Introducing Blender Studio Vault: the ultimate archive of production history behind 20 years of Open Movies 🎦
Enjoy a guided tour by Francesco and Andy, and browse through terabytes of files yourself at https://t.co/8ojYemaTaU
#b3d#OpenMovie#BlenderStudio
Blender 5.1 alpha w/ DLSS viewport denoising. Very impressive, although it has trouble with volumetrics, transparency & dynamic lights. Download link to the compiled version in 🧵#b3d
17,000 tokens per second!! Read that again!
LLM is hard-wired directly into silicon. no HBM, no liquid cooling, just raw specialized hardware. 10x faster and 20x cheaper than a B200.
the "waiting for the LLM to think" era is dead. Code generates at the speed of human thought.
Transition from brute-force GPU clusters to actual AI appliances.
https://t.co/Bf6DH7Q6Uf
Krea AI killed it with their real-time editing feature
this is a level up for architecture & home design (and beyond)
you can paint, drag and drop, or prompt changes - and watch them render in real time(!)
New Blender 5.0 Volume grid nodes are awesome! Points to volume yielding some really cool results. I’ll have a tutorial up on Patreon tomorrow and have a more official thing for YouTube later. #b3d#blender#geometrynodes
ohhh so if you derive the normal for an SDF you can pass it into the principled BSDF shader and render fake geometry with environment reflections and lighting :d
We're thrilled to launch our new Hunyuan3D 3.0! It features 3x higher precision, 1536³ geometric resolution, and 3.6B voxel ultra-HD modeling for stunning detail.🔥🔥🔥
🌟Highlights:
✅Creates faces with lifelike facial contours and natural poses, creating truly realistic, high-fidelity models.
✅Precisely inteprets input images to reconstruct complex structures using a layered generation strategy, capturing hidden details
✅Generates ultra-clear, professional-grade details with enhanced texture fidelity and alignment for immersive, true-to-design visuals
Free access via Hunyuan 3D AI Engine (20 generations). Available via Tencent Cloud API. Transform gaming, film, e-commerce, and more!
👉🏻Try it now: https://t.co/BPyoN8fHHa
I believe they made a little tool for designers to accurately place lighting PER VIEW, same as for packshots.
And I found the files – they're loaded on the page as separate glTF files which contain little "light dots" and "shadow dots" in front of a neutral environment:
Apple's 3D viewer is based on @threejs, uses @glTF3D and gets more impressive every year!
CAD meshes, environment blends, reflection probes, occlusion: let's take a look at what's special this time –
(long thread ahead)
Relight a video with just a click!
I re-lit videos on my machine in minutes using @NVIDIAAIDev's DiffusionRenderer locally on my PC.
Imagine when this runs in real time.
I break down what you are seeing in the 🧵
#AI#GenerativeAI#NVIDIA#GENAI
Every robot you see is a data firehose generating terabytes of chaos.
This hidden crisis is the #1 reason robots fail, and it's costing the industry billions.
You see hardware, but not the data swamp drowning engineers.
In 2025, a quiet revolution is fixing it. Here’s how. 🧵