Patmacs (@patmacs_) 's Twitter Profile
Patmacs

@patmacs_

20+ years of dev. Learn, Adapt, Adopt, Teach, Repeat. Among a short list of people keeping track of all of the technologies at once
discord.gg/gnkBG6rUS

ID: 112472217

calendar_today08-02-2010 16:35:13

2,2K Tweet

333 Takipçi

1,1K Takip Edilen

Emily (@iamemily2050) 's Twitter Profile Photo

Veo3 fast { "shot": { "composition": "High-angle wide shot, 35mm lens, shot on ARRI Alexa Mini, deep depth of field for full skyline detail", "camera_motion": "slow drone orbit around the top corner of the skyscraper, gradually pushing in to emphasize scale and

Bilawal Sidhu (@bilawalsidhu) 's Twitter Profile Photo

SceneScript treats 3D reconstruction as a language problem rather than a geometry one. The model watches a video of a room and just learns to write a script for it. It autoregressively spits out text commands like make_wall(...) or make_bbox(...) that define the scene.

CoffeeVectors (@coffeevectors) 's Twitter Profile Photo

First try making a continuous walk and talk by combining 3 videos. // Midjourney -> Veo 3 -> Premiere Pro I’ve switched to using JSON prompts in Veo 3 because it’s more organized, tho sometimes trad prompts help fix issues. Sample prompt below.

Bilawal Sidhu (@bilawalsidhu) 's Twitter Profile Photo

Combining the explicit control of 3D software with the creativity of generative AI models is a promising yet underrated workflow. Build your 3D scenes procedurally by describing them in natural language, then take them all the way with your image & video models of choice. Tools

Asad (@asadalishahid) 's Twitter Profile Photo

🎶Can a robot learn to play music? YES! — by teaching itself, one beat at a time 🎼 🥁Introducing Robot Drummer: Learning Rhythmic Skills for Humanoid Drumming 🤖 🔍 For details, check out: robotdrummer.github.io

Xor (@xordev) 's Twitter Profile Photo

Navigation improvements to my shader arsenal! -Added shader titles -Added a search bar -Added shader tags and categories -Added alphabetical sorting

CoffeeVectors (@coffeevectors) 's Twitter Profile Photo

Trying Ethan Mollick’s Veo 3 prompt but with movies as community theater. These are pretty fun! Also surprised AI knows how to do this. Avengers, Lord of the Rings, Transformers, Harry Potter, Top Gun, Dune, Predator, Ghostbusters, Titanic, Wakanda Forever, Batman, 300

Midjourney (@midjourney) 's Twitter Profile Photo

We're trying a new experiment called Midjourney TV. Watch trending videos live from the minds of our community. Videos match the shape of your browser window and you can have as many open as you want at once. Try it out at Midjourney.tv or youtube.com/live/Jkbmn13F2…

Joao Rodrigues (@jonaz_777) 's Twitter Profile Photo

Never got the idea of testing Three.js experiences on my watch browser. This is the power of web. A real cross-platform, interoperable and open technology. That's why the future #VR #AR wearables must have enough processing to run the browser engine

Bad Decisions Studio (@badxstudio) 's Twitter Profile Photo

Unreal Engine truly Empowers you as an Artist 🧑‍🎨 The ability to jump into your photorealistic cinematic worlds, take control of the camera in real time, and scrub through your animations while rehearsing your shots is insanely powerful! We teach you all of this and more in our

martin_casado (@martin_casado) 's Twitter Profile Photo

AI is so trippy. This entire scene, including the exterior, was created from a single image of the ovens in the interior. This is a multi-view reconstruction, not a video. No v2v used. Prompt image in reply.

Bilawal Sidhu (@bilawalsidhu) 's Twitter Profile Photo

4d gaussian splat processed from one of the largest volumetric capture stages ever made. And fun fact, it was Intel that originally made it! I remember seeing the results in 2017, and my mind was blown. You could capture something once, and reframe it infinitely in post. Alas,

Gabriele Romagnoli (@gabroxr) 's Twitter Profile Photo

This is the type of excellent tech demos I like to cover in my weekly XR AI news roundup 👇 I briefly discussed the different models for generating Gaussian Splatting (SPLAT3, MCMC and ADC) in my video comparing various 3DGS apps: youtu.be/CrlSey4RmVI The tech demo in the

Xiaoan (@_seanliu) 's Twitter Profile Photo

Talking to your AI glasses is silly, so we built Reality Proxy, a direct manipulation interface that lets you instantly select real-world objects and share context with AI. A step toward JARVIS.

Wevolver (@wevolverapp) 's Twitter Profile Photo

A System Uses Flying Drones for 3D Printing A team of researchers from UCL and Imperial College London has developed a system where flying drones collaborate to 3D print objects. The system, called Aerial Additive Manufacturing (Aerial-AM), uses drones to transport and deposit