Brad Hammond
5.7K posts
Brad Hammond
@XY01
XR - Interactive creative experiences - Giant robot bug car - Shaders - VR firefighter training Lead Dev @ EXP/Flaim Systems.
Melbourne, Australia Присоединился Şubat 2009
1.8K Подписки445 Подписчики
Brad Hammond ретвитнул
Brad Hammond ретвитнул
This is British values - Robert Fisk is a real reporter and he’s spot on here …..
English
Brad Hammond ретвитнул
Brad Hammond ретвитнул
Brad Hammond ретвитнул
Three.js (TSL) + WebGPU で3D流体シミュレーション。
追加実装しました。
・燃料と温度の相互作用に基づく燃焼モデルと爆発的な体積膨張
・カールノイズによる乱気流の適用
コードはGemini 3.1 Pro Previewで生成。
#fluidsimulation #combustion #vfx #tsl #threejs #webgpu #gemini #ai
日本語
Brad Hammond ретвитнул
We're extremely excited to announce the release of PATINA, a first-of-its-kind model that excels at PBR texture generation 🚀
🥇 SOTA commercial offering of PBR material creation, bridging the gap between AI image generation and traditional CGI
🌱 Homegrown by us at fal
🤑 Estimate your own material maps at $0.01 / map / megapixel
🖼️ 1K up to 8K material generation starting at just $0.08 for a complete five-map-plus-render material from text (and optional image)
🔍 Identify and extract materials from images with plain language
English
Brad Hammond ретвитнул
動画生成じゃなくて画像生成
これwebカメラからのリアルタイム画像生成だけど動画生成のフレーム補完と違ってなんか温もりを感じて好き
日本語
Brad Hammond ретвитнул
Brad Hammond ретвитнул
Brad Hammond ретвитнул
@alon_mizrahi …Well seperation of church and state is definitely not it
English
Brad Hammond ретвитнул
Brad Hammond ретвитнул
I used Gemma4 + Falcon Perception from this mlx-vlm release to build a grounded reasoning agent runs fully local on M3
the idea: VLMs are great at reasoning but not great at measuring. Falcon Perception is great at segmentation but cant reason. so you loop them: Gemma4 decides what to look for, FP segments it and returns pixel-accurate coordinates, Gemma4 reasons on the numbers
ask "is the blue player offside?" → it grounds the players, finds the second-to-last defender, compares centroid positions, applies the rule. check the video for some examples
@Prince_Canuma I can submit a PR with this demo if you want
Prince Canuma@Prince_Canuma
mlx-vlm v0.4.4 is out 🚀🔥 New models: 🦅 Falcon-Perception 300M by @TIIuae Highlights: ⚡️ TurboQuant Metal kernels optimized — upto 1.90x decode speed up over baseline on longer context with 89% KV cache savings. 👀 VisionFeatureCache — multi-turn image caching so you don’t re-encode the same image every turn. 🔧Gemma 4 fixes — chunked prefill for KV-shared models & thinking, vision + text degradation, processor config, and nested tool parsing 📹Video CLI fixes Get started today: > uv pip install -U mlx-vlm Shoutout to the awesome @N8Programs for helping me spot and fix some critical yet subtle issues on Gemma 4 ❤️ Happy easter everyone 🐣 and remember to leave us a star ⭐️ github.com/Blaizzy/mlx-vlm
English
Brad Hammond ретвитнул
New project coming soon - Mac LLM users would be able to inference while at some cases only needing 1/3rd the amount of RAM
Will be open source by next week; not theoretical, fully working with these models. Will update after testing GLM 5 and Kimi 2.5, and will do MMLU tests with all models for more information.
#macbook #llm #mlx
English
Brad Hammond ретвитнул
Brad Hammond ретвитнул
A legendary programmer who built the 3D graphics engines that defined modern gaming realized one terrifying truth:
Complexity is the absolute enemy of execution.
His name is John Carmack, the man who famously co-founded id Software and pioneered modern virtual reality. He argued that we obsess over building infinitely scalable architectures and completely ignore the cognitive load it puts on the team.
Here are 4 operational frameworks he used to build elite, high-velocity engineering teams:
English
Brad Hammond ретвитнул
We've updated RconViaGen-v0.5 based on TRELLIS.2, supporting the generation of high-resolution meshes and PBR materials from multi-view images, and have also released the training code for ReconViaGen!
Code：github.com/GAP-LAB-CUHK-S…
Huggingface demo：huggingface.co/spaces/Stable-…
English
Brad Hammond ретвитнул
