hans

Verified account

@wavefunk_

Neural networks and neuro basses

NL

Joined March 2011

1.1K Following

1K Followers

2.2K Posts

Pinned Tweet

over 5 years ago

I'm excited to say my paper, Audio-reactive Latent Interpolations with StyleGAN, has been accepted to the Workshop on Machine Learning for Creativity & Design @ NeurIPS 2020! Blog: https://t.co/YTxGg4B4rM Paper: https://t.co/fsPQjqxRfM Code: https://t.co/Fa2MRFJ0TO Video:

7

181

23

22

0

wavefunk_ retweeted

about 2 months ago

Jamming with @cerspense on Sentinel. Built a 3D scene of points and lines, fed it through SDXL to turn it into jellyfish, layered a particle ripple system on top, finished with film grain. Everything vibe coded with Claude in real time. We described what we wanted as we listened to the music and just watched it come together.

0

26

6

5

1K

about 2 months ago

@kettukaa @dnbt777 Wrote it up in more detail here https://t.co/YTxGg4B4rM

0

1

0

0

10

about 2 months ago

@kettukaa @dnbt777 Yeah, I looked at a lot of higher-level spectral/musical features (onset envelopes, chromagrams, etc) and tried to map as many of those as possible to the different bits of styleGAN as I could

1

1

0

0

18

Who to follow

Nerdy Rodent 🐀🤓💻🪐🚴

Verified account

Does stuff with AI. Likes rodents and Open Source. See my YouTube channel for AI tutorials & fun since 2020 :)

Surfing on sound, music, AI, and waves 🏄 / Founder of @qosmo_inc & @neutone_ai / @naotokui in 🇯🇵

Alex Mordvintsev

Verified account

Mad Scientist, DeepDream creator. Designing Self-Organising Systems and Programmable Artificial Life. https://t.co/rntipHzHW3

2 months ago

@Ji_Ha_Kim @nhigham there's almost surely a "what is" post about this, but reverse lookup is hard haha

0

0

0

0

261

2 months ago

@ErwannMillon @torchcompiled Does torch.compile do these kinds of horizontal fusions? It is indeed just a specific form of grouped mm

0

0

0

0

57

3 months ago

@SkopeUK YESSS!

0

0

0

0

20

wavefunk_ retweeted

3 months ago

@cerspense has been developing a tool (Sentinel) that allows live diffusion. I have been playing with it in conjunction with TouchDesigner (for audio reactivity) and my Teenage Engineering OP-XY (for additional effects trigger). Being able to make animations on the fly based on a song feels like playing an instrument that makes visuals instead of sounds. It is awesome! This has been made possible thanks to my Dell Pro Max T2 tower equipped with an NVIDIA RTX PRO GPU (you can check out the spec here: https://t.co/w5xWEcaOun). #DellProPrecision #DellTech #NVIDIA

6

59

6

26

2K

3 months ago

0

1

0

0

42

3 months ago

Less subway map, more star wars...

3 months ago

0

0

0

0

139

0

1

0

0

91

3 months ago

0

1

0

0

45

3 months ago

0

0

0

0

42

3 months ago

0

1

0

0

57

3 months ago

0

1

0

0

56

3 months ago

0

0

0

0

139

3 months ago

Upcycling some old finetuned RuDALL-E generations with LTX-2

0

0

0

0

74

3 months ago

wavefunk_'s tweet photo. https://t.co/bWjokLw9W3

0

0

0

0

27

3 months ago

Some autoregressive image generation from the hard drive archive I think it's either a finetuned RuDALL-E or CogView

wavefunk_'s tweet photo. Some autoregressive image generation from the hard drive archive

I think it's either a finetuned RuDALL-E or CogView https://t.co/ePuZ0JG33K

1

1

0

0

115

3 months ago

Love letters from latent space

wavefunk_'s tweet photo. Love letters from latent space https://t.co/c2y81b8BeG

1

1

0

1

47

3 months ago

@thomasmassena Very nice! Just fyi, some of your plots are pretty hard to read on mobile.

wavefunk_'s tweet photo. @thomasmassena Very nice!

Just fyi, some of your plots are pretty hard to read on mobile. https://t.co/htvOla5uOM

2

1

0

0

106

Last Seen Users on Sotwe

Trends for you

Most Popular Users