https://stability.ai/research/stable-audio-efficient-timing-latent-diffusion
Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion — Stability AI
Stable Audio represents the cutting-edge audio generation research by Stability AI’s generative audio research lab, Harmonai. We continue to improve our model architectures, datasets, and training procedures to improve output quality, controllability, in
stability.ai
To train our flagship Stable Audio model, we used a dataset consisting of over 800,000 audio files containing music, sound effects, and single-instrument stems, as well as corresponding text metadata, provided through a deal with stock music provider AudioSparx. This dataset adds up to over 19,500 hours of audio.
차후에 오픈소스로 공개 한답니다.
'AI > Music' 카테고리의 다른 글
| MAGNeT (0) | 2024.01.21 |
|---|---|
| deepmind_DreamTrack_Music AI Tools (0) | 2023.11.20 |
| AudioCraft: Generative AI for audio made simple and available to all (0) | 2023.08.10 |
| 작곡 (0) | 2023.06.05 |
| TTS (0) | 2023.05.01 |
댓글