffer.update(diff)
+        diff = momentum_buffer.running_average
+
+    if norm_threshold > 0:
+        ones = torch.ones_like(diff)
+        diff_norm = diff.norm(p=2, dim=dims, keepdim=True)
+        scale_factor = torch.minimum(ones, norm_threshold / diff_norm)
+        diff = diff * scale_factor
+
+    diff_parallel, diff_orthogonal = project(diff, pred_cond, dims)
+    normalized_update = diff_orthogonal + eta * diff_parallel
+    pred_guided = pred_cond + (guidance_scale - 1) * normalized_update
+    return pred_guided
+
+
+def cfg_forward(cond_output, uncond_output, cfg_strength):
+    return uncond_output + cfg_strength * (cond_output - uncond_output)
+
+
+def cfg_double_condition_forward(
+    cond_output,
+    uncond_output,
+    only_text_cond_output,
+    guidance_scale_text,
+    guidance_scale_lyric,
+):
+    return (1 - guidance_scale_text) * uncond_output + (guidance_scale_text - guidance_scale_lyric) * only_text_cond_output + guidance_scale_lyric * cond_output 
+
+
+def optimized_scale(positive_flat, negative_flat):
+
+    # Calculate dot production
+    dot_product = torch.sum(positive_flat * negative_flat, dim=1, keepdim=True)
+
+    # Squared norm of uncondition
+    squared_norm = torch.sum(negative_flat ** 2, dim=1, keepdim=True) + 1e-8
+
+    # st_star = v_cond^T * v_uncond / ||v_uncond||^2
+    st_star = dot_product / squared_norm
+    
+    return st_star
+
+
+def cfg_zero_star(noise_pred_with_cond, noise_pred_uncond, guidance_scale, i, zero_steps=1, use_zero_init=True):
+    bsz = noise_pred_with_cond.shape[0]
+    positive_flat = noise_pred_with_cond.view(bsz, -1)
+    negative_flat = noise_pred_uncond.view(bsz, -1)
+    alpha = optimized_scale(positive_flat, negative_flat)
+    alpha = alpha.view(bsz, 1, 1, 1)
+    if (i <= zero_steps) and use_zero_init:
+        noise_pred = noise_pred_with_cond * 0.
+    else:
+        noise_pred = noise_pred_uncond * alpha + guidance_scale * (noise_pred_with_cond - noise_pred_uncond * alpha)
+    return noise_pred

app.py

@@ -0,0 +1,45 @@
+import argparse
+from ui.components import create_main_demo_ui
+from pipeline_ace_step import ACEStepPipeline
+from data_sampler import DataSampler
+import os
+
+
+parser = argparse.ArgumentParser()
+parser.add_argument("--checkpoint_path", type=str, default=None)
+parser.add_argument("--server_name", type=str, default="0.0.0.0")
+parser.add_argument("--port", type=int, default=7860)
+parser.add_argument("--device_id", type=int, default=0)
+parser.add_argument("--share", action='store_true', default=False)
+parser.add_argument("--bf16", action='store_true', default=True)
+parser.add_argument("--torch_compile", type=bool, default=False)
+
+args = parser.parse_args()
+os.environ["CUDA_VISIBLE_DEVICES"] = str(args.device_id)
+
+
+persistent_storage_path = "/data"
+
+
+def main(args):
+
+    model_demo = ACEStepPipeline(
+        checkpoint_dir=args.checkpoint_path,
+        dtype="bfloat16" if args.bf16 else "float32",
+        persistent_storage_path=persistent_storage_path,
+        torch_compile=args.torch_compile
+    )
+    data_sampler = DataSampler()
+
+    demo = create_main_demo_ui(
+        text2music_process_func=model_demo.__call__,
+        sample_data_func=data_sampler.sample,
+        load_data_func=data_sampler.load_json,
+    )
+    demo.queue(default_concurrency_limit=8).launch(
+        
+    )
+
+
+if __name__ == "__main__":
+    main(args)

config/zh_rap_lora_config.json

@@ -0,0 +1,15 @@
+{
+    "r": 256,
+    "lora_alpha": 32,
+    "target_modules": [
+        "speaker_embedder",
+        "linear_q",
+        "linear_k",
+        "linear_v",
+        "to_q",
+        "to_k",
+        "to_v",
+        "to_out.0"
+    ],
+    "use_rslora": true
+}

data_sampler.py

@@ -0,0 +1,30 @@
+import json
+from pathlib import Path
+import random
+
+
+DEFAULT_ROOT_DIR = "examples/default/input_params"
+ZH_RAP_LORA_ROOT_DIR = "examples/zh_rap_lora/input_params"
+
+class DataSampler:
+    def __init__(self, root_dir=DEFAULT_ROOT_DIR):
+        self.root_dir = root_dir
+        self.input_params_files = list(Path(self.root_dir).glob("*.json"))
+        self.zh_rap_lora_input_params_files = list(Path(ZH_RAP_LORA_ROOT_DIR).glob("*.json"))
+        self.zh_rap_lora_input_params_files += list(Path(ZH_RAP_LORA_ROOT_DIR).glob("*.json"))
+
+    def load_json(self, file_path):
+        with open(file_path, "r", encoding="utf-8") as f:
+            return json.load(f)
+
+    def sample(self, lora_name_or_path=None):
+        if lora_name_or_path is None or lora_name_or_path == "none":
+            json_path = random.choice(self.input_params_files)
+            json_data = self.load_json(json_path)
+        else:
+            json_path = random.choice(self.zh_rap_lora_input_params_files)
+            json_data = self.load_json(json_path)
+            # Update the lora_name in the json_data
+            json_data["lora_name_or_path"] = lora_name_or_path
+
+        return json_data

examples/default/input_params/output_20250426071706_0_input_params.json

@@ -0,0 +1,25 @@
+{
+    "prompt": "pop, rap, electronic, blues, hip-house, rhythm and blues",
+    "lyrics": "[verse]\n我走过深夜的街道\n冷风吹乱思念的漂亮外套\n你的微笑像星光很炫耀\n照亮了我孤独的每分每秒\n\n[chorus]\n愿你是风吹过我的脸\n带我飞过最远最遥远的山间\n愿你是风轻触我的梦\n停在心头不再飘散无迹无踪\n\n[verse]\n一起在喧哗避开世俗的骚动\n独自在天台探望月色的朦胧\n你说爱像音乐带点重节奏\n一拍一跳让我忘了心的温度多空洞\n\n[bridge]\n唱起对你的想念不隐藏\n像诗又像画写满藏不了的渴望\n你的影子挥不掉像风的倔强\n追着你飞扬穿越云海一样泛光\n\n[chorus]\n愿你是风吹过我的手\n暖暖的触碰像春日细雨温柔\n愿你是风盘绕我的身\n深情万万重不会有一天走远走\n\n[verse]\n深夜的钢琴弹起动人的旋律\n低音鼓砸进心底的每一次呼吸\n要是能将爱化作歌声传递\n你是否会听见我心里的真心实意",
+    "audio_duration": 170.63997916666668,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": true,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 3.191075086593628,
+        "diffusion": 17.459356784820557,
+        "latent2audio": 1.7095518112182617
+    },
+    "actual_seeds": [
+        3299954530
+    ]
+}

examples/default/input_params/output_20250426071812_0_input_params.json

@@ -0,0 +1,25 @@
+{
+    "prompt": "country rock, folk rock, southern rock, bluegrass, country pop",
+    "lyrics": "[verse]\nWoke up to the sunrise glow\nTook my heart and hit the road\nWheels hummin' the only tune I know\nStraight to where the wildflowers grow\n\n[verse]\nGot that old map all wrinkled and torn\nDestination unknown but I'm reborn\nWith a smile that the wind has worn\nChasin' dreams that can't be sworn\n\n[chorus]\nRidin' on a highway to sunshine\nGot my shades and my radio on fine\nLeave the shadows in the rearview rhyme\nHeart's racing as we chase the time\n\n[verse]\nMet a girl with a heart of gold\nTold stories that never get old\nHer laugh like a tale that's been told\nA melody so bold yet uncontrolled\n\n[bridge]\nClouds roll by like silent ghosts\nAs we drive along the coast\nWe toast to the days we love the most\nFreedom's song is what we post\n\n[chorus]\nRidin' on a highway to sunshine\nGot my shades and my radio on fine\nLeave the shadows in the rearview rhyme\nHeart's racing as we chase the time",
+    "audio_duration": 224.23997916666667,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": true,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 4.262240648269653,
+        "diffusion": 15.380569219589233,
+        "latent2audio": 2.3227272033691406
+    },
+    "actual_seeds": [
+        401640
+    ]
+}

examples/default/input_params/output_20250426072346_0_input_params.json

@@ -0,0 +1,25 @@
+{
+    "prompt": "hip-house, funk",
+    "lyrics": "[verse]\n哎呀跳起来，脚尖踩节拍 (oo-yeah!)\n灯光闪烁像星星盛开 (uh-huh!)\n人人都醒来，把烦恼踹开 (get it!)\n热血沸腾，汗水自己安排\n\n[chorus]\n嘿，你还等啥？快抓住节拍 (come on!)\n光芒指引，让心都不存在 (whoa!)\n点燃热火，我们一起飙high (let’s go!)\n跳入午夜的狂欢时代\n\n[bridge]\n咚咚鼓声啊，让你的灵魂起飞 (woo!)\n手心拍一拍，能量翻倍 (ah-hah!)\n键盘响起来，如宇宙的交汇 (oh yeah!)\n就是这感觉，兄弟姐妹都陶醉\n\n[verse]\n灵魂从不睡，只想继续燃烧 (woo!)\n节奏像热浪，席卷这街道 (ow!)\n大伙儿涌上楼台，满面微笑 (yeah!)\n这一刻属于我们，无可替代\n\n[chorus]\n嘿，你还等啥？快抓住节拍 (come on!)\n光芒指引，让心都不存在 (whoa!)\n点燃热火，我们一起飙high (let’s go!)\n跳入午夜的狂欢时代\n\n[verse]\n世界多精彩，握紧把它打开 (alright!)\n每一步都像星球在摇摆 (uh-huh!)\n无边无际的律动像大海 (oo-yeah!)\n跟着光芒之舞，一起澎湃",
+    "audio_duration": 204.19997916666668,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": true,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.05196118354797363,
+        "diffusion": 15.530808210372925,
+        "latent2audio": 2.5604095458984375
+    },
+    "actual_seeds": [
+        401640
+    ]
+}

examples/default/input_params/output_20250426072508_0_input_params.json

@@ -0,0 +1,25 @@
+{
+    "prompt": "funk, pop, soul, rock, melodic, guitar, drums, bass, keyboard, percussion, 105 BPM, energetic, upbeat, groovy, vibrant, dynamic",
+    "lyrics": "[verse]\nNeon lights they flicker bright\nCity hums in dead of night\nRhythms pulse through concrete veins\nLost in echoes of refrains\n\n[verse]\nBassline groovin' in my chest\nHeartbeats match the city's zest\nElectric whispers fill the air\nSynthesized dreams everywhere\n\n[chorus]\nTurn it up and let it flow\nFeel the fire let it grow\nIn this rhythm we belong\nHear the night sing out our song\n\n[verse]\nGuitar strings they start to weep\nWake the soul from silent sleep\nEvery note a story told\nIn this night we’re bold and gold\n\n[bridge]\nVoices blend in harmony\nLost in pure cacophony\nTimeless echoes timeless cries\nSoulful shouts beneath the skies\n\n[verse]\nKeyboard dances on the keys\nMelodies on evening breeze\nCatch the tune and hold it tight\nIn this moment we take flight",
+    "audio_duration": 178.87997916666666,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": true,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.02882218360900879,
+        "diffusion": 16.91233205795288,
+        "latent2audio": 1.7794082164764404
+    },
+    "actual_seeds": [
+        401640
+    ]
+}

examples/default/input_params/output_20250426073829_0_input_params.json

@@ -0,0 +1,25 @@
+{
+    "prompt": "electronic rap",
+    "lyrics": "[verse]\nWaves on the bass, pulsing in the speakers,\nTurn the dial up, we chasing six-figure features,\nGrinding on the beats, codes in the creases,\nDigital hustler, midnight in sneakers.\n\n[chorus]\nElectro vibes, hearts beat with the hum,\nUrban legends ride, we ain't ever numb,\nCircuits sparking live, tapping on the drum,\nLiving on the edge, never succumb.\n\n[verse]\nSynthesizers blaze, city lights a glow,\nRhythm in the haze, moving with the flow,\nSwagger on stage, energy to blow,\nFrom the blocks to the booth, you already know.\n\n[bridge]\nNight's electric, streets full of dreams,\nBass hits collective, bursting at seams,\nHustle perspective, all in the schemes,\nRise and reflective, ain't no in-betweens.\n\n[verse]\nVibin' with the crew, sync in the wire,\nGot the dance moves, fire in the attire,\nRhythm and blues, soul's our supplier,\nRun the digital zoo, higher and higher.\n\n[chorus]\nElectro vibes, hearts beat with the hum,\nUrban legends ride, we ain't ever numb,\nCircuits sparking live, tapping on the drum,\nLiving on the edge, never succumb.",
+    "audio_duration": 221.42547916666666,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": true,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.024875164031982422,
+        "diffusion": 20.566852569580078,
+        "latent2audio": 2.2281734943389893
+    },
+    "actual_seeds": [
+        401640
+    ]
+}

examples/default/input_params/output_20250426074037_0_input_params.json

@@ -0,0 +1,25 @@
+{
+    "prompt": "electronic, house, electro house, synthesizer, drums, bass, percussion, fast, energetic, uplifting, exciting",
+    "lyrics": "[verse]\n霓虹灯下我们追逐\n人群跃动像潮水满布\n热浪袭来吹散孤独\n跳进节奏不如停下脚步\n\n[pre-chorus]\n脚尖触电快点感受\n迎着风声释放自由\n心跳节拍配合节奏\n一切烦恼请靠边游\n\n[chorus]\n夏夜狂奔没有尽头\n星光闪烁舞池不朽\n尽情挥洒所有节奏\n无边热情把你包裹哦\n\n[verse]\n天空翻滚黑云入夜\n每颗星星像音乐律贴\n耳边回响那低音线\n环绕耳际如梦境般甜\n\n[pre-chorus]\n脚尖触电快点感受\n迎着风声释放自由\n心跳节拍配合节奏\n一切烦恼请靠边游\n\n[chorus]\n夏夜狂奔没有尽头\n星光闪烁舞池不朽\n尽情挥洒所有节奏\n无边热情把你包裹哦",
+    "audio_duration": 221.47997916666668,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": true,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.028400182723999023,
+        "diffusion": 13.195815324783325,
+        "latent2audio": 2.1679723262786865
+    },
+    "actual_seeds": [
+        3440445703
+    ]
+}

examples/default/input_params/output_20250426074214_0_input_params.json

@@ -0,0 +1,25 @@
+{
+    "prompt": "synth-pop, electronic, pop, synthesizer, drums, bass, piano, 128 BPM, energetic, uplifting, modern",
+    "lyrics": "[verse]\nWoke up in a city that's always alive\nNeon lights they shimmer they thrive\nElectric pulses beat they drive\nMy heart races just to survive\n\n[chorus]\nOh electric dreams they keep me high\nThrough the wires I soar and fly\nMidnight rhythms in the sky\nElectric dreams together we’ll defy\n\n[verse]\nLost in the labyrinth of screens\nVirtual love or so it seems\nIn the night the city gleams\nDigital faces haunted by memes\n\n[chorus]\nOh electric dreams they keep me high\nThrough the wires I soar and fly\nMidnight rhythms in the sky\nElectric dreams together we’ll defy\n\n[bridge]\nSilent whispers in my ear\nPixelated love serene and clear\nThrough the chaos find you near\nIn electric dreams no fear\n\n[verse]\nBound by circuits intertwined\nLove like ours is hard to find\nIn this world we’re truly blind\nBut electric dreams free the mind",
+    "audio_duration": 221.27997916666666,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": true,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.025463581085205078,
+        "diffusion": 15.243804454803467,
+        "latent2audio": 2.170398473739624
+    },
+    "actual_seeds": [
+        3400270027
+    ]
+}

examples/default/input_params/output_20250426074413_0_input_params.json

@@ -0,0 +1,25 @@
+{
+    "prompt": "Cuban music, salsa, son, Afro-Cuban, traditional Cuban",
+    "lyrics": "[verse]\nSun dips low the night ignites\nBassline hums with gleaming lights\nElectric guitar singing tales so fine\nIn the rhythm we all intertwine\n\n[verse]\nDrums beat steady calling out\nPercussion guides no room for doubt\nElectric pulse through every vein\nDance away every ounce of pain\n\n[chorus]\nFeel the rhythm feel the flow\nLet the music take control\nBassline deep electric hum\nIn this night we're never numb\n\n[bridge]\nStars above they start to glow\nEchoes of the night's soft glow\nElectric strings weave through the air\nIn this moment none compare\n\n[verse]\nHeartbeats sync with every tone\nLost in music never alone\nElectric tales of love and peace\nIn this groove we find release\n\n[chorus]\nFeel the rhythm feel the flow\nLet the music take control\nBassline deep electric hum\nIn this night we're never numb",
+    "audio_duration": 208.27997916666666,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": true,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.026132583618164062,
+        "diffusion": 15.139378070831299,
+        "latent2audio": 2.2071540355682373
+    },
+    "actual_seeds": [
+        3358899399
+    ]
+}

examples/default/input_params/output_20250426075107_0_input_params.json

@@ -0,0 +1,25 @@
+{
+    "prompt": "pop, piano, rap, dark, atmospheric",
+    "lyrics": "[verse]\n月光爬上窗 染白冷的床\n心跳的方向 带我入迷惘\n黑夜吞噬光 命运的纸张\n爱是血色霜 邪恶又芬芳\n\n[chorus]\n你是猎人的欲望 我是迷途的小羊\n深陷你眼眸的荒 唐突献出心脏\n我在夜里回荡 是谁给我希望\n黑暗风中飘荡 假装不再受伤\n\n[verse]\n心锁在门外 谁会解开关怀\n温柔的手拍 藏着冷酷杀害\n思绪如尘埃 撞击爱的霹雳\n灵魂的独白 为你沾满血迹\n\n[bridge]\n你是噩梦的歌唱 是灵魂的捆绑\n绝望中带着光 悬崖边的渴望\n心跳被你鼓掌 恶魔也痴痴想\n渐渐没了抵抗 古老诡计流淌\n\n[chorus]\n你是猎人的欲望 我是迷途的小羊\n深陷你眼眸的荒 唐突献出心脏\n我在夜里回荡 是谁给我希望\n黑暗风中飘荡 假装不再受伤\n\n[outro]\n爱如月黑无光 渗进梦的战场\n逃入无声的场 放手或心嚷嚷\n隐秘的极端 爱是极致风浪\n灵魂彻底交偿 你是终极虚妄",
+    "audio_duration": 146.91997916666668,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": true,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.03876018524169922,
+        "diffusion": 15.962624549865723,
+        "latent2audio": 1.4594337940216064
+    },
+    "actual_seeds": [
+        2065110378
+    ]
+}

examples/default/input_params/output_20250426075537_0_input_params.json

@@ -0,0 +1,25 @@
+{
+    "prompt": "surf music",
+    "lyrics": "[verse]\nSunshine on the boulevard the beach is calling loud\nWaves are dancing golden sand under a cotton cloud\nElectric heartbeat pounding fast the tide is on our side\nCatch a wave and feel alive we’ll take it for a ride\n\n[verse]\nPalm trees swaying left to right they know where we belong\nFeel the rhythm of the night it keeps us moving strong\nSea spray kisses salty air we’re flying with the breeze\nChampagne states of mind we ride we do just as we please\n\n[chorus]\nWe’re riding waves of life together hand in hand\nWith every beat we chase the beat it’s our own wonderland\nFeel the music take you higher as the shorelines blur\nThis is our world our endless summer as we live and learn\n\n[bridge]\nMoonlight paints the ocean blue reflections in our eyes\nStars align to light our path we’re surfing through the skies\nEvery moment like a song we sing it loud and clear\nEvery day’s a new adventure with you always near\n\n[verse]\nNeon lights and city sounds they blend with ocean views\nWe’re unstoppable tonight no way that we can lose\nDreams are written in the sand they sparkle in the sun\nTogether we’re a masterpiece our story’s just begun\n\n[chorus]\nWe’re riding waves of life together hand in hand\nWith every beat we chase the beat it’s our own wonderland\nFeel the music take you higher as the shorelines blur\nThis is our world our endless summer as we live and learn",
+    "audio_duration": 236.55997916666666,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": true,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.033666133880615234,
+        "diffusion": 16.291455507278442,
+        "latent2audio": 2.3726775646209717
+    },
+    "actual_seeds": [
+        508630535
+    ]
+}

examples/default/input_params/output_20250426075843_0_input_params.json

@@ -0,0 +1,25 @@
+{
+    "prompt": "alternative rock, pop, rock",
+    "lyrics": "[verse]\nBright lights flashing in the city sky\nRunning fast and we don't know why\nElectric nights got our hearts on fire\nChasing dreams we'll never tire\n\n[verse]\nGrit in our eyes wind in our hair\nBreaking rules we don't even care\nShouting loud above the crowd\nLiving life like we're unbowed\n\n[chorus]\nRunning wild in the night so free\nFeel the beat pumping endlessly\nHearts collide in the midnight air\nWe belong we don't have a care\n\n[verse]\nPiercing through like a lightning strike\nEvery moment feels like a hike\nDaring bold never backing down\nKings and queens without a crown\n\n[chorus]\nRunning wild in the night so free\nFeel the beat pumping endlessly\nHearts collide in the midnight air\nWe belong we don't have a care\n\n[bridge]\nClose your eyes let your spirit soar\nWe are the ones who wanted more\nBreaking chains of the mundane\nIn this world we'll make our claim",
+    "audio_duration": 202.19997916666668,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": true,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.02512216567993164,
+        "diffusion": 18.860822677612305,
+        "latent2audio": 2.0361969470977783
+    },
+    "actual_seeds": [
+        1255121549
+    ]
+}

examples/default/input_params/output_20250426080234_0_input_params.json

@@ -0,0 +1,25 @@
+{
+    "prompt": "rock, hip - hop, orchestral, bass, drums, electric guitar, piano, synthesizer, violin, viola, cello, fast, energetic, motivational, inspirational, empowering",
+    "lyrics": "### **[Intro – Spoken]**  \n*\"The streets whisper, their echoes never fade.  \nEvery step I take leaves a mark—this ain't just a game.\"*  \n\n### **[Hook/Chorus]**  \nBorn in the chaos, I weather the storm,  \nRising from ashes where warriors are born.  \nChains couldn't hold me, the system’s a maze,  \nI rewrite the rules, set the city ablaze!  \n\n### **[Verse 1]**  \nCold nights, empty pockets, dreams laced with fight,  \nEvery loss made me sharper, cut deep like a knife.  \nThey said I wouldn’t make it, now they watch in despair,  \nFrom the curb to the throne, took the pain, made it rare.  \nEvery siren’s a melody, every alley holds a tale,  \nRose from the shadows, left my name on the trail.  \nStreetlights flicker like warnings in the haze,  \nBut I move like a phantom, unfazed by the blaze.  \n\n### **[Hook/Chorus]**  \nBorn in the chaos, I weather the storm,  \nRising from ashes where warriors are born.  \nChains couldn't hold me, the system’s a maze,  \nI rewrite the rules, set the city ablaze!  \n\n### **[Verse 2]**  \nBarbed wire fences couldn't lock in my mind,  \nEvery cage they designed, I left broken behind.  \nThey want control, but I’m destined to roam,  \nWhere the lost find their voice, where the heart sets the tone.  \nSteel and concrete, where the lessons run deep,  \nEvery crack in the pavement tells a story of heat.  \nBut I rise, undefeated, like a king with no throne,  \nWriting scripts in the struggle, my legacy’s stone.  \n\n### **[Bridge]**  \nFeel the rhythm of the underground roar,  \nEvery wound tells a story of the battles before.  \nBlood, sweat, and echoes fill the cold midnight,  \nBut we move with the fire—unshaken, upright.  \n\n### **[Verse 3]**  \nNo regrets, no retreat, this game has no pause,  \nEvery step that I take is a win for the lost.  \nI took lessons from hustlers, wisdom from pain,  \nNow the echoes of struggle carve power in my name.  \nThey built walls, but I walk through the cracks,  \nTurned dirt into gold, never looked back.  \nThrough the struggle we rise, through the fire we claim,  \nThis is more than just music—it's life in the frame.  \n\n### **[Hook/Chorus – Reprise]**  \nBorn in the chaos, I weather the storm,  \nRising from ashes where warriors are born.  \nChains couldn't hold me, the system’s a maze,  \nI rewrite the rules, set the city ablaze!  \n\n### **[Outro – Spoken]**  \n*\"The scars, the struggle, the grind—it’s all part of the rhythm.  \nWe never break, we never fold. We rise.\"*",
+    "audio_duration": 153.95997916666667,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": true,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.04368758201599121,
+        "diffusion": 17.16369390487671,
+        "latent2audio": 1.5405471324920654
+    },
+    "actual_seeds": [
+        2659225017
+    ]
+}

examples/default/input_params/output_20250426080407_0_input_params.json

@@ -0,0 +1,25 @@
+{
+    "prompt": "tango finlandés, campanas, disco, dark pop, electro, guitarra clásica, corridos tumba",
+    "lyrics": "[inst]",
+    "audio_duration": 162.79997916666667,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": true,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.011058568954467773,
+        "diffusion": 9.924944400787354,
+        "latent2audio": 1.6034839153289795
+    },
+    "actual_seeds": [
+        780297686
+    ]
+}

examples/default/input_params/output_20250426080601_0_input_params.json

@@ -0,0 +1,25 @@
+{
+    "prompt": "Nightclubs, dance parties, workout playlists, radio broadcasts",
+    "lyrics": "Burning in motion, set me alight!\nEvery heartbeat turns into a fight!\nCaged in rhythm, chained in time!\nLove’s a battle— You're Mine!  You're Mine!",
+    "audio_duration": 221.83997916666667,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": true,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.012485980987548828,
+        "diffusion": 14.345409154891968,
+        "latent2audio": 2.174558639526367
+    },
+    "actual_seeds": [
+        1318394052
+    ]
+}

examples/default/input_params/output_20250426081134_0_input_params.json

@@ -0,0 +1,25 @@
+{
+    "prompt": "melancholic, world, sad, medieval, soulful",
+    "lyrics": "[Verse]\nIn a world so grand he roams the skies alone\nHis heart a heavy stone a tale untold\nWhispers of his past echo through the night\nA lonely dragon searching for the light\n\n[Verse 2]\nOnce a mighty force now he drifts in pain\nHis scales once shimmered now they're dark with shame\nCast out by his kin in shadows he does hide\nA haunting sorrow burns deep inside\n\n[Chorus]\nRoaming endless fields with no friend in sight\nHis roar a mournful cry beneath the moon's pale light\nTears fall like stars as he flies on his way\nA lonely dragon yearning for the break of day\n\n[Bridge]\nThe world turns cold the nights grow long\nIn his heart he carries an ancient song\nOf battles fought and love long gone\nA legend now but his soul is torn\n\n[Verse 3]\nHoping for a day he'll find a kindred soul\nTo share his pain and make him whole\nTill then he drifts a shadow in the sky\nA lonely dragon with tears in his eye\n\n[Chorus]\nRoaming endless fields with no friend in sight\nHis roar a mournful cry beneath the moon's pale light\nTears fall like stars as he flies on his way\nA lonely dragon yearning for the break of day",
+    "audio_duration": 239.99997916666666,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": true,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.029100656509399414,
+        "diffusion": 22.503791570663452,
+        "latent2audio": 2.3603708744049072
+    },
+    "actual_seeds": [
+        2166832218
+    ]
+}

examples/default/input_params/output_20250426091716_0_input_params.json

@@ -0,0 +1,25 @@
+{
+    "prompt": "anime, cute female vocals, kawaii pop, j-pop, childish, piano, guitar, synthesizer, fast, happy, cheerful, lighthearted",
+    "lyrics": "[Chorus]\nねぇ、顔が赤いよ？\nどうしたの？ 熱があるの？\nそれとも怒ってるの？\nねぇ、言ってよ！\n\nどうしてそんな目で見るの？\n私、悪いことした？\n何か間違えたの？\nお願い、やめて… 怖いから…\nだから、やめてよ…\n\n[Bridge]\n目を閉じて、くるっと背を向けて、\n何も見なかったフリするから、\n怒らないで… 許してよ…\n\n[Chorus]\nねぇ、顔が赤いよ？\nどうしたの？ 熱があるの？\nそれとも怒ってるの？\nねぇ、言ってよ！\n\nどうしてそんな目で見るの？\n私、悪いことした？\n何か間違えたの？\nお願い、やめて… 怖いから…\nだから、やめてよ…\n\n[Bridge 2]\n待って、もし私が悪いなら、\nごめんなさいって言うから、\nアイスクリームあげるから、\nもう怒らないで？\n\nOoooh… 言ってよ！",
+    "audio_duration": 160,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": true,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.0282442569732666,
+        "diffusion": 12.104875326156616,
+        "latent2audio": 1.587641954421997
+    },
+    "actual_seeds": [
+        4028738662
+    ]
+}

examples/default/input_params/output_20250426092025_0_input_params.json

@@ -0,0 +1,25 @@
+{
+    "prompt": "dark, death rock, metal, hardcore, electric guitar, powerful, bass, drums, 110 bpm, G major",
+    "lyrics": "[Verse]\nMy lovers betray me\nThe snake in my garden is hissing\nIn the air is the sweetness of roses\nAnd under my skin\nThere's a thorn\n\n[Verse 2]\nI should have known\nThat God sends his angel in shadows\nWith blood in his veins\nI watch the enemy\nGivin' me the hand of my savior\n\n[Chorus]\nAnd I can't love again\nWith the echo of your name in my head\nWith the demons in my bed\nWith the memories\nYour ghost\nI see it\n'Cause it comes to haunt me\nJust to taunt me\nIt comes to haunt me\nJust to taunt me\n\n[Verse 3]\nWith sugar and spice\nIt's hard to ignore the nostalgia\nWith the men on their knees\nAt the gates of my heart\nHow they beg me\n\n[Verse 4]\nThey say\n\"No one will ever love you\nThe way that I do\nNo one will ever touch you\nThe way that I do\"\n\n[Chorus]\nAnd I can't love again\nWith the echo of your name in my head\nWith the demons in my bed\nWith the memories\nYour ghost\nI see it\n'Cause it comes to haunt me\nJust to taunt me\nIt comes to haunt me\nJust to taunt me",
+    "audio_duration": 174.27997916666666,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": true,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 3.8372838497161865,
+        "diffusion": 13.039669275283813,
+        "latent2audio": 1.7923030853271484
+    },
+    "actual_seeds": [
+        4064916393
+    ]
+}

examples/default/input_params/output_20250426093007_0_input_params.json

@@ -0,0 +1,25 @@
+{
+    "prompt": "aggressive, Heavy Riffs, Blast Beats, Satanic Black Metal",
+    "lyrics": "[verse]\nFloating through the galaxy on a midnight ride\nStars are dancing all around in cosmic tides\nFeel the pulse of space and time beneath our feet\nEvery beat a heartbeat in this endless suite\n\n[chorus]\nGalactic dreams under neon lights\nSailing through the velvet nights\nWe are echoes in a cosmic sea\nIn a universe where we are free\n\n[verse]\nPlanetary whispers in the sky tonight\nEvery constellation's got a secret sight\nDistant worlds and moons we have yet to see\nIn the void of space where we can just be\n\n[bridge]\nAsteroids and comets in a ballet they spin\nLost in the rhythm of where our dreams begin\nClose your eyes and let the synths take flight\nWe're voyagers on an electric night\n\n[verse]\nLet the piano keys unlock the stars above\nEvery chord a memory every note is love\nIn this synth symphony we find our grace\nDrifting forever in this boundless space\n\n[chorus]\nGalactic dreams under neon lights\nSailing through the velvet nights\nWe are echoes in a cosmic sea\nIn a universe where we are free",
+    "audio_duration": 181.99997916666666,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": true,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.025065898895263672,
+        "diffusion": 17.176705837249756,
+        "latent2audio": 1.8225171566009521
+    },
+    "actual_seeds": [
+        1132623236
+    ]
+}

examples/default/input_params/output_20250426093146_0_input_params.json

@@ -0,0 +1,25 @@
+{
+    "prompt": "r&b, soul, funk/soul",
+    "lyrics": "[verse]\nDancing through electric fires\nHeart is buzzing like live wires\nIn your arms I find desire\nFeel the beat as we get higher\n\n[chorus]\nElectric love in the night sky\nWe’re gonna soar baby you and I\nDrop the bass let the rhythm fly\nFeel the heat and don't ask why\n\n[verse]\nWhisper secrets that make me blush\nUnder the neon city hush\nYour touch gives me such a rush\nTurn it up we're feeling lush\n\n[chorus]\nElectric love in the night sky\nWe’re gonna soar baby you and I\nDrop the bass let the rhythm fly\nFeel the heat and don't ask why\n\n[bridge]\nThrough the lights and the smoky haze\nI see you in a thousand ways\nLove's a script and we’re the play\nTurn the page stay till we sway\n\n[chorus]\nElectric love in the night sky\nWe’re gonna soar baby you and I\nDrop the bass let the rhythm fly\nFeel the heat and don't ask why",
+    "audio_duration": 195.15997916666666,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": true,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.025553464889526367,
+        "diffusion": 18.250118494033813,
+        "latent2audio": 1.9400627613067627
+    },
+    "actual_seeds": [
+        2853131993
+    ]
+}

examples/zh_rap_lora/input_params/output_20250512101839_0_input_params.json

@@ -0,0 +1,45 @@
+{
+    "lora_name_or_path": "/root/sag_train/data/ace_step_v1_chinese_rap_lora",
+    "task": "text2music",
+    "prompt": "Rap, adult, male, spoken word, singing, bright, energetic, clear",
+    "lyrics": "[Intro]\n他们说我来自阴影里\n说我的肤色是原罪的印记\n\n[Verse]\n眼神像刀子刮过 穿透我的皮肤\n带着审判和偏见 让我无处可逃处\n你没听过我的故事 没走过我的路\n凭什么就下一个判决 把我划出你的版图\n你说我威胁到你 抢走了你的机会\n可你可知我付出的 是你不敢想象的血泪\n被贴上标签 被区别对待\n呼吸都是错的 只因我生来就不一样态\n\n[Chorus]\n看不见的墙 把我阻隔在外面\n听不见的声音 屏蔽了我的呼唤\n他们制造偏见 他们散播谎言\n只因为我的存在 让他们觉得不安\n\n[Verse]\n每一次努力争取 都会被审视被放大\n每一个细微的错误 都变成攻击的靶\n他们选择性失明 看不见我的汗水\n只看见他们想看的 带着恶意的定位\n系统性的歧视 像一张无形的网\n把我困在原地 无法自由地翱翔\n他们在享受特权 却指责我的贫困\n嘲笑我的口音 我的名字 我的出身\n\n[Chorus]\n看不见的墙 把我阻隔在外面\n听不见的声音 屏蔽了我的呼唤\n他们制造偏见 他们散播谎言\n只因为我的存在 让他们觉得不安\n\n[Bridge]\n我不想寻求同情 只想被公平对待\n不想被定义被束缚 有选择自己未来的权利\n什么时候 才能放下心中的成见\n看到真正的我 而不是你脑海里的画面\n\n[Outro]\n画面... 不安...\n偏见... 歧视...\n什么时候能停止...",
+    "audio_duration": 134.64,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.3,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": false,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.032018184661865234,
+        "diffusion": 13.275121927261353,
+        "latent2audio": 1.291429042816162
+    },
+    "actual_seeds": [
+        3826585269
+    ],
+    "retake_seeds": [
+        2907904223
+    ],
+    "retake_variance": 0.5,
+    "guidance_scale_text": 0,
+    "guidance_scale_lyric": 0,
+    "repaint_start": 0,
+    "repaint_end": 0,
+    "edit_n_min": 0.0,
+    "edit_n_max": 1.0,
+    "edit_n_avg": 1,
+    "src_audio_path": null,
+    "edit_target_prompt": null,
+    "edit_target_lyrics": null,
+    "audio2audio_enable": false,
+    "ref_audio_strength": 0.5,
+    "ref_audio_input": null,
+    "audio_path": "./outputs/output_20250512101839_0.wav"
+}

examples/zh_rap_lora/input_params/output_20250512114703_0_input_params.json

@@ -0,0 +1,45 @@
+{
+    "lora_name_or_path": "/root/sag_train/data/ace_step_v1_chinese_rap_lora",
+    "task": "text2music",
+    "prompt": "Chorus Hook, Melodic Rap, Ambient Synth Pads, adult, rap, Very Fast, Storytelling, Chinese Rap, male, spoken word, bright, energetic, Melodic Flow, clear, clarity, 130 bpm",
+    "lyrics": "[Intro]\n舌 头 打 结 了... 快 念 快 念...\n\n[Verse 1]\n这 个 赌 鬼 蹲 在 柜 台 啃 着 苦 瓜 干 快 很 干\n赌 桌 堆 满 骨 牌 古 怪 股 票 和 五 块 钢 镚 儿 钢 镚\n他 甩 出 扑 克 牌 啪 啪 啪 拍 扁 螃 蟹 壳 哦 壳 扁\n又 摸 摸 麻 将 摸 出 幺 鸡 摸 出 发 财 摸 出 一 条 蛇 蛇 蛇\n庄 家 咳 嗽 咳 破 锣 嗓 子 喊 开 开 开 快 开 开\n赌 鬼 咕 嘟 咕 嘟 灌 咖 啡 灌 到 筷 子 戳 穿 碗 快 戳 穿\n空 气 里 飘 着 锅 巴 味 混 合 隔 夜 的 酸 奶 罐 哦 酸\n输 光 裤 带 还 想 翻 盘 翻 成 煎 饼 摊 老 板 快 翻 盘\n\n[Chorus]\n赌 鬼 赌 鬼 哦 赌 鬼 赌 鬼 快 很 快\n舌 头 打 结 着 念 这 段 哦 这 段 绕 口 令 牌\n若 念 错 一 字 就 罚 你 哦 罚 你 吞 十 斤 海 带\n赌 场 规 矩 就 是 绕 晕 你 哦 绕 晕 你 快 很 快\n\n[Verse 2]\n他 掏 出 铜 板 抠 出 口 袋 最 后 一 颗 快 很 颗\n庄 家 哗 啦 哗 啦 摇 骰 子 摇 出 三 点 又 三 点 哦 三 点\n赌 鬼 急 得 咬 牙 切 齿 咬 到 舌 头 打 蝴 蝶 结 快 打 结\n还 想 押 上 祖 传 的 拖 鞋 拖 把 铁 锅 和 半 包 盐 盐 盐\n突 然 警 笛 嘀 嘟 嘀 嘟 吓 得 他 钻 进 垃 圾 罐 哦 垃 圾\n警 察 咔 嚓 咔 嚓 拍 照 拍 到 他 头 顶 菠 菜 叶 快 拍 照\n最 后 赌 鬼 蹲 监 狱 天 天 背 这 首 绕 口 令 哦 背 不 完\n若 背 错 一 句 就 加 刑 十 年 再 加 十 年 快 加 刑\n\n[Outro]\n舌 头 打 结 了... 赌 鬼 哭 了 哦...\n这 首 歌... 绕 死 人 了 哦...",
+    "audio_duration": 186.59997916666666,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.7,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": false,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.03011012077331543,
+        "diffusion": 21.696259260177612,
+        "latent2audio": 1.7648537158966064
+    },
+    "actual_seeds": [
+        3776541388
+    ],
+    "retake_seeds": [
+        4274500599
+    ],
+    "retake_variance": 0.5,
+    "guidance_scale_text": 0,
+    "guidance_scale_lyric": 0,
+    "repaint_start": 0,
+    "repaint_end": 0,
+    "edit_n_min": 0.0,
+    "edit_n_max": 1.0,
+    "edit_n_avg": 1,
+    "src_audio_path": null,
+    "edit_target_prompt": null,
+    "edit_target_lyrics": null,
+    "audio2audio_enable": false,
+    "ref_audio_strength": 0.5,
+    "ref_audio_input": null,
+    "audio_path": "./outputs/output_20250512114703_0.wav"
+}

examples/zh_rap_lora/input_params/output_20250512115409_0_input_params.json

@@ -0,0 +1,45 @@
+{
+    "lora_name_or_path": "/root/sag_train/data/ace_step_v1_chinese_rap_lora",
+    "task": "text2music",
+    "prompt": "electronic, hip-hop, rap, synthesizer, drums, vocals, fast, energetic, modern, uplifting, young adult, male, spoken word, singing, bright, energetic, clear, 140 bpm, female",
+    "lyrics": "[Verse 1]\n红鲤鱼绿鲤鱼，驴在河里追鲤鱼，\n驴追鲤鱼鱼躲驴，气得驴子直喘气。\n扁担长板凳宽，扁担绑在板凳边，\n扁担要绑板凳不让绑，扁担偏要绑上板凳面！\n\n[Chorus]\n绕口令，练嘴皮，\n说快说慢别迟疑，\n红鲤鱼驴扁担板凳，\n一口气念完算你赢！\n\n[Verse 2]\n四是四十是十，十四是十四四十是四十，\n谁说四十是十四，舌头打结别放肆。\n黑化肥会挥发，灰化肥也发黑，\n化肥混一起，黑灰不分嘴发废！\n\n[Chorus]\n绕口令，练嘴皮，\n说快说慢别迟疑，\n四十十四化肥灰，\n念错罚你唱十回！\n\n[Bridge]\n坡上立着一只鹅，坡下流着一条河，\n鹅要过河河渡鹅，河要渡鹅鹅笑河——\n到底谁更啰嗦？！\n\n[Outro]\n嘴皮子功夫别小瞧，\n绕口令rap我最飙，\n下次挑战准备好，\n舌头打结别求饶！",
+    "audio_duration": 123.2,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.7,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": false,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.026150941848754883,
+        "diffusion": 12.212433099746704,
+        "latent2audio": 1.1857895851135254
+    },
+    "actual_seeds": [
+        1415752189
+    ],
+    "retake_seeds": [
+        685932970
+    ],
+    "retake_variance": 0.5,
+    "guidance_scale_text": 0,
+    "guidance_scale_lyric": 0,
+    "repaint_start": 0,
+    "repaint_end": 0,
+    "edit_n_min": 0.0,
+    "edit_n_max": 1.0,
+    "edit_n_avg": 1,
+    "src_audio_path": null,
+    "edit_target_prompt": null,
+    "edit_target_lyrics": null,
+    "audio2audio_enable": false,
+    "ref_audio_strength": 0.5,
+    "ref_audio_input": null,
+    "audio_path": "./outputs/output_20250512115409_0.wav"
+}

examples/zh_rap_lora/input_params/output_20250512120348_0_input_params.json

@@ -0,0 +1,45 @@
+{
+    "lora_name_or_path": "/root/sag_train/data/ace_step_v1_chinese_rap_lora",
+    "task": "text2music",
+    "prompt": "singing, bright, slightly nasal, energetic, spoken word, young adult, male, rap music",
+    "lyrics": "[Intro]\nYo, check it—speed demon, lyrical heat, uh!\nRatatat like a drum when the beat bumps, uh!\n\n[Verse 1]\nRapatapa tap tap, flash like a snap,\nRap tap tap, I don’t chat, I clap clap clap!\nFingers snap, flow don’t slack, rapataptaptap,\nSpit it fast, hit the gas, rap tap tap rap!\n\n[Pre-Chorus]\nBoom-bap, zoom past, leave ’em flat,\nRap taptaprapataptaptap—where ya at?\n\n[Chorus]\nRapatapa tap tap, yeah, I go brrrr,\nRap tap tap, make the crowd stir!\nRapataptaptap, no lag, just spit,\nRap taptaprapataptaptap—I’m lit!\n\n[Verse 2]\nTongue-twist, quick wrist, rapatapa boom,\nTap tap rap, leave ya stuck like glue-gum!\nNo slow-mo, turbo, rapataptaptap,\nRap tap rap, yeah, I clap clap clap!\n\n[Outro]\nRapatapa—TAP! Mic drop—that’s that.",
+    "audio_duration": 60,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": false,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.018491744995117188,
+        "diffusion": 8.084580898284912,
+        "latent2audio": 0.5694489479064941
+    },
+    "actual_seeds": [
+        226581098
+    ],
+    "retake_seeds": [
+        1603201617
+    ],
+    "retake_variance": 0.5,
+    "guidance_scale_text": 0,
+    "guidance_scale_lyric": 0,
+    "repaint_start": 0,
+    "repaint_end": 0,
+    "edit_n_min": 0.0,
+    "edit_n_max": 1.0,
+    "edit_n_avg": 1,
+    "src_audio_path": null,
+    "edit_target_prompt": null,
+    "edit_target_lyrics": null,
+    "audio2audio_enable": false,
+    "ref_audio_strength": 0.5,
+    "ref_audio_input": null,
+    "audio_path": "./outputs/output_20250512120348_0.wav"
+}

examples/zh_rap_lora/input_params/output_20250512143242_0_input_params.json

@@ -0,0 +1,45 @@
+{
+    "lora_name_or_path": "ACE-Step/ACE-Step-v1-chinese-rap-LoRA",
+    "task": "text2music",
+    "prompt": "G-Funk, Hip Hop, Rap, Female Vocals, Melodic Rap, Summer, Laid-back Groove, Smooth Rhythm, Synthesizer Lead, Heavy Bassline, Groovy, West Coast Hip Hop",
+    "lyrics": "(Intro)\nOh yeah... \n\n(Verse 1)\n阳光下，沙滩排球场，一个身影跳跃\n小麦色，运动背心，闪耀活力四射\n她跳起扣杀，动作利落又巧妙\n汗水浸湿发梢，笑容比阳光更美好\n摇摆的节奏，是她的背景配乐\n每一次移动，都踩在鼓点上那么和谐\n我不由自主地停下脚步\n目光被她紧紧锁住\n\n(Chorus)\n沙滩排球女孩， 摇摆节拍下的身材\n无忧无虑的笑容，把我的心都填满\n想走上前去搭讪，嫌自己笨拙呆板\n这青春的气息，耀眼，灿烂！\n\n(Verse 3)\n她和队友击掌庆祝，笑声清脆悦耳\n拿起毛巾擦汗，不经意间瞥我一眼\n鼓起勇气走上前，假装问问时间\n她友好地回答，笑容灿烂没有敷衍\n聊了几句，发现彼此爱这摇摆音乐\n她眼中也闪过惊喜和亲切\n这共同点，让气氛变得融洽又热烈！\n夏天的故事，就这样开始了感觉真切！\n\n(Chorus)\n沙滩排球女孩， 摇摆节拍下的身材\n无忧无虑的笑容，把我的心都填满\n不再犹豫和等待，勇敢把脚步迈开\n这夏天的感觉，心跳，不断！",
+    "audio_duration": 93.93038,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": false,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.03020024299621582,
+        "diffusion": 9.942127704620361,
+        "latent2audio": 0.9470341205596924
+    },
+    "actual_seeds": [
+        3826585299
+    ],
+    "retake_seeds": [
+        2519711205
+    ],
+    "retake_variance": 0.5,
+    "guidance_scale_text": 0,
+    "guidance_scale_lyric": 0,
+    "repaint_start": 0,
+    "repaint_end": 0,
+    "edit_n_min": 0.0,
+    "edit_n_max": 1.0,
+    "edit_n_avg": 1,
+    "src_audio_path": null,
+    "edit_target_prompt": null,
+    "edit_target_lyrics": null,
+    "audio2audio_enable": false,
+    "ref_audio_strength": 0.5,
+    "ref_audio_input": null,
+    "audio_path": "./outputs/output_20250512143242_0.wav"
+}

examples/zh_rap_lora/input_params/output_20250512145057_0_input_params.json

@@ -0,0 +1,45 @@
+{
+    "lora_name_or_path": "/root/sag_train/data/ace_step_v1_chinese_rap_lora_80k",
+    "task": "text2music",
+    "prompt": "lyrical rap, young adult, female, rap flow, spoken word, ad-libs, bright, energetic, eat, Fast, Engaging, Energetic",
+    "lyrics": "[Intro]\n扁擔寬 板凳長 扁擔想綁在板凳上\n扁擔寬 板凳長 扁擔想綁在板凳上\n\n[Verse]\n倫敦 瑪莉蓮 買了 件 旗袍 送 媽媽\n莫斯科 的 夫司基 愛上 牛肉 麵 疙瘩\n各種 顏色 的 皮膚 各種 顏色 的 頭髮\n嘴裡念的 說的 開始 流行 中國話 (中國話)\n\n[Bridge]\n多少年 我們 苦練 英文 發音 和 文法 (yeah)\n這幾年 換他們 捲著 舌頭 學 平上去入 的 變化\n平平 仄仄 平平 仄\n好聰明 的 中國人 好優美 的 中國話\n\n[Verse]\n扁擔寬 板凳長 扁擔想綁在板凳上\n板凳不讓扁擔綁在板凳上 扁擔偏要綁在板凳上\n板凳偏偏不讓扁擔綁在那板凳上\n到底扁擔寬 還是板凳長？\n\n[Verse]\n哥哥弟弟坡前坐\n坡上臥著一隻鵝 坡下流著一條河\n哥哥說 寬寬的河 弟弟說 白白的鵝\n鵝要過河 河要渡鵝\n不知是那鵝過河 還是河渡鵝\n\n[Chorus]\n全世界都在學中國話\n孔夫子的話 越來越國際化\n全世界都在講中國話\n我們說的話 讓世界都認真聽話\n\n[Verse]\n紐約蘇珊娜開了間禪風 lounge bar\n柏林來的沃夫岡拿胡琴配著電吉他\n各種顏色的皮膚 各種顏色的頭髮\n嘴裡念的 說的 開始流行中國話 (中國話)\n\n[Bridge]\n多少年我們苦練英文發音和文法 (yeah)\n這幾年換他們捲著舌頭學平上去入的變化\n仄仄平平仄仄平\n好聰明的中國人 好優美的中國話\n\n[Verse]\n有個小孩叫小杜 上街打醋又買布\n買了布 打了醋 回頭看見鷹抓兔\n放下布 擱下醋 上前去追鷹和兔\n飛了鷹 跑了兔 灑了醋 濕了布\n\n[Verse]\n嘴說腿 腿說嘴\n嘴說腿 愛跑腿\n腿說嘴 愛賣嘴\n光動嘴 不動腿\n光動腿 不動嘴\n不如不長腿和嘴\n到底是那嘴說腿 還是腿說嘴？\n\n[Chorus]\n全世界都在學中國話\n孔夫子的話 越來越國際化\n全世界都在講中國話\n我們說的話 讓世界都認真聽話\n\n[outro]\n全世界都在學中國話 (在學中國話)\n孔夫子的話 越來越國際化\n全世界都在講中國話\n我們說的話 (讓他) 讓世界 (認真) 都認真聽話",
+    "audio_duration": 239.8355625,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": false,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.04363536834716797,
+        "diffusion": 18.706920385360718,
+        "latent2audio": 2.1645781993865967
+    },
+    "actual_seeds": [
+        2364345905
+    ],
+    "retake_seeds": [
+        2100914041
+    ],
+    "retake_variance": 0.5,
+    "guidance_scale_text": 0,
+    "guidance_scale_lyric": 0,
+    "repaint_start": 0,
+    "repaint_end": 0,
+    "edit_n_min": 0.0,
+    "edit_n_max": 1.0,
+    "edit_n_avg": 1,
+    "src_audio_path": null,
+    "edit_target_prompt": null,
+    "edit_target_lyrics": null,
+    "audio2audio_enable": false,
+    "ref_audio_strength": 0.5,
+    "ref_audio_input": null,
+    "audio_path": "./outputs/output_20250512145057_0.wav"
+}

examples/zh_rap_lora/input_params/output_20250512152217_0_input_params.json

@@ -0,0 +1,45 @@
+{
+    "lora_name_or_path": "/root/sag_train/data/ace_step_v1_chinese_rap_lora_80k",
+    "task": "text2music",
+    "prompt": "articulate, spoken word, young adult, warm, rap music, male, clear, street, dark, rap flow, hardcore rap",
+    "lyrics": "[verse]\n球场 的 橡胶味 弥漫 隔壁 是 健身房\n场 边上 的 老教练 战术 有 三套\n教 交叉 运球 的 大叔 会 欧洲步 耍 背后 传\n硬 身板 对抗 最 擅长 还 会 急停跳 后仰 投\n他们 徒弟 我 习惯 从小 就 耳濡目染\n什么 胯下 跟 变向 我 都 玩 的 有模有样\n什么 招式 最 喜欢 转身 过 人 柔中 带 刚\n想要 去 纽约 街头 斗 洛克 公园 场\n\n[chorus]\n看什么 看什么\n变速 突破 心 自在\n看什么 看什么\n假动作 晃 开 防守 来\n看什么 看什么\n每日 训练 绑 沙袋\n空中拉杆 莫 奇怪\n唰唰 入袋\n\n[verse]\n一个 试探 步后 一记 左 变向 右 变向\n一句 挑衅 我 的 人 别 嚣张\n一再 重演 一颗 我 不 投 的 球\n悬在 篮筐 上 它 一直 在 摇晃\n\n[chorus]\n看什么 看什么\n我 激活 小宇宙 来\n看什么 看什么\n菜鸟 新人 的 名号\n看什么 看什么\n已 被 我 一球 击倒\n\n[chorus]\n快 秀出 指尖 转球 砰砰 啪嗒\n快 秀出 指尖 转球 砰砰 啪嗒\n篮球 之 人 切记 勇者 无惧\n是 谁 在 玩 花式 引爆 空气\n快 秀出 指尖 转球 砰砰 啪嗒\n快 秀出 指尖 转球 砰砰 啪嗒\n如果 我 有 滞空 逆天 补扣\n为人 热血 不怂 一生 傲骨 吼\n\n[verse]\n他们 徒弟 我 习惯 从小 就 耳濡目染\n什么 胯下 跟 变向 我 都 玩 的 有模有样\n什么 招式 最 喜欢 转身 过 人 柔中 带 刚\n想要 去 纽约 街头 斗 洛克 公园 场\n\n[outro]\n快 秀出 指尖 转球 砰\n快 秀出 指尖 转球 砰\n如果 我 有 滞空 吼\n为人 热血 不怂 一生 傲骨 吼\n快 秀出 指尖 转球 砰\n我 用 背传 助攻 吼\n压哨 的 三分 球",
+    "audio_duration": 239.8355625,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": false,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.05357813835144043,
+        "diffusion": 25.644447326660156,
+        "latent2audio": 2.1787476539611816
+    },
+    "actual_seeds": [
+        3246571430
+    ],
+    "retake_seeds": [
+        1352325167
+    ],
+    "retake_variance": 0.5,
+    "guidance_scale_text": 0,
+    "guidance_scale_lyric": 0,
+    "repaint_start": 0,
+    "repaint_end": 0,
+    "edit_n_min": 0.0,
+    "edit_n_max": 1.0,
+    "edit_n_avg": 1,
+    "src_audio_path": null,
+    "edit_target_prompt": null,
+    "edit_target_lyrics": null,
+    "audio2audio_enable": false,
+    "ref_audio_strength": 0.5,
+    "ref_audio_input": null,
+    "audio_path": "./outputs/output_20250512152217_0.wav"
+}

examples/zh_rap_lora/input_params/output_20250512153616_0_input_params.json

@@ -0,0 +1,45 @@
+{
+    "lora_name_or_path": "/root/sag_train/data/ace_step_v1_chinese_rap_lora_80k",
+    "task": "text2music",
+    "prompt": "articulate, spoken word, young adult, warm, rap music, male, clear, street, dark, rap flow, hardcore rap, fast",
+    "lyrics": "[verse]\n球场 的 橡胶味 弥漫 隔壁 是 健身房\n场 边上 的 老教练 战术 有 三套\n教 交叉 运球 的 大叔 会 欧洲步 耍 背后 传\n硬 身板 对抗 最 擅长 还 会 急停跳 后仰 投\n他们 徒弟 我 习惯 从小 就 耳濡目染\n什么 胯下 跟 变向 我 都 玩 的 有模有样\n什么 招式 最 喜欢 转身 过 人 柔中 带 刚\n想要 去 纽约 街头 斗 洛克 公园 场\n\n[chorus]\n看什么 看什么\n变速 突破 心 自在\n看什么 看什么\n假动作 晃 开 防守 来\n看什么 看什么\n每日 训练 绑 沙袋\n空中拉杆 莫 奇怪\n唰唰 入袋\n\n[verse]\n一个 试探 步后 一记 左 变向 右 变向\n一句 挑衅 我 的 人 别 嚣张\n一再 重演 一颗 我 不 投 的 球\n悬在 篮筐 上 它 一直 在 摇晃\n\n[chorus]\n看什么 看什么\n我 激活 小宇宙 来\n看什么 看什么\n菜鸟 新人 的 名号\n看什么 看什么\n已 被 我 一球 击倒\n\n[chorus]\n快 秀出 指尖 转球 砰砰 啪嗒\n快 秀出 指尖 转球 砰砰 啪嗒\n篮球 之 人 切记 勇者 无惧\n是 谁 在 玩 花式 引爆 空气\n快 秀出 指尖 转球 砰砰 啪嗒\n快 秀出 指尖 转球 砰砰 啪嗒\n如果 我 有 滞空 逆天 补扣\n为人 热血 不怂 一生 傲骨 吼\n\n[verse]\n他们 徒弟 我 习惯 从小 就 耳濡目染\n什么 胯下 跟 变向 我 都 玩 的 有模有样\n什么 招式 最 喜欢 转身 过 人 柔中 带 刚\n想要 去 纽约 街头 斗 洛克 公园 场\n\n[outro]\n快 秀出 指尖 转球 砰\n快 秀出 指尖 转球 砰\n如果 我 有 滞空 吼\n为人 热血 不怂 一生 傲骨 吼\n快 秀出 指尖 转球 砰\n我 用 背传 助攻 吼\n压哨 的 三分 球",
+    "audio_duration": 183.23,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": false,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.046170711517333984,
+        "diffusion": 14.21678113937378,
+        "latent2audio": 2.685957193374634
+    },
+    "actual_seeds": [
+        3072005931
+    ],
+    "retake_seeds": [
+        562842491
+    ],
+    "retake_variance": 0.5,
+    "guidance_scale_text": 0,
+    "guidance_scale_lyric": 0,
+    "repaint_start": 0,
+    "repaint_end": 0,
+    "edit_n_min": 0.0,
+    "edit_n_max": 1.0,
+    "edit_n_avg": 1,
+    "src_audio_path": null,
+    "edit_target_prompt": null,
+    "edit_target_lyrics": null,
+    "audio2audio_enable": false,
+    "ref_audio_strength": 0.5,
+    "ref_audio_input": null,
+    "audio_path": "./outputs/output_20250512153616_0.wav"
+}

examples/zh_rap_lora/input_params/output_20250512154907_0_input_params.json

@@ -0,0 +1,45 @@
+{
+    "lora_name_or_path": "/root/sag_train/data/ace_step_v1_chinese_rap_lora_80k",
+    "task": "text2music",
+    "prompt": "articulate, spoken word, young adult, rap music, female, clear, energetic, warm",
+    "lyrics": "[Intro]\n\"System booting... 语言 模型 loading...\"\n\n[Verse 1]\n硅谷 那个 coder 调试 neural network\n北京 的 极客 训练 A I 写 report\n不同 架构 的 chip 不同 算法 的 war\n屏幕上 跑的 全是 machine learning (learning)\n\n[Bridge]\n多少年 我们 chase 摩尔 定律 的 trend (yeah)\n这两年 换他们 study 中文 N L P\nConvolution L S T M\n好烧脑 的 backprop 好暴力 的 big data\n\n[Verse 2]\nPython 强 say加加 刚 Python 调用 C++ 的 A P I\nsay加加 嫌 Python 太 slow Python 笑 C++ 太 hardcore\nL L V M 默默 generate 中间 code\n到底 interpreter 还是 compiler 屌？\n\n[Verse 3]\nP M 和 engineer\n白板 画满 flow chart 服务器 闪着 red light\nP M 说 add feature engineer 说 no way\n需求 变更 code 重构\n不知 是 P M 太 fly 还是 deadline 太 high\n\n[Chorus]\n全世界 都在 train neural network\nTransformer 的 paper 越来越 难 go through\n全世界 都在 tune 超参数\n我们 写的 bug 让 G P U 都 say no\n\n[Verse 4]\n柏林 hackathon demo blockchain contract\n上海 的 dev 用 federated learning 破 data wall\n各种 语言 的 error 各种 框架 的 doc\nterminal 里 滚的 全是 dependency 冲突\n\n[Bridge]\n曾以为 English 才是 coding 的 language (yeah)\n直到见 G P T 用 文言文 generate 正则 expression\nGradient explode\n好硬核 的 prompt 好头秃 的 debug road\n\n[Verse 5]\n有个 bug 叫 quantum\n测试 环境 run perfect 上线 立即就 crash\n查 log 看 monitor 发现是 thread 不同步\n改 sync 加 lock 慢 deadlock 更难办\n量子 computer 也解不开 这 chaos chain\n\n[Verse 6]\n你说 996 我说 007\n你说 福报 我说 burnout\nProduct 要 agile Boss 要 KPI\nCode 要 elegant deadline 是 tomorrow\n不如 直接 script 自动 submit 离职信\n\n[Outro]\n\"Warning: 内存 leak...core dumping...\"\n全世界 都在 train neural network (neural network)\nLoss 还没 converge 天已经亮\n全世界 都在 tune 超参数\n我们 写的 code (让它) 让 world (reboot) 都 reboot 无效",
+    "audio_duration": 179.12,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": false,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.062120914459228516,
+        "diffusion": 13.499217987060547,
+        "latent2audio": 1.6430137157440186
+    },
+    "actual_seeds": [
+        1637990575
+    ],
+    "retake_seeds": [
+        101283039
+    ],
+    "retake_variance": 0.5,
+    "guidance_scale_text": 0,
+    "guidance_scale_lyric": 0,
+    "repaint_start": 0,
+    "repaint_end": 0,
+    "edit_n_min": 0.0,
+    "edit_n_max": 1.0,
+    "edit_n_avg": 1,
+    "src_audio_path": null,
+    "edit_target_prompt": null,
+    "edit_target_lyrics": null,
+    "audio2audio_enable": false,
+    "ref_audio_strength": 0.5,
+    "ref_audio_input": null,
+    "audio_path": "./outputs/output_20250512154907_0.wav"
+}

examples/zh_rap_lora/input_params/output_20250512161832_0_input_params.json

@@ -0,0 +1,45 @@
+{
+    "lora_name_or_path": "/root/sag_train/data/ace_step_v1_chinese_rap_lora_80k",
+    "task": "text2music",
+    "prompt": "articulate, spoken word, young adult, rap music, male, clear, energetic, warm, relaxed, breathy, night club, auto-tune, mumble rap, trap",
+    "lyrics": "[verse]\n这 这 谁 又 在 派 对 喝 多\n我 的 脑 袋\n像 被 驴 踢 过\n不 对 劲\n舌 头 打 结 不 会 说\n你 来 挑 战 我 就 跪\n开 局 直 接 崩 溃\n\n[chorus]\n就 咪 乱 咪 念 咪 错 咪\n嘴 咪 瓢 咪 成 咪 狗 咪\n脑 咪 袋 咪 像 咪 浆 咪 糊 咪\n跟 咪 着 咪 节 咪 奏 咪\n把 咪 歌 咪 词 咪 全 咪 忘 咪\n一 咪 张 咪 嘴 咪 就 咪 废 咪\n只 咪 剩 咪 下 咪 尴 咪 尬 咪 回 咪 忆\n草！\n\n[verse]\n错 错 错 错 了\n一 口 气 全 念 错\n错 错 错 错 了\n舌 头 打 结 甩 锅\n甩 甩 甩 甩 锅\n甩 锅 甩 锅\n拍 子 全 部 乱 套\n观 众 笑 到 吐 血\n\n[verse]\n你 的 歌 词 我 的 噩 梦\n唱 完 直 接 社 死\n调 跑 到 外 太 空\n观 众 表 情 裂 开\n你 笑 我 菜\n我 笑 你 不 懂\n这 叫 艺 术 表 演\n不 服 你 来！\n\n[verse]\n这 这 谁 又 在 派 对 丢 人\n我 的 世 界\n已 经 彻 底 崩 溃\n没 有 完 美\n只 有 翻 车 现 场\n以 及 观 众 的 嘲 讽\n\n[chorus]\n就 咪 乱 咪 念 咪 错 咪\n嘴 咪 瓢 咪 成 咪 狗 咪\n脑 咪 袋 咪 像 咪 浆 咪 糊 咪\n跟 咪 着 咪 节 咪 奏 咪\n把 咪 歌 咪 词 咪 全 咪 忘 咪\n一 咪 张 咪 嘴 咪 就 咪 废 咪\n只 咪 剩 咪 下 咪 尴 咪 尬 咪 回 咪 忆\n草！\n\n[verse]\n错 错 错 错 了\n一 口 气 全 念 错\n错 错 错 错 了\n舌 头 打 结 甩 锅\n甩 甩 甩 甩 锅\n甩 锅 甩 锅\n拍 子 全 部 乱 套\n观 众 笑 到 吐 血\n\n[verse]\n你 的 歌 词 我 的 噩 梦\n唱 完 直 接 社 死\n调 跑 到 外 太 空\n观 众 表 情 裂 开\n你 笑 我 菜\n我 笑 你 不 懂\n这 叫 艺 术 表 演\n不 服 你 来！",
+    "audio_duration": 169.12,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": false,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.04321885108947754,
+        "diffusion": 14.026689767837524,
+        "latent2audio": 1.5587565898895264
+    },
+    "actual_seeds": [
+        1905941472
+    ],
+    "retake_seeds": [
+        3018484796
+    ],
+    "retake_variance": 0.5,
+    "guidance_scale_text": 0,
+    "guidance_scale_lyric": 0,
+    "repaint_start": 0,
+    "repaint_end": 0,
+    "edit_n_min": 0.0,
+    "edit_n_max": 1.0,
+    "edit_n_avg": 1,
+    "src_audio_path": null,
+    "edit_target_prompt": null,
+    "edit_target_lyrics": null,
+    "audio2audio_enable": false,
+    "ref_audio_strength": 0.5,
+    "ref_audio_input": null,
+    "audio_path": "./outputs/output_20250512161832_0.wav"
+}

examples/zh_rap_lora/input_params/output_20250512164224_0_input_params.json

@@ -0,0 +1,45 @@
+{
+    "lora_name_or_path": "/root/sag_train/data/ace_step_v1_chinese_rap_lora_80k",
+    "task": "text2music",
+    "prompt": "四川话, spoken word, male, Tempo - Fast, Elements - Chorus Hook, Subgenre-Satirical Hip Hop, Rap, Chinese-language music, energetic, slightly nasal, Instrument - Live Bass Guitar, adult, Vocals - Syncopated Flow, Genre - Hip-Hop, rapping, bright",
+    "lyrics": "[chorus]\n黑 墨镜 金 链子 越 低调 越 霸气\n玩 街机 泡 吧里 再 野的 场子 都 不 怯气\n上海 滩 老 江湖 外滩 钟声 敲 胜负\n陆家嘴 黄浦江 财路 宽 给 你 开 扇窗\n\n[verse]\n老子 在 弄堂 斜起 走 想 拦路 的 先 报 名号\n我 早看透 你们 手抖 脚软\n只敢 网上 吠 现实 怂成 猫\n看 你们 混的 真 可怜 整天 蹲在 网吧 蹭 烟\n钱 赚不到 架 不敢打 还 学人 摆 大哥 脸\n\n[verse]\n叫 我 沪上 老 克勒 不是 拉菲 我 不 碰杯\n规矩 我 懒得 讲 太多 钞票 直接 拍 你 脸上 飞\n老子 耐心 差 门槛 高 你 找茬 等于 自 寻 烦恼\n要么 跪 要么 爬 最后 警告 只 说 一 遭\n\n[chorus]\n黑 墨镜 金 链子 越 低调 越 霸气\n玩 街机 泡 吧里 再 野的 场子 都 不 怯气\n上海 滩 老 江湖 外滩 钟声 敲 胜负\n陆家嘴 黄浦江 财路 宽 给 你 开 扇窗\n\n[verse]\n古巴 雪茄 在 指间 绕 代表 魔都 格调 必须 顶\nOG 在 你 够不到 的 高度 My bro 永远 在 顶层 盯\nCheck my vibe 不靠 大 金劳 留声机 放 周璇 和 白光\n爹妈 太 宠你 养出 巨婴 症 早晚 社会 教你 做人 经\n\n[verse]\n玩 说唱 小囡 太 年轻 要 比 flow 先去 练 气功\n廿年 磨 枪 才 亮 锋芒 我 三十六 招 收 你 入 瓮\n老子 存在 就是 打假 标\n多少 人 眼红 又 不敢 挑\n键盘 侠 的 狠话 像 棉花 糖\n见 真人 秒变 Hello Kitty 叫\n\n[chorus]\n黑 墨镜 金 链子 越 低调 越 霸气\n玩 街机 泡 吧里 再 野的 场子 都 不 怯气\n上海 滩 老 江湖 外滩 钟声 敲 胜负\n陆家嘴 黄浦江 财路 宽 给 你 开 扇窗\n\n[chorus]\n黑 墨镜 金 链子 越 低调 越 霸气\n玩 街机 泡 吧里 再 野的 场子 都 不 怯气\n上海 滩 老 江湖 外滩 钟声 敲 胜负\n陆家嘴 黄浦江 财路 宽 给 你 开 扇窗",
+    "audio_duration": 135.92,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": false,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.038518667221069336,
+        "diffusion": 16.47420620918274,
+        "latent2audio": 2.5094873905181885
+    },
+    "actual_seeds": [
+        2159904788
+    ],
+    "retake_seeds": [
+        2403013980
+    ],
+    "retake_variance": 0.5,
+    "guidance_scale_text": 0,
+    "guidance_scale_lyric": 0,
+    "repaint_start": 0,
+    "repaint_end": 0,
+    "edit_n_min": 0.0,
+    "edit_n_max": 1.0,
+    "edit_n_avg": 1,
+    "src_audio_path": null,
+    "edit_target_prompt": null,
+    "edit_target_lyrics": null,
+    "audio2audio_enable": false,
+    "ref_audio_strength": 0.5,
+    "ref_audio_input": null,
+    "audio_path": "./outputs/output_20250512164224_0.wav"
+}

examples/zh_rap_lora/input_params/output_20250512171227_0_input_params.json

@@ -0,0 +1,45 @@
+{
+    "lora_name_or_path": "ACE-Step/ACE-Step-v1-chinese-rap-LoRA",
+    "task": "text2music",
+    "prompt": "Rap, Chinese Rap, J-Pop, Anime, kawaii pop, EDM, Aggressive, Intense, Crisp Snare, Super Fast, Clear",
+    "lyrics": "(Intro)\nLet's drift away...\n\n(Verse 1)\n现实是灰色的格子间，重复的工作，枯燥的报表 \n敲打着键盘，眼神却放空，意识早已挣脱了肉体的镣铐\n飘向窗外，飞过拥挤的街道，穿过云层，到达想象的群岛\n那里色彩斑斓，形状奇异，逻辑失效，一切都随心所欲地飘摇\n迷幻的鼓点，像心跳的变奏，忽快忽慢，难以预料\n抽象的采样，扭曲的人声，构建一个超现实的音景环绕\n我变成一只鸟，一条鱼，一束光，自由地变换形态和奔跑\n在这白日梦里，我无所不能，摆脱了所有现实的烦恼， feeling the afterglow\n\n(Chorus)\n意识漫游，逃离乏味的轨道 \n迷幻嘻哈的节拍，是白日梦的引导 \n抽象的世界，逻辑被重新构造\nMind wandering free, where reality starts to fade slow\n\n(Verse 2)\n会议室里老板在讲话，声音模糊，像隔着水听不清道\n我的思绪，早已潜入深海，与发光的水母一起舞蹈\n或者飞向外太空，在星云间穿梭，探索未知的星球和轨道\n现实的规则，在这里被打破，物理定律也失去效劳\n白日梦是我的避难所，是精神的氧气罩\n在乏味的现实里，为我注入一点色彩和奇妙\n虽然短暂，虽然虚幻，但它让我能够喘息，重新把能量找到\n然后回到现实，继续扮演那个，循规蹈矩的角色，把梦藏好， keep the dream aglow\n\n(Chorus)\n意识漫游，逃离乏味的轨道\n迷幻嘻哈的节拍，是白日梦的引导\n抽象的世界，逻辑被重新构造\nMind wandering free, where reality starts to fade slow\n",
+    "audio_duration": 153.7148,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": false,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.04823446273803711,
+        "diffusion": 13.158645629882812,
+        "latent2audio": 1.493880033493042
+    },
+    "actual_seeds": [
+        2945962357
+    ],
+    "retake_seeds": [
+        2676242300
+    ],
+    "retake_variance": 0.5,
+    "guidance_scale_text": 0.7,
+    "guidance_scale_lyric": 1.5,
+    "repaint_start": 0,
+    "repaint_end": 0,
+    "edit_n_min": 0.0,
+    "edit_n_max": 1.0,
+    "edit_n_avg": 1,
+    "src_audio_path": null,
+    "edit_target_prompt": null,
+    "edit_target_lyrics": null,
+    "audio2audio_enable": false,
+    "ref_audio_strength": 0.5,
+    "ref_audio_input": null,
+    "audio_path": "./outputs/output_20250512171227_0.wav"
+}

examples/zh_rap_lora/input_params/output_20250512171809_0_input_params.json

@@ -0,0 +1,45 @@
+{
+    "lora_name_or_path": "/root/sag_train/data/ace_step_v1_chinese_rap_lora",
+    "task": "text2music",
+    "prompt": "J-Pop, Anime, kawaii future bass, Femal vocals, EDM, Boombap, Aggressive, Intense, Crisp Snare, Super Fast, Rap",
+    "lyrics": "[Intro]\nYo, 这是来自深渊的怒吼\n\n[Verse]\n指尖飞快刷新，屏幕又亮起\n渴望那点赞，像致命的氧气\n精心修饰的脸庞，完美到诡异\n背后隐藏的疲惫，谁又会在意\n光鲜亮丽的橱窗，贩卖着焦虑\n每个人都在表演，戴着虚伪面具\n比较的游戏，让人逐渐窒息\n迷失在数据洪流，找不到自己\n\n[Chorus]\n这流量的时代，真假早已分不清\n盲目追随潮流，丢掉了初心\n为了那点虚荣，灵魂在沉沦\n看不见的锁链，捆绑每个灵魂\n\n[Verse]\n滤镜下的生活，美得不切实际\n营造虚假繁荣，掩盖内心空虚\n他人的光环下，显得自己多余\n嫉妒和自卑，交织成悲剧\n\n[Chorus]\n朋友圈里炫耀，现实中却叹气\n刷着别人的故事，忘记了呼吸\n算法推荐着你，想看的一切东西\n不知不觉间，你已不再是你\n他们说这是进步，我看是种病\n精神鸦片侵蚀，慢慢要了你的命\n\n[Bridge]\n屏幕亮了又暗，一天又过去\n究竟得到了什么，还是失去了自己\n那真实的连接，在何处寻觅\n困在这迷宫里，找不到出口的轨迹\n\n[Outro]\n我想挣脱，我想呼吸\n这虚拟的繁华，让我喘不过气\n谁能告诉我，这到底有什么意义\n一切都像泡沫，一触就破裂没余地",
+    "audio_duration": 119.44348,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": false,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.04764962196350098,
+        "diffusion": 10.94297981262207,
+        "latent2audio": 1.1815783977508545
+    },
+    "actual_seeds": [
+        3826585273
+    ],
+    "retake_seeds": [
+        2527594022
+    ],
+    "retake_variance": 0.5,
+    "guidance_scale_text": 0,
+    "guidance_scale_lyric": 0,
+    "repaint_start": 0,
+    "repaint_end": 0,
+    "edit_n_min": 0.0,
+    "edit_n_max": 1.0,
+    "edit_n_avg": 1,
+    "src_audio_path": null,
+    "edit_target_prompt": null,
+    "edit_target_lyrics": null,
+    "audio2audio_enable": false,
+    "ref_audio_strength": 0.5,
+    "ref_audio_input": null,
+    "audio_path": "./outputs/output_20250512171809_0.wav"
+}

examples/zh_rap_lora/input_params/output_20250512172941_0_input_params.json

@@ -0,0 +1,45 @@
+{
+    "lora_name_or_path": "/root/sag_train/data/ace_step_v1_chinese_rap_lora_80k",
+    "task": "text2music",
+    "prompt": "Hip Hop, Hi-hat Rolls, spoken word, Melodic Flow, articulate, Female Rap, 120 BPM, clear, warm, female, melodic Rap, adult, super fast",
+    "lyrics": "[Verse 1]\n打南边来了个喇嘛，手里提拉着五斤鳎目，\n打北边来了个哑巴，腰里别着个喇叭。\n喇嘛想换哑巴的喇叭，哑巴摇头不说话，\n鳎目一甩像道闪电，喇叭一响震天涯！\n\n[Chorus]\n丁丁当当，乒乓乓乓，\n话赶话，舌绕梁，\n东边的钉，西边的墙，\n绕不完的弯，唱不完的慌！\n\n[Verse 2]\n墙上一根钉，钉下绳摇晃，\n绳吊着瓶，瓶碰碎了光。\n灯骂瓶，瓶怪绳，绳怨钉，\n稀里哗啦，一场荒唐！\n\n[Chorus]\n丁丁当当，乒乓乓乓，\n话赶话，舌绕梁，\n东边的钉，西边的墙，\n绕不完的弯，唱不完的慌！\n\n[Verse 3]\n板凳宽，扁担长，\n一个偏要绑，一个偏不让。\n青龙洞里龙翻身，\n千年大梦变稻香！\n\n[Bridge]\n麻婆婆的狗，咬破麻叉口，\n麻线穿针眼，补丁也风流。\n左一句，右一句，\n舌头打结心自由！\n\n[Chorus]\n丁丁当当，乒乓乓乓，\n话赶话，舌绕梁，\n东边的钉，西边的墙，\n绕不完的弯，唱不完的慌！",
+    "audio_duration": 214.12,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": false,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.031190156936645508,
+        "diffusion": 20.130417823791504,
+        "latent2audio": 1.9650826454162598
+    },
+    "actual_seeds": [
+        1946426111
+    ],
+    "retake_seeds": [
+        331383387
+    ],
+    "retake_variance": 0.5,
+    "guidance_scale_text": 0,
+    "guidance_scale_lyric": 0,
+    "repaint_start": 0,
+    "repaint_end": 0,
+    "edit_n_min": 0.0,
+    "edit_n_max": 1.0,
+    "edit_n_avg": 1,
+    "src_audio_path": null,
+    "edit_target_prompt": null,
+    "edit_target_lyrics": null,
+    "audio2audio_enable": false,
+    "ref_audio_strength": 0.5,
+    "ref_audio_input": null,
+    "audio_path": "./outputs/output_20250512172941_0.wav"
+}

examples/zh_rap_lora/input_params/output_20250513044511_0_input_params.json

@@ -0,0 +1,45 @@
+{
+    "lora_name_or_path": "/root/sag_train/data/ace_step_v1_chinese_rap_lora_100k",
+    "task": "text2music",
+    "prompt": "东北话, spoken word, male, Tempo - Fast, Elements - Chorus Hook, Subgenre-Satirical Hip Hop, Rap, Chinese-language music, energetic, slightly nasal, Instrument - Live Bass Guitar, adult, Vocals - Syncopated Flow, Genre - Hip-Hop, rapping, bright",
+    "lyrics": "[verse]\n挣着 憋屈的 工资 还得 装乐呵\n猫着 怂样儿 还搁 朋友圈 嘚瑟\n扛着 傻逼的 指标 没人 搭把手\n这儿 不是 托儿所 少整 那出儿 哭唧尿嚎\n\n俺们 就像 一条条 老板的 裤衩子\n陪着 笑脸 接他 每一回 突突\n哎呦 老板 今儿个 穿我呗\n他 撅个腚 眼角 瞟你 那熊样\n\n[chorus]\n他们 骂我 打工仔 太多人 没睡醒\n寻思 抠搜 老板 一天天 穷折腾\n不想 俺的 人生 烂在 这嘎达\n不想 俺的 将来 折在 这破棚\n\n老子 不想 上班 老子 是外星人\n你都 把俺 骂急眼了 俺还 这么淡定\n现实 才是 梦 啥时候 能醒啊\n那 糟践人的 答案 在西北风 里飘\n\n[verse]\n瞅见 二愣子 同事 给老板 舔腚沟子\n瞅见 浪蹄子 女同事 在老板 胯骨轴 扭搭\n瞅见 白瞎的 光阴 耗在 没亮儿的 道儿\n瞅见 公交车上 一帮 僵尸 吐酸水\n\n瞅见 俺的 命 定在 苦逼的 坑里\n瞅见 俺的 爱情 被轮了 成了 老处女\n瞅见 好事儿 全归 高富帅\n还有 那些 臭不要脸 扭腚的 货色\n\n[chorus]（重复）\n他们 骂我 打工仔 太多人 没睡醒...\n\n[bridge]\n加班 没补助 俺认了\n欠薪 揍员工 把俺 当牲口\n去你妈 的小姘头\n\n[verse]\n破逼 管理制度 净整 娱乐八卦\n撸管式 管理 也就 你自己 嗨\n出点儿 屁事儿 就往 下属 脑瓜子 扣\n挣俩 钢镚儿 立马 牛逼 不分 公母\n\n你挖个 大坑 把俺们 往里 踹\n说这 叫梦想 你当年 多能耐\n俺们 就当 听传销 洗脑课\n可怜 连骗人 你都 就会 这一套\n\n[outro]\n老子 不想 上班\n老子 不想 上班\n老子 不想 上班",
+    "audio_duration": 135.92,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": false,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.06204533576965332,
+        "diffusion": 35.75483560562134,
+        "latent2audio": 1.5193355083465576
+    },
+    "actual_seeds": [
+        4176354214
+    ],
+    "retake_seeds": [
+        601086915
+    ],
+    "retake_variance": 0.5,
+    "guidance_scale_text": 0,
+    "guidance_scale_lyric": 0,
+    "repaint_start": 0,
+    "repaint_end": 0,
+    "edit_n_min": 0.0,
+    "edit_n_max": 1.0,
+    "edit_n_avg": 1,
+    "src_audio_path": null,
+    "edit_target_prompt": null,
+    "edit_target_lyrics": null,
+    "audio2audio_enable": false,
+    "ref_audio_strength": 0.5,
+    "ref_audio_input": null,
+    "audio_path": "./outputs/output_20250513044511_0.wav"
+}

examples/zh_rap_lora/input_params/output_20250513050200_0_input_params.json

@@ -0,0 +1,45 @@
+{
+    "lora_name_or_path": "/root/sag_train/data/ace_step_v1_chinese_rap_lora_100k",
+    "task": "text2music",
+    "prompt": "Rap, J-Pop, Anime, kawaii pop, EDM, Aggressive, Intense, Crisp Snare, Super Fast, Clear",
+    "lyrics": "[Intro]\nNya.\n\n[Verse]\n我 在 五 点 二 十 早 起，十 三 点 十 四 弹 会儿 琴\n习 惯 了 坐 班，习惯了 隔夜 的  剩 饭，\n习 惯 了 没有 你\n\n[Verse]\n怕 你 想 不 开，拦 在 你 的 面 前\n那 时 候 摔 得 差 点 住 院\n东 京 的 春 天 莺 莺 燕 燕\n我 说 想 不 想 来 跟 我 玩 音乐\n\n[Verse]\n带 着 我 的 朋 友 守 在 你 的 门 口\n弹 着 我 的 钢 琴 当 伴 奏\n等 你 放 学 后，陪 你   K   T   V\n端 着 我 的 红 茶 跟 你 碰 杯\n\n[Pre-Chorus]\n忽然间现实淹没了远方\n万家灯火，盖住月光\n奔走，忍受，变成了人偶\n别再对我伸出你的 双 手，会 受 伤\n\n[Chorus]\n明明都向前走，方向却渐渐不同\n时间让你我越走越近，却越来越陌生\n春 天 在 滂 沱 的 大 雨 里 飘 落\n得 了 心 太 高 脸 太 薄 的病\n\n[Bridge]\n我越难过，春日影越顶\n眼泪晃得我看不清\n埋葬了懦弱还有矫情\n却还是会在半夜摸眼睛\n\n青春期大部分时间在工 作\n用微笑换来余额几个零\n戴上了面具也明白了生活\n拼的是数字和脸更是命\n\n[Verse]\n我在五点二十早起，十三点十四弹会琴\n早上要做饭，回家时满地的瓶罐\n\n师 徒 二 人 站 在 我 的 面 前\n台 词 很 熟 练，照 着 就 念\n\n背 后 的 小 睦 扭 扭 捏 捏\n我 说 我 还 有 点 事 要 不 改 天 见\n\n然 后 你 的 双手 握 住 我 的 袖 口\n开 始 哭 着 求 我 不 要 走\n\n[Verse]\n我在下班后，忙活柴米油\n你和你的姐妹住着高楼\n\n苦 来 兮 苦，早 就 没 了\n现 实 扬 鞭，赶 着 我 向 前\n没有时间跟你分辨什么对与错\n\n[Bridge]\n没有什么对错，没有罪过\n谁不曾天真，是我太早看破\n生活一片狼藉，却又不想放弃\n一 边 聚 光 灯 下 绽 放，一 边 坠 落\n故作坚强，筑起心的墙\n越是委屈的伤口，越要藏\nLet it all out， it’s all right\n\n[Outro]\n俺 是 东 京 嘞，东 京 打 工 妹\n\n从虎之门带你转到浅草\n再从新宿转到竹桥\n\n俺 是 东 京 嘞，东 京 打 工 妹\n\n带 你 转 羽田 成田 蒲田 神田\n做 你 嘞 小 甜 甜！\n\n俺 是 东 京 嘞，东 京 打 工 妹\n带 你 转 赤 坂，带 你 转 霞 关\n恁 咋 不 早 说，今 天 不 管 饭\n",
+    "audio_duration": 147.62212,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.5,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": false,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.052134037017822266,
+        "diffusion": 17.909283876419067,
+        "latent2audio": 1.4904146194458008
+    },
+    "actual_seeds": [
+        2945962357
+    ],
+    "retake_seeds": [
+        2252292438
+    ],
+    "retake_variance": 0.5,
+    "guidance_scale_text": 0.7,
+    "guidance_scale_lyric": 0,
+    "repaint_start": 0,
+    "repaint_end": 0,
+    "edit_n_min": 0.0,
+    "edit_n_max": 1.0,
+    "edit_n_avg": 1,
+    "src_audio_path": null,
+    "edit_target_prompt": null,
+    "edit_target_lyrics": null,
+    "audio2audio_enable": false,
+    "ref_audio_strength": 0.5,
+    "ref_audio_input": null,
+    "audio_path": "./outputs/output_20250513050200_0.wav"
+}

examples/zh_rap_lora/input_params/output_20250513055451_0_input_params.json

@@ -0,0 +1,45 @@
+{
+    "lora_name_or_path": "/root/sag_train/data/ace_step_v1_chinese_rap_lora_100k",
+    "task": "text2music",
+    "prompt": "Rap, adult, male, spoken word, rapping, clear, warm, articulate, Lo-Fi Hip Hop, 100-120 BPM, Keyboard Chords, Male Rap, Lazy Rhythm, Melancholy, Rap",
+    "lyrics": "[Intro]\n夜色 很 淡 像 褪色 的 照片  \n但 记忆 却 像 刀锋 一样 锐利  \n\n[Verse 1]\n你 说过 的 甜言蜜语 现在 听来 像 最 恶毒 的 咒骂  \n你 刺进 我 心里 的 刀 现在 还 在 滴血 未 干 哪  \n慵懒 的 旋律 像 我 的 脚步 拖着 沉重 的 躯壳  \n脑海 里 循环 播放 那 画面 快 把 我 逼疯 了  \n键盘 和弦 低沉 又 忧伤 弹奏 着 我 的 绝望  \n我 曾经 的 信任 像 玻璃 一样 被 你 狠狠 地 摔 在 地上  \n不想 振作 不想 原谅 只 想 让 这 一切 都 停止  \n可 心底 有 个 声音 嘶吼 着 要 你 付出 该 有 的 代价  \n\n[Chorus]\n背叛 像 毒药 渗透 我 的 血液  \n复仇 的 火焰 在 我 眼中 燃起  \n哪怕 遍体鳞伤 哪怕 万劫不复  \n我 也 要 亲手 撕碎 你 的 幸福  \n这 是 我 的 哀歌 也 是 我 的 战书  \n键盘 的 音符 每 一下 都 带着 恨意 和 痛苦  \n\n[Verse 2]\n曾经 的 兄弟 现在 面目全非 像 个 陌生人  \n你 的 自私 像 癌细胞 一点点 吞噬 我 的 纯真  \n我 学着 你 的 样子 把 心 锁 起来 不再 轻易 相信  \n让 懒散 的 节奏 包裹 我 给 自己 一点 喘息  \n键盘 的 音色 变得 更加 阴冷 像 秋天 的 雨滴  \n冲刷 掉 所有 温情 只 剩下 彻骨 的 寒意  \n我 不会 大喊大叫 只是 默默 地 计划  \n每 一步 都 走向 让 你 后悔 的 那 一 刹那  \n\n[Chorus]\n背叛 像 毒药 渗透 我 的 血液  \n复仇 的 火焰 在 我 眼中 燃起  \n哪怕 遍体鳞伤 哪怕 万劫不复  \n我 也 要 亲手 撕碎 你 的 幸福  \n这 是 我 的 哀歌 也 是 我 的 战书  \n键盘 的 音符 每 一下 都 带着 恨意 和 痛苦  \n\n[Bridge]\n也许 复仇 不能 带来 平静  \n也许 只 会 让 我 更 堕落  \n但 如果 不 这样 做  \n我 连 活下去 的 勇气 都 没有  \n\n[Outro]\n复仇 复仇 复仇  \n直到 最后 一刻  \n懒散 地 复仇 着  ",
+    "audio_duration": 202.64,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.65,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": false,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 0.036400794982910156,
+        "diffusion": 23.055809259414673,
+        "latent2audio": 1.8787360191345215
+    },
+    "actual_seeds": [
+        3900061002
+    ],
+    "retake_seeds": [
+        3037373819
+    ],
+    "retake_variance": 0.5,
+    "guidance_scale_text": 0,
+    "guidance_scale_lyric": 0,
+    "repaint_start": 0,
+    "repaint_end": 0,
+    "edit_n_min": 0.0,
+    "edit_n_max": 1.0,
+    "edit_n_avg": 1,
+    "src_audio_path": null,
+    "edit_target_prompt": null,
+    "edit_target_lyrics": null,
+    "audio2audio_enable": false,
+    "ref_audio_strength": 0.5,
+    "ref_audio_input": null,
+    "audio_path": "./outputs/output_20250513055451_0.wav"
+}

examples/zh_rap_lora/input_params/output_20250513060150_0_input_params.json

@@ -0,0 +1,45 @@
+{
+    "lora_name_or_path": "/root/sag_train/data/ace_step_v1_chinese_rap_lora_100k",
+    "task": "text2music",
+    "prompt": "Orchestra, Symphony, Sonata, Opera, Concerto, Rap, Beat, DJ, MC, StreetCulture",
+    "lyrics": "[verse1]\n羊皮卷轴 墨香飘 莫扎特 熬 安魂曲 通宵  \n和弦齿轮 咔哒转 比 瑞士 手表 更 精密 律动  \n八轨磁带 玩叠叠乐 披头士 炸 录音棚 天花板  \nAI 卷起 新风暴 像 灭霸 打响指 般 简单  \n\n[chorus]\n琴弦 到 代码 进化论 狂飙（skr）  \n象牙塔 被 鼠标 点爆 像 泡泡（boom）  \n灵感 加 算法 等于 王炸 大招  \n人类 心跳 才是 终极 混音 调料  \n\n[verse2]\n春之祭 召唤 百人 乐团 才够 燥  \n合成器 极客 玩电焊 焊出 赛博 神庙  \nDAW 解放 双手 钢琴卷帘 变 乐高  \n音色库 开挂 像 吃 金币 的 马里奥  \n\nAI 拆解 爵士乐 黑话 像 庖丁 解牛  \nCityPop 复古 滤镜 直接 参数 调油  \n神经网络 偷师 贝多芬 半夜 翻墙头  \n音乐 基因库 被 改写成 超频 万花筒  \n\n[chorus]  \n琴弦 到 代码 进化论 狂飙（skr）  \n象牙塔 被 鼠标 点爆 像 泡泡（boom）  \n灵感 加 算法 等于 王炸 大招  \n人类 心跳 才是 终极 混音 调料  \n\n[verse3]  \n电子琴 被 吐槽 塑料 味 超标  \n卧室 制作人 用 鼠标 单挑 整个 乐团 编制  \nAI 伴奏 刚上线 就被 键盘侠 集火  \n却 忘了 电吉他 曾被 说 是 魔鬼 的 副歌  \n\n现在 我 指尖 蹦迪 在 数据 炼丹炉  \n提示词 召唤 莫扎特 跨次元 碰杯 珍珠奶茶  \n当 比特 海洋 淹没 所有 物理 琴柱  \n最后 的 音轨 永远 连着 心脏 的 跳针  \n\n[bridge]  \n鹅毛笔 蘸着 银河 当 墨汁（绝了）  \n音浪 在 元宇宙 开 分店（疯了）  \n技术 迷雾 散成 像素 烟花  \n而 我们 始终 带着 老派 的 心跳 混搭  \n\n[chorus]  \n琴弦 到 代码 进化论 狂飙（skr）  \n象牙塔 被 鼠标 点爆 像 泡泡（boom）  \n灵感 加 算法 等于 王炸 大招  \n人类 心跳 才是 终极 混音 调料  \n\n[outro]  \n从 蒸汽 到 硅基 浪潮 我 冲浪（yo）  \n用 脑洞 接住 每个 技术 暴击（叮）  \n当 所有 设备 没电 的 凌晨 三点钟  \n最 原始 的 旋律 在 胸腔 敲击 成 龙卷风  ",
+    "audio_duration": 172.64,
+    "infer_step": 60,
+    "guidance_scale": 15,
+    "scheduler_type": "euler",
+    "cfg_type": "apg",
+    "omega_scale": 10,
+    "guidance_interval": 0.65,
+    "guidance_interval_decay": 0,
+    "min_guidance_scale": 3,
+    "use_erg_tag": true,
+    "use_erg_lyric": false,
+    "use_erg_diffusion": true,
+    "oss_steps": [],
+    "timecosts": {
+        "preprocess": 3.648996353149414,
+        "diffusion": 16.44967818260193,
+        "latent2audio": 1.614703893661499
+    },
+    "actual_seeds": [
+        1198023141
+    ],
+    "retake_seeds": [
+        3389016134
+    ],
+    "retake_variance": 0.5,
+    "guidance_scale_text": 0,
+    "guidance_scale_lyric": 0,
+    "repaint_start": 0,
+    "repaint_end": 0,
+    "edit_n_min": 0.0,
+    "edit_n_max": 1.0,
+    "edit_n_avg": 1,
+    "src_audio_path": null,
+    "edit_target_prompt": null,
+    "edit_target_lyrics": null,
+    "audio2audio_enable": false,
+    "ref_audio_strength": 0.5,
+    "ref_audio_input": null,
+    "audio_path": "./outputs/output_20250513060150_0.wav"
+}