🤣

Definitely appreciate the support we received to scale up udio!

Definitely did not intend to create a standup comedy model!

folks

you've been making some great tracks

here's a gorgeous sample from user Inever

keep up the good work 🫡

Check out my new startup, a music making app for everyone. And I mean everyone! Thrilled to see this finally in the open. What a wild ride!

Wouldn't be possible without the amazing co-founders Charlie Nash, Conor Durkan, Andrew Sanchez and David Ding and all the…

Excited to share Udio, a music generation app.

I co-founded Udio with the brilliant Yaroslav Ganin Conor Durkan David Ding Andrew Sanchez

Thanks to them and to all our supporters. Let's make some music!

Thrilled to announce udio. Amazing group of people have brought this to life: David Ding Conor Durkan Charlie Nash Yaroslav Ganin

Choral music has been a constant source of joy in my life, and here is a particular favorite created on udio.

Will has been giving us amazing feedback, and we look forward to continued collaboration with him to make this a top-tier tool for artists and producers!

Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs

paper page: huggingface.co/papers/2401.11…

Diffusion models have exhibit exceptional performance in text-to-image generation and editing. However, existing methods often face challenges when…

Our take on text-to-image generation is finally out after quite some time in the making (and a healthy amount of YOLOing). It was so much fun to work on alongside amazing colleagues at Google DeepMind
🖇️ dpmd.ai/x-imagen2 (be sure to check out style conditioning 🤖)

I’m so happy to finally see this out. That model is insanely good, and what’s shown here only scratches the surface!

#Lyria is in production and can already used by selected creators on YT Shorts. You can find samples here:
youtube.com/hashtag/dreamt…

Excited that this is out! When Kazuya and I started training the first versions of this model last year, we had no idea that it would turn out this good, the progress that the team has made in the last year was incredible. Thanks Aäron van den Oord for being a fantastic team lead!

I'm speechless.

Not peer-reviewed yet but a submitted paper.

The 'presented images' were shown to a group of humans. The 'reconstructed images' were the result of an fMRI output to Stable Diffusion.

In other words, #stablediffusion literally read people's minds.

Source 👇