ACEStepOptions

Options & Configuration ยท AiDotNet.Audio.Generation

Configuration options for the ACE-Step model.

Inheritance: ModelOptions โ†’ ACEStepOptions

For Beginners

ACE-Step generates music from text descriptions super fast. While most AI music generators need many steps (like painting layer by layer), ACE-Step can create music in just 1-4 steps, making it fast enough for real-time use.

How It Works

ACE-Step (2024) is an Accelerated Consistency-Enhanced music generation model that uses consistency training to generate high-quality music in very few diffusion steps (1-4 steps vs 50-100 for standard diffusion). It achieves real-time music generation while maintaining quality comparable to multi-step models.

Constructors

Constructor Summary
ACEStepOptions()

Properties

Property Summary
OnnxModelOptions OnnxOptions { get; set; } Gets or sets the ONNX runtime options.
double DropoutRate { get; set; } Gets or sets the dropout rate.
double LearningRate { get; set; } Gets or sets the learning rate.
int LatentDim { get; set; } Gets or sets the latent dimension.
int NumChannels { get; set; } Gets or sets the number of output channels.
int NumSteps { get; set; } Gets or sets the number of inference steps.
int NumUNetLayers { get; set; } Gets or sets the number of U-Net layers.
int SampleRate { get; set; } Gets or sets the output sample rate in Hz.
int TextEncoderDim { get; set; } Gets or sets the text encoder dimension.
int UNetDim { get; set; } Gets or sets the U-Net hidden dimension.
string ModelPath { get; set; } Gets or sets the path to the ONNX model file.
string Variant { get; set; } Gets or sets the model variant.