@LinusEkenstam There is a reason:
If you kern the (rapidly accelerating) numbers, the 2 would be jumping left and right on every value change, and will make the entire numerical block -feel- very messy.
@MacRumors so, uh, NO GOOD DRAWING on iPhone Duo.
Everything that makes drawing magical on iPad (Procreate etc) is pressure sensitivity, which isn't in this model.
@Aurelien_Gz I've spent the last 15 years or so making vision-films and similar assets for various brands and products as an animation/vfx process.
Love these Microsoft films, there's a few others.
Depth-aware light injection in TypeGPU
I got a 448x448 monocular depth model down to ~8 ms on my M4 Pro across ~250 dispatches, which is fast enough to use in realtime :D
Since the inference is written directly in TypeGPU, I can just feed the depth buffer straight into the lighting pass. It never has to leave the GPU or go through any extra synchronization/interop step
Inference, lighting and draw all go through the same command encoder.
Tomorrow I'll be sharing my favorite chat codes for building strong creative client relationships.
Habits, processes, and some specific phrases that change the dynamic from "vendor" to trusted partner.
RSVP to join ⬇️
https://t.co/yDBbPn6lmJ
God’s Eye View V1 is open source. It feels like a spy simulator in your browser -- except the underlying data is real, and you can talk to the planet too.
Track planes, ships, satellites, traffic cameras, and critical infrastructure. Use voice mode to ask what’s happening, annotate the 3D world, or jump into a plane’s cockpit.
Already a ton to explore. Code is MIT licensed, so add new layers, extend the voice agent, break things, and show me what you cook.
LOVED the new Spider-Man.
Handshake gave me the feels.
After seeing the Homecoming rough-cut in 2016/17, @Dougasaurus and I loved the Peter/Ned handshake so much that we learned it, and traced it for the title sequence.