---
title: emsong
canonical_url: "https://www.modelscope.ai/models/DeterminantMatrix/emsong"
md_url: "https://www.modelscope.ai/models/DeterminantMatrix/emsong.md"
repository: DeterminantMatrix/emsong
last_updated: 2026-09-26
license: "Apache License 2.0"
base_model:
  - ACE-Step/acestep-v15-xl-sft
base_model_relation: adapter
parameters: 159.4M
tensor_type:
  - BF16
library_name:
  - pytorch
  - lora
  - safetensors
supports_inference: txt2audio
downloads: 131
stars: 0
tags:
  - LoRA
  - text-to-audio
---

# emsong

> emsong - An open-source model by DeterminantMatrix on ModelScope. This model is trained using the Civision/model training environment and computing resources provided by ModelScope.

DeterminantMatrix/emsong is a 159.4M-parameter machine learning model on ModelScope. licensed under Apache License 2.0. derived from ACE-Step/acestep-v15-xl-sft. and supports online inference (txt2audio).

- **Repository**: DeterminantMatrix/emsong
- **License**: Apache License 2.0
- **Parameters**: 159.4M
- **Base model**: ACE-Step/acestep-v15-xl-sft
- **Online inference**: txt2audio
- **Tags**: LoRA, text-to-audio
- **Downloads**: 131
- **Stars**: 0
- **Last updated**: 2026-09-26

Source: https://www.modelscope.ai/models/DeterminantMatrix/emsong

---

# 

## Model Introduction

This model is trained using the [Civision/model training](https://modelscope.ai/civision/modelTraining) environment and computing resources provided by ModelScope.

* Model Type: LoRA
* Base Model: [ACE-Step/acestep-v15-xl-sft](https://modelscope.ai/models/ACE-Step/acestep-v15-xl-sft)
* Training Code: [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
* Data amount：4
* Total training steps：4000
* License: Apache-2.0

## Inference Code

Install [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio):

```bash
pip install diffsynth
```

Inference:

```python
from diffsynth.pipelines.ace_step import AceStepPipeline, ModelConfig
from diffsynth.utils.data.audio import save_audio
import torch

pipe = AceStepPipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="ACE-Step/acestep-v15-xl-sft", origin_file_pattern="model-*.safetensors"),
        ModelConfig(model_id="ACE-Step/Ace-Step1.5", origin_file_pattern="Qwen3-Embedding-0.6B/model.safetensors"),
        ModelConfig(model_id="ACE-Step/Ace-Step1.5", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
    ],
    text_tokenizer_config=ModelConfig(model_id="ACE-Step/Ace-Step1.5", origin_file_pattern="Qwen3-Embedding-0.6B/"),
    silence_latent_config=ModelConfig(model_id="ACE-Step/Ace-Step1.5", origin_file_pattern="acestep-v15-turbo/silence_latent.pt"),
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="DeterminantMatrix/emsong", origin_file_pattern="emsong_c1-st4000.safetensors"))

prompt = "An explosive, high-energy pop-rock track with a strong anime theme song feel."
lyrics = "I Love you. Forever. I Love you. Forever."
audio = pipe(
    prompt=prompt,
    lyrics=lyrics,
    duration=160,
    bpm=100,
    keyscale="B minor",
    timesignature="4",
    vocal_language="zh",
    seed=1,
    num_inference_steps=50,
    cfg_scale=4.0,
)
save_audio(audio, pipe.vae.sampling_rate, "music.wav")
```