Merge branch 'main' of github.com:ace-step/ACE-Step

This commit is contained in:
Sayo
2025-05-06 20:24:52 +08:00
2 changed files with 17 additions and 8 deletions
+11 -4
View File
@@ -194,7 +194,7 @@ It is highly recommended to use a virtual environment to manage project dependen
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu126 pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu126
# then install other dependencies # then install other dependencies
pip install -r requirements_win.txt pip install -r requirements.txt
``` ```
## 🚀 Usage ## 🚀 Usage
@@ -338,9 +338,16 @@ Example LoRA configuration file (lora_config.json):
{ {
"r": 16, "r": 16,
"lora_alpha": 32, "lora_alpha": 32,
"target_modules": ["q_proj", "k_proj", "v_proj", "out_proj"], "target_modules": [
"lora_dropout": 0.05, "speaker_embedder",
"bias": "none" "linear_q",
"linear_k",
"linear_v",
"to_q",
"to_k",
"to_v",
"to_out.0"
]
} }
``` ```
+6 -4
View File
@@ -2,8 +2,8 @@ import gradio as gr
import librosa import librosa
TAG_PLACEHOLDER = "funk, pop, soul, rock, melodic, guitar, drums, bass, keyboard, percussion, 105 BPM, energetic, upbeat, groovy, vibrant, dynamic" TAG_DEFAULT = "funk, pop, soul, rock, melodic, guitar, drums, bass, keyboard, percussion, 105 BPM, energetic, upbeat, groovy, vibrant, dynamic"
LYRIC_PLACEHOLDER = """[verse] LYRIC_DEFAULT = """[verse]
Neon lights they flicker bright Neon lights they flicker bright
City hums in dead of night City hums in dead of night
Rhythms pulse through concrete veins Rhythms pulse through concrete veins
@@ -41,6 +41,8 @@ In this moment we take flight
""" """
def create_output_ui(task_name="Text2Music"): def create_output_ui(task_name="Text2Music"):
# For many consumer-grade GPU devices, only one batch can be run # For many consumer-grade GPU devices, only one batch can be run
output_audio1 = gr.Audio(type="filepath", label=f"{task_name} Generated Audio 1") output_audio1 = gr.Audio(type="filepath", label=f"{task_name} Generated Audio 1")
@@ -69,8 +71,8 @@ def create_text2music_ui(
audio_duration = gr.Slider(-1, 240.0, step=0.00001, value=-1, label="Audio Duration", interactive=True, info="-1 means random duration (30 ~ 240).", scale=9) audio_duration = gr.Slider(-1, 240.0, step=0.00001, value=-1, label="Audio Duration", interactive=True, info="-1 means random duration (30 ~ 240).", scale=9)
sample_bnt = gr.Button("Sample", variant="primary", scale=1) sample_bnt = gr.Button("Sample", variant="primary", scale=1)
prompt = gr.Textbox(lines=2, label="Tags", max_lines=4, placeholder=TAG_PLACEHOLDER, info="Support tags, descriptions, and scene. Use commas to separate different tags.\ntags and lyrics examples are from ai music generation community") prompt = gr.Textbox(lines=2, label="Tags", max_lines=4, value=TAG_DEFAULT, info="Support tags, descriptions, and scene. Use commas to separate different tags.\ntags and lyrics examples are from ai music generation community")
lyrics = gr.Textbox(lines=9, label="Lyrics", max_lines=13, placeholder=LYRIC_PLACEHOLDER, info="Support lyric structure tags like [verse], [chorus], and [bridge] to separate different parts of the lyrics.\nUse [instrumental] or [inst] to generate instrumental music. Not support genre structure tag in lyrics") lyrics = gr.Textbox(lines=9, label="Lyrics", max_lines=13, value=LYRIC_DEFAULT, info="Support lyric structure tags like [verse], [chorus], and [bridge] to separate different parts of the lyrics.\nUse [instrumental] or [inst] to generate instrumental music. Not support genre structure tag in lyrics")
with gr.Accordion("Basic Settings", open=False): with gr.Accordion("Basic Settings", open=False):
infer_step = gr.Slider(minimum=1, maximum=1000, step=1, value=27, label="Infer Steps", interactive=True) infer_step = gr.Slider(minimum=1, maximum=1000, step=1, value=27, label="Infer Steps", interactive=True)