Having a few hours this afternoon after #CVPR2026? Consider... visiting Red Rocks 20 minutes outside of Denver! For some inspiration, here's a world processed by SpAItial AI Echo-2 HQ model from a single phone image! Link to the world in🧵show more

This AI workflow is wild I used GPT Image... 2 to create a character sheet, then animated it with Seedance 2.0 in just a few minutes Prompt in thread 🧵show more

Echo-2 is a physically-grounded world model from which we... can distill meshes, point clouds, or 3DGS scene representations. Directly usable in a myriad of downstream applications from gaming to training robots. Want to build your own world? Try it here:show more

World Models are heating up as Prof. Fei-fei Li... Fei-Fei Li's World Labs World Labs ignites the space with their first product Marble 🔥🌍 Riding that momentum, we’re launching a World Model demo on Theta Network EdgeCloud, powered by Tencent Tencent 腾讯's open-source Hunyuan 3D World Model, and packaged as a standard model template for creators, devs, and AI worldbuilders. Text/Image → explorable 3D worlds. Single image → full geometry. Exportable, editable, fast! Try it now:show more

Selected as a best paper finalist at #CVPR2026: PixelDiT... from NVIDIA Research In most image generation models, a pretrained autoencoder compresses the image before any diffusion happens, causing quality loss that accumulates across the entire pipeline. PixelDiT, or Pixel Diffusion Transformers, removes this step entirely. It's a single-stage model that learns the diffusion process directly in pixel space, end-to-end.show more

In 1983, there was an attempt to break the... world record for fastest time to build a house from the ground up. The time to beat was 4 hours and 18 minutes, and they built the house in just over 2 hours and 45 minutes.show more

AI anime production is crazy now I used GPT... Image 2 to create my first pirate character sheet, then animated the story with Seedance 2.0 in just a few minutes. As a longtime One Piece fan, this was way too much fun. Prompt in thread 🧵show more

Will the world rely on a single #GenAI model?... Don’t count on it. In this AI Academy episode, IBM Director of Research Darío Gil explores different approaches to #AI and how businesses can go from AI users to value creators. Watch it here:show more

This is a 🔥 launch for AI image generation!... I uploaded four photos of myself to Krea and got a model that generates real-time images of me. Adjust the prompt and you'll immediately see a change - watch me travel around the world ✨show more

Electricity update: We've had no power for 4 hours... in the morning, afternoon, and now again. That's a total of 12 hours daily. Internet is barely working. Everything's disrupted—from defrosted fridges in supermarkets to stalled manufacturing. 1/2 🧵show more

Experimenting with image-to-world: creating consistent 3D environments from a... single photo. As someone who studied architecture, this feels like a glimpse into the future of spatial creation and I’m excited to see where World Labs takes it.show more

Built a fully native, SwiftUI app for tracking our... son’s naps and distributed it via TestFlight to my wife, over a few hours all from my phone(!!!) using Bitrig. It’s obviously not the best app in the world, but it’s fun and uses some iOS 26 APIs + modern components:show more

Thread on some of the most surreal & beautiful... train rides in the world🧵 1. A ride from Bangalore to Idagunji, Karnataka, India 🇮🇳show more

World Models are the path for some AI Models... in the future. But how can we efficiently train these models to not only see the world the way humans do but to see the world in a new and unique way. By visualizing, what is normally sequenced audio patterns, we can derive much more insights. Here we see Paganini in a visual form that can than be described and transcribed into a World Model. We can observe connections in a manner that may not have been clear prior to the digitalization of music and sound in this way. The company with the most valuable potential in building a World Model is Tesla. Not that this type of visualization is being used, but that the mechanisms are in place, and the technology is in place for the company to thrive in this new form of AI.show more

This update introduces a groundbreaking "Native Audio" capability. The... model completely transforms the traditional AI video workflow of "first generating silent visuals, then manually adding voiceovers and sound effects." By deeply aligning the semantics of sounds and dynamic visuals from the physical world, VIDEO 2.6 enables the end-to-end generation of complete videos in a single go...show more

🎬 Hollywood better watch out. You only need a... few minutes and a single AI model to create videos like this. Here’s the full workflow + prompt so you can try it too. 🔖 Bookmark for latershow more

AI can now literally sell anything to anyone. Sora... 2 is live inside arcads. just upload image, write a script, set the accent and tone. the output looks like a real person filmed it on their phone brands are still paying $500 for worse output than this. Here's how to do it 🧵show more

This croissant is generated by a text-to-3d AI model.... Just a short few years after Yakuza: Like a Dragon We've hit the pinnacle of bread-tech. More examples in reply + more info here:show more

🧮Turn single image into a custom LoRA model in... one click ! Should work for character and product ! This ComfyUI workflow: → Uses Gemini AI to generate 20 diverse prompts from your image → Creates 20 consistent variations with FLUX.1 Kontext → Automatically builds the dataset + trains the LoRA One image in → Trained LoRA out 🎯 #ComfyUI #LoRA #AIArt #FLUX #AutomatedAI ComfyUI BlackForestLabsAI - Unofficial 🔗 Check it out: This workflow was made for the hackathon organized by ComfyUI in SF yesterdayshow more