ageek.ss @jikkimi

this is basically what wearing AR glasses will be like but all the time

Rohan Nuttall @rohancalum

3 days ago

Astra, make this photo interactive and find the books

194 888 11K 1.2M 7K

GPT-6 Astra is a beast. Give it a Zillow listing. It can 3D model the house based on the listing photos and create a cool promotion video. The video was just created in one shot and there are still some wrong details. But I am sure it will be much better if I ask it to polish further. OpenAI is so back.

GPT-6 changes 3D modeling forever. It works inside Blender completely autonomously, like an artist: gathers reference photos on its own, builds the scene, renders test frames, checks them against the references, then fixes what's off. When the scene holds up, it ships it to Unreal Engine 5 as a walkable level. Clips from the @OpenAI launch. More demos in the thread. Full announcement: openai.com/index/gpt-6-as…

GPT-6 Astra is the strongest model for 3D game from a single prompt. We described the game in one sentence > GPT-6 Astra wrote the whole thing - drift physics, combo scoring, near-miss bonuses, speed traps, nitro > out came Street Heat, a full arcade racer running in the browser. The whole pipeline ran end-to-end on Higgsfield Supercomputer.

If you look at the state of the art in procedural 3d generation then you’ll quickly realize that language models will make a serious dent in controllable world building - manifesting whatever we want into existing 3d tools like houdini, blender or unreal.

@AdamsuMus 쓰ree gathering 은제 또 함 될까요? ㅎㅎㅎ @clairejiyeonj

Introducing Proofs — visual, dynamic interfaces to build games with Bezi. Proofs are freeform mini-apps you spawn for any custom need: communicate your design intent to AI, represent real-time data about your project, or expand your workspace in any other creative way you wish.

FLUX 3 Video is live in ComfyUI via Partner Nodes @bfl_ai FLUX 3 Model highlights: → 20s in a single generation → native audio, not dubbed on after → text-to-video, image-to-video, keyframes, continuation → multi-scene and multi-angle in one prompt → multilingual dialogue with lipsync that holds → typography that sits in the scene → chain clips agentically for longer stories One model across video, audio, image, and action. Click the link below to download the workflows and learn more with blog

Blender → ComfyUI → LTX-2.3 IC-LoRA ⚡️ • Shot on green screen • Composited into a Blender scene • Extracted Depth + Pose • Generated the final render with LTX-2.3 IC-LoRA Simple 3D blockout → AI-powered cinematic render. @ComfyUI @ltx_io

Late night experiment. I built a demo that generates 3D environments from images into 3DGS, then uses them as a spatial reference for directing real-time AR camera movements. The capture is then run through Seedance 2.0 for the final output. all running on the web via three.js↓

Doing a demo for GENESIS and the markerless solve. Here it is accurately capturing TEN people in a volume of 6m x 6m 🤯🤯🤯 This is pretty astounding, works in realtime and the truth is we reckon the system can probably do double this number. Should we try it ? 😵‍💫😀 Loads more multi person captures to come. For a live or virtual demo, or to experience the system and data quality first hand visit move.ai #motioncapture #markerlessmotioncapture #ai #artificialintelligence

Check out this city generator addon — it’s a really cool tool for city building and urban design work. Link 👇 superhivemarket.com/products/icity… #Blender #CityBuilding #3DArt #UrbanDesign #Gaming

AI actors are getting scary good.. spent 2 day making this short film.. if you still think actors are safe, ihave nothing to say.. this is so over check my prompts and workflow on buzzy now:

Still can't believe how good Siri AI looks on Apple Vision Pro.

Meta rolled out the ability to develop visual apps for Meta Ray-Ban Display, controlled by Meta Neural Band, and developers are already building interesting things. Details here: uploadvr.com/meta-ray-ban-d…

If you can build for Android, you can build for Meta Quest. Next up in our Build Faster, Earn More series: AI tooling for Android developers that automates the VR-specific differences so you can use the same workflows you already know. Get started 👉 bit.ly/3S4gIly

Users were sideloading this developer's Android file manager on Quest before he even supported it. He took the hint, ported it in a week, and matched his monthly revenue rate on other platforms in just 2 months. 🚀 Read the story behind 'AnExplorer' 👉 bit.ly/4o11x8s

This is such a real take 😂🔥 UE5 tech demos set expectations insanely high, and now every game gets compared to that standard. Do you think the gap is about hardware, optimization, or overhype? 👀 Drop your honest take below 👇 #UnrealEngine #UE5 #UE7 #GameDev #Gaming

A two-person studio shipped 25 VR builds in 4 weeks. 🚀 They used AI agents, Meta analytics, and a tight feedback loop to overhaul their onboarding and grow revenue. Read how Virtual Beings, the team behind @ForeverPets_ did it 👉 bit.ly/4acmzv8 #VR #MetaQuest

. @GrooveJonesXR needed to deliver the impossible: giant NFL-licensed Crocs parachuting into Dick's Sporting Goods parking lots; hyper-realistic, multi-location, vertical 9:16  on a holiday deadline. A traditional CG pipeline wasn't an option. So they built a new one inside ComfyUI. Their Senior Creative Technologist @heydoughogan architected a single-graph workflow that orchestrated Flux, Gemini Flash, Veo 3.1, and Moonvalley's Marey. With custom LoRAs trained on Crocs NFL product and DSG storefronts ensuring brand accuracy across every shot. Client iterations that once took weeks happened same-day. Final compositing in Nuke brought it to 2K for Reels, TikTok, and Shorts. The campaign delivered on time. It also won the Aaron Award for Best AI Workflow for Production. "VFX projects used to operate at razor thin margins. Comfy solved that for us." - Dale Carman, Co-founder @ Groove Jones This is what a modern production pipeline looks like