MusicGen
About
A model designed for conditional music generation using a single-stage transformer that produces high-quality audio. It accepts text or melodic guides, offering flexible controls. Advanced techniques such as melody-guided generation and diffusion-based enhancements improve coherence and authenticity in stereophonic formats while efficiently managing long-term structures.
Percs
High-Quality Music
Text-to-Music
Melody-Guided
Stereo Support
Settings
BPM- Beats Per Minute. Set the tempo of a generation
Track duration- The duration of a generation
Model version- Different models make different sound.
Normalization Strategy- Strategy for normalizing audio
Temperature- Controls the 'conservativeness' of the sampling process. Higher temperature means more diversity.
Top K- Reduces sampling to the k most likely tokens.
Top P- Reduces sampling to tokens with cumulative probability of p. When set to `0` (default), top_k sampling is used.
Classifier Free Guidance- Increases the influence of inputs on the output. Higher values produce lower-varience outputs that adhere more closely to inputs.