DeepMind Blog
We’re launching Lyria 3.5 in Google Flow Music, with advances across musicality, lyrics, vocals, and creative control
Read the original on DeepMind Blog →The Flow has not summarised this story yet — read it at DeepMind Blog.
Related stories
DeepMind Blog
Mar 25
Lyria 3 Pro: Create longer tracks in more
Introducing Lyria 3 Pro, which unlocks longer tracks with structural awareness. We’re also bringing Lyria to more Google products and surfaces.
DeepMind Blog
Feb 18
A new way to express yourself: Gemini can now create music
The Gemini app now features our most advanced music generation model Lyria 3, empowering anyone to make 30-second tracks using text or images.
arXiv AI
Jun 30
LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training
arXiv:2606. 30642v1 Announce Type: cross Abstract: Full-length song generation must preserve coherence and musicality, render detailed vocal and accompaniment acoustics, and follow lyrics and prompts.
OpenAI Blog
Apr 30, 2020
Jukebox
We’re introducing Jukebox, a neural net that generates music, including rudimentary singing, as raw audio in a variety of genres and artist styles. We’re releasing the model weights and code, along with a tool to explore the generated samples.
Hugging Face Trending Papers
Jun 25
DanceDuo: Bridging Human Movement and AI Choreography
In recent years, advancements in deep learning and generative models have revolutionized music-driven dance generation. This paper introduces a novel platform, namely DanceDuo, leveraging diffusion models to generate AI-choreographed dance sequences synchronized with a variety of music genres, to encourage dancing practice.
arXiv Machine Learning
Jun 11
PianoKontext: Expressive Performance Rendering from Deadpan Context
arXiv:2606. 12282v1 Announce Type: cross Abstract: Expressive performance rendering (EPR) aims to generate realistic performances constrained on sequences of notes.