YuE-s2-1B-general
| Property | Value |
|---|---|
| License | Apache 2.0 |
| Authors | HKUST/M-A-P |
| Release Date | January 2025 |
| Model Size | 1B parameters |
What is YuE-s2-1B-general?
YuE-s2-1B-general is part of the groundbreaking YuE series of foundation models specifically designed for music generation. The name YuE (乐) means "music" and "happiness" in Chinese. This 1B parameter model specializes in lyrics-to-song generation, capable of creating complete songs with both vocal and accompaniment tracks.
Implementation Details
The model is implemented as a foundation model for music generation, utilizing advanced AI techniques to transform written lyrics into fully realized musical compositions. It's designed with multi-lingual and multi-genre capabilities, making it versatile for various musical applications.
- Complete song generation capability
- Multi-minute song output support
- Integrated vocal and accompaniment generation
- Multi-language support including English, Japanese, Korean, and Chinese
- Various genre capabilities including Pop and Metal
Core Capabilities
- Lyrics to complete song transformation
- Multiple genre support with demonstrated capabilities in Pop and Metal
- Multi-language vocal generation
- Extended duration music generation
- Combined vocal and instrumental track creation
Frequently Asked Questions
Q: What makes this model unique?
YuE-s2-1B-general stands out for its ability to generate complete songs from lyrics, including both vocals and accompaniment, while supporting multiple languages and genres. It's also notable for being released under the Apache 2.0 license, allowing for commercial use with attribution.
Q: What are the recommended use cases?
The model is ideal for artists and content creators looking to generate complete songs from lyrics, create musical content across different genres, and develop multi-lingual musical projects. It's suitable for both personal and commercial use, with proper attribution.
