Adam Roberts
@ada_rob
ai researcher & engineer @ Google DeepMind :: ♫ Co-lead Magenta & Lyria :: 📝 Foundational LLM work: TL for T5 & C4, core PaLM :: 👨💻 TL for T5x & SeqIO
Introducing Magenta RealTime, our open weights live music model! Like Lyria RealTime, this model provides the user continuous control of the musical flow 🌊. We will be sharing some of our favorite ways to extend these models over the next few weeks. Can't wait to see what you…
Excited to announce 🎵Magenta RealTime, the first open weights music generation model capable of real-time audio generation with real-time control. 👋 **Try Magenta RT on Colab TPUs**: colab.research.google.com/github/magenta… 👀 Blog post: g.co/magenta/rt 🧵 below
I'm enjoying Google's new AI Music VST... it's a great antidote to the "two song" approach taken by Suno and Udio. The interface puts me in a flow state, like fishing in a stream, more than "crate digging" per se. Outputs here reminded me of "Lemon of Pink" @jesseengel
One of my favorite use cases for our new Lyria RealTime plug-in "Infinite Crate" is live jamming. While it can't listen to you (yet), it can act as a partner for improvisation, helping inspire new musical ideas. Here is @sidecartommy experimenting with it during early testing.…
New VST/AU Plugin! 🚨 Play with Lyria RealTime directly from inside your favorite DAW with “The Infinite Crate” 🎧🎶 Like other Lyria RT demos, you can mix together text prompts and other controls to steer the model in real-time. But now with a VST plugin you can feed audio…
Btw as an aside, we didn’t announce on Friday because we respected the IMO Board's original request that all AI labs share their results only after the official results had been verified by independent experts & the students had rightly received the acclamation they deserved
✨ made a realtime bhangra (punjabi folk music) × techno/breakcore fusion using @googlemagenta 's lyria vst plugin in ableton. the mix constantly shifts live between genres, visualized as a sliding gradient bar 📶
Cool to see a hackathon on live coding with Lyria RealTime in Jakarta ❤️
Livecode/ai music workshop in Jakarta, Indonesia. July 27. Won't be there but looks fire!! instagram.com/p/DL_wNxWSZ1U/
Really neat how @dev_valladares used Lyria to generate the music using images from the film. 🖼️🎵 x.com/dev_valladares…
To generate the soundtrack I used my Image Radio tool (built atop Google Lyria) to oneshot a 6-minute track based on 4 screenshots x.com/dev_valladares…
To generate the soundtrack I used my Image Radio tool (built atop Google Lyria) to oneshot a 6-minute track based on 4 screenshots x.com/dev_valladares…
𝙸𝙼𝙰𝙶𝙴 𝚁𝙰𝙳𝙸𝙾 🖼️📻 Tune into any image in the world 🎷🔊 Day 4/30 of experiments with Gemini. Created using Google's Lyria RealTime on AI Studio → 🧵
Really excited to see the return of open weights encoder-decoder models! It's amazing how often I still see T5 variants creating immense value at Google, and I'm sure we're not the only ones.
Introducing T5Gemma: the next generation of encoder-decoder/T5 models! 🔧Decoder models adapted to be encoder-decoder 🔥32 models with different combinations 🤗Available in Hugging Face and Kaggle developers.googleblog.com/en/t5gemma
New VST/AU Plugin! 🚨 Play with Lyria RealTime directly from inside your favorite DAW with “The Infinite Crate” 🎧🎶 Like other Lyria RT demos, you can mix together text prompts and other controls to steer the model in real-time. But now with a VST plugin you can feed audio…
Jam Along 🎸🥁: Create dynamic backing tracks that are different every time, varying and evolving as you play on top.
Lots of people think AGI is going to give us the answers to solve all sorts of problems we have created for ourselves: inequality, climate change, ecosystem collapse. What if it just says "stop cutting taxes for the rich and accelerate the adoption of renewable energy you…
New features to try with MagentaRT. More to come!
Show don't tell... Magenta RealTime now supports audio prompting in addition to text prompting, so you can now use clips of audio as latent anchors to steer generation. youtu.be/vHIf2UKXmp4?si…
Show don't tell... Magenta RealTime now supports audio prompting in addition to text prompting, so you can now use clips of audio as latent anchors to steer generation. youtu.be/vHIf2UKXmp4?si…
P5.js is such a fun way to prototype new creative experiences, so I ported the "Genre Pad" using Lyria Realtime over to run in the P5.js web editor. Please fork and hack as you will 🎶♥️
such a joy to play with... g.co/magenta/prompt… (psychedelic djembe ftw)
sunday magenta-realtime latent jockey session with frens 🎶 hooked the newest magenta-realtime music model from @GoogleDeepMind to a MIDI controller 🎹, built a custom front-end for it sound on 🔊
I’m particularly excited about this as it’s the only open model that enables streaming audio generation with real-time controls creating what feels like a genuinely new paradigm that is both fun and musically inspiring.
𝙸𝙼𝙰𝙶𝙴 𝚁𝙰𝙳𝙸𝙾 🖼️📻 Tune into any image in the world 🎷🔊 Day 4/30 of experiments with Gemini. Created using Google's Lyria RealTime on AI Studio → 🧵