Vegard Danger Whatofit Myklebust

Make stupid food, serve it on a skateboard, and impress your friends by drawing in your coffee. #HipsterCafe youtube.com/watch?v=yxcOAI…

@fofrAI I tried it and hit a level of control ceiling within 1 hour.

4o native image generation is the beginning. It's a seismic change in generative AI. Where is this all going? We won't need ipadapters, or controlnets, or loras, or comfy workflows, or face landmark models, or segmentation models, or niche task specific models. It'll be one model to rule them all. You'll only need a prompt, perhaps a reference, and your imagination. It's only going to get better, and it will apply to more and more mediums – audio and video are next. And it'll happen soon.

Excerpt from a video I just posted on YouTube (about the multilayer perception layers in a transformer, and how LLMs may store facts).

New episode of coding adventures: exploring sound and the discrete Fourier transform! youtu.be/iA6wRgwl7k0 Many thanks to @3blue1brown for the great videos on the subject, which helped me to wrap my head around it.

Boost your inner chi alongside the star of the Kung Fu Panda franchise, Po, voiced by @jackblack Created by Nexus Studios, @UniversalPics & @Dreamworks , with animation led by Oscar-winning director @PatrickTOsborne Available on Apple Vision Pro. nexusstudios.com/work/school-of…

@git_fork Can I please please have these quality of life buttons on this part of the UI when merging a different branch into mine.

💥CANNES GRAND PRIX WINNER 💥 Adoptable, our collaboration with #Pedigree and @ColensoBBDO picked up the top prize for Outdoor. Check out this AI for social good campaign (featuring cute dogs) here. nexusstudios.com/work/pedigree-…

@8Infinite8 Amazing quality!

We're proud to showcase some recent real-time work with 3D / 4D Gaussian splatting. In January of 2024 we acquired a full 3DGS commercial license with Inria to allow us to offer 4DGS services to clients around the world. We've spent the last 10 months developing our custom 4DGS software pipeline, utilizing our own Nvidia GPU cluster to batch process 100,000's of 4DGS frames rapidly, combined with our state-of-the-art custom built volumetric capture system(s). We can capture anything from complex character interactions for visual effects shots, or dynamic fast fighting scenes, sports, acting, even capturing and storing memories of family and friends for the future! The possibilities are endless. Our focus is always on high-quality and high-fidelity. We don't cut corners and we're continually striving to learn and improve. The below video showcases some 6-dof spatial captures we took of @henrypearce4D's family. These scenes are played back in real-time @ 30fps inside a 3rd party engine running in a 120fps virtual environment. This is a culmination of years of hard work and dedication and we are keen to commercialize this technology with you. Please do reach out if you're interested in our capture systems or our 3D/4DGS processing services. HQ YouTube Link: youtu.be/NudQHBrkqhY HQ Vimeo Link: vimeo.com/936993124 #spatialcapture #vr #virtualmemories #inria #3dgs #4dgs #aeonx #ir #ximea Music "Vision" by megiddo music Special thanks to @aras_p

Another lovely Coding Adventure by @SebastianLague I'm not sure why, but listening to Sebastian debug frustrating floating point errors somehow soothes the pain of my own debugging. youtube.com/watch?v=SO83KQ…

We had an amazing opportunity to use bleeding edge AI technology for good: Helping dogs get adopted. marketing-beat.co.uk/2024/04/12/ped…

Always amazed at how good Grant's videos are at breaking down and clearly explaining subjects in a way that lets the viewer establish intuition about how to think about them.

@FreyaHolmer Try making the text readout for t as well as the line and handle around 40% thiccer/taller for the t line than the others, that should overpower the natural top left reading order so it comes first. Maybe fade the other colour saturations a bit too

this message isn't going to reach the target audience but man I wish people would read threads oh my lord lol

I have a UX puzzle I want users to interact with the green t slider, but I can't put it above the b/a knobs, because on mobile your thumb would be in the way of the middle dot I also want users to be able to change b and a, but I want to discourage them from doing so first

⚡Headspace XR is here ⚡ An immersive playground for the mind, #HeadspaceXR is a first-of-its-kind XR Product for @MetaQuestVR, where users can move, play, meditate, and explore the vast open world with friends. By Nexus Studios, @Headspace & @Meta nexusstudios.com/work/headspace…

Here's a showcase video of the shapes we have developed so far for the 'Shader Functions for Technical Artists' book. Hope you like it 🙂First two chapters will be available this month. Subscribe if you are interested! ⭐️jettelly.com/books/visualiz… #indiedev #gamedev #madewithunity #procedural #shader #ゲーム制作 #インディーゲーム #3dart

Many of you have asked about how we achieve our 2.5D art style. Here's our process, step-by-step. Shout out to @DanFessler our Chief Creative Officer for recording this clip. #digitalillustration #gameart #gamedev

A first demonstration of Cellular Automata GI in 3D. The different injection phases are shown in the video. Sunlight and Skylight are propagated and injected with pure CA too!

Coming exclusively to Meta Quest 3 - Headspace XR. Your mind's virtual playground so you can relax, move, play, explore and adventure with your friends.

This is getting out of hand! - Will Smith

Working on a Cellular Automata model that solves multi-bounce Global Illumination. It's fast, integer based and fully GPU parallelizable!

And now a fast-to-compile version of the volumetric path tracing ShaderToy with a Cloudy Bunny shadertoy.com/view/7dVGWR