Neural networks and neuro basses https://teapawt.org/t.co/PtyPP6Qopv
NL
Joined March 2011
- Tweets2.2K
- Following1.1K
- Followers1K
- Likes19.1K
Pinned Tweet
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: wavefunk.xyz/audio-reactive-…
Paper: wavefunk.xyz/assets/audio-re…
Code: github.com/JCBrouwer/maua-st…
Video:
hans retweeted
i swear i yeard this one hears ago. retrocausal recursive manifestation innit. tangled in the machine
hans retweeted
.@advadnoun was talking about BigBiGAN recently, and it reminded me of all my video work in 2020 where I would feed full videos into @runwayml. So on Saturday I had Astra bring it back for me (all runs locally, and its so much faster than it was 6 years ago).
hans retweeted
and here’s @mxsage’s lovely “36 points” running on this 60hz eink panel with the @Modostech glider driver board
hans retweeted
trained my own with trl + openenv
blog with open artifacts (code, models, dataset, rl env...) soon!
hans retweeted
@MiniMax_AI H3 model is some of the most fun iv had in a long time in diffusion. Open source Has been stale for video for so long. This allows people to make some seriously impressive stuff.
This is a single render, 1088x1920. I built a custom prompt scheduling system that allows me to schedule conditioning (prompts) to cut in and out as i please.
So naturally i made it beat synced to t
he song. There is zero editing done to this video
Gave flux3 a try this morning. This was an idea that had been bouncing around my head for a while but that I hadn't been able to convince a video model to do for me yet. Excited to meet some people at the @bfl_ai @NousResearch thing later!
🤖 Made with AI
hans retweeted
Our Red Rocks performance is premiering live in 10 minutes!
youtu.be/_sx3Rj1IXQE
hans retweeted
playing around with audio reactivity in sentinel
running audio straight into the gpu buffer let opus 5 create this entire beat detection technique + interface as an interactive shader. sdxl streamdiff images are generated, depth mapped, cut out and spawned in real time
hans retweeted
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.
hans retweeted
@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: lnkd.in/gQ-S9cF3).
#DellProPrecision #DellTech #NVIDIA