🎵 ACE-Step 1.5 Custom Edition
Three powerful interfaces for music generation and training
Models will download automatically on first use (~7GB from HuggingFace)
Full-featured standard ACE-Step 1.5 interface
10 240
Style
0.1 1.5
0.1 1
Audio Input (Optional)
Upload audio file or record to use as style guidance
Generated Output
Advanced Controls
0.1 1
Custom Timeline-based Generation
Generate 32-second clips that seamlessly blend together on a master timeline.
How far back to reference for style guidance
0 120
Style
0.5 1
Train Custom LoRA Models
Upload audio files to train specialized models for voice cloning, style adaptation, etc.
1. Upload Training Data
2. Training Configuration
1 16
1 100
4 128
4 128
Training Tips
- Upload 10+ audio samples for best results
- Keep samples consistent in style/quality
- Higher rank = more capacity but slower training
- Start with 10-20 epochs and adjust
- Use existing LoRA to continue training
About
ACE-Step 1.5 Custom Edition by Gamahea | Based on ACE-Step