Brian Caffey
@briancaffey
Followers
168
Following
467
Media
10
Statuses
52
GTC DC 2025 was amazing!! 🤩 Robots, agents, quantum and much, much more. I joined the World’s Shortest Hackathon, did hands-on training labs, connected with experts, walked miles on the expo floor and saw what’s next in AI 👀 NVIDIA hosted a “Golden Ticket” developer contest
One last surprise for our #NVIDIAGTC golden ticket winners 👀 🎁 Yesterday, we took the winners to see our brand new NVIDIA DGX Spark on the show floor... and then gave them each one. We can't wait to see what they create. #SparkSomethingBig ✨
0
1
6
🎶 The background music is Neon Reverie, one of my favorite generations on @SunoMusic 🗣️ Video narration was made with the dia model from @nari_labs
https://t.co/Zc6SsrREmt
0
0
2
https://t.co/1WPWRkqtBr NIM Kit is built with FastAPI and Redis on the backend and Nuxt.js and shadcn on the frontend. Start the backend with `docker compose up`, start the backend with `yarn && yarn dev`, and then tap into NVIDIA’s optimized inference models running on your RTX
github.com
A toolkit to explore and build with NVIDIA NIMs. Contribute to briancaffey/nvidia-nim-kit development by creating an account on GitHub.
1
0
5
📢 Introducing NIM Kit, an open-source application for building with NVDIA Inference Microservices (NIMs) NIM Kit is a local version of https://t.co/9FjTg9cFFY. It brings together all of the libraries and interfaces for a variety of AI inference models including LLMs, image
5
2
18
🏆 Project G-Assist Plug-in Hackathon Winner Spotlight (1st Place): Flux Plug-in for Project G-Assist by @BrianCaffey 🖼️ Use this plug-in to generate images using text-to-image or image/screenshot-to-image @bfl_ml FLUX models. Try it in G-Assist today 👉 https://t.co/lIXRTeZ9F4
3
2
13
Flux Plug-in for Project G-Assist ⚡️🎨🤖🖼️🖥️⚡️ Generate stunning images on your NVIDIA GeForce RTX AI PC with natural language using G-Assist #AIonRTXHackathon 🖼️ @bfl_ml flux.1-dev & flux-kontext 🎶 @SunoMusic “vibes” by @briancaffey 🗣️ @nari_labs dia (video narration) my
2
1
5
We are joining forces with @vercel ✨ Nuxt stays MIT-licensed. The roadmap stays public. The community stays at the center. 💚
We are excited to announce that NuxtLabs is joining @Vercel to pursue our mission on creating the best DX to deliver the best UX. Read more at https://t.co/Lp4SPXR31B
35
134
1K
High quality image editing no longer needs closed models We release FLUX.1 Kontext [dev] - an open weights model for proprietary-level image editing performance. Runs on consumer chips. ✓ Open weights available ✓ Best in-class performance ✓ Self-serve commercial licensing
99
363
2K
🚀 Hunyuan 3D 2.1 is here! The first fully open-source, production-ready PBR 3D generative model! ✅Cinema-grade visuals: PBR material synthesis brings leather, bronze, and more to life with stunning light interactions. ✅ Fully open-source: Model weights, training/inference
81
318
2K
@NVIDIAAIDev
https://t.co/X5Ei9TDLiu Here's an article I wrote that gives a deeper look at the technical side of Mediation Simulator and how it uses NVIDIA Agent Intelligence Toolkit
briancaffey.github.io
Mediation Simulator is an AI application designed to help legal students and professionals build dispute resolution skills through simulated mediation sessions
0
0
1
📑🤝🤖⚖️ Mediation Simulator is my submission for the NVIDIA Agent Intelligence Toolkit Hackathon! This application simulates law school mediation competitions using agentic workflows with LLMs, orchestrated by the NVIDIA Agent Intelligence Toolkit #NVIDIAHackathon @NVIDIAAIDev
3
3
9
Studio Ghibli style transfer is holding back progress in AGI
14
10
408
Anduril is taking over IVAS, and we don't have time for business as usual. Whatever you are imagining, however crazy you imagine I am, multiply it by ten and then do it again. I am back, and I am only getting started.
Anduril is taking over the @USArmy's Integrated Visual Augmentation System (IVAS) program pending @DeptofDefense approval. We are now fully responsible for production, hardware, software, and integrating Lattice to greatly expand warfighter capabilities.
485
601
9K
AugmentOS 1.0 has dropped. AugmentOS is the open source OS and super app for smart glasses. It enables apps and AI agents for the next 8 billion personal devices. And we're launching today, with hardware you can buy today. 1/🧵
104
204
2K
https://t.co/4XW7k1cf7h RedLM code repo on GitHub
github.com
RedLM is an AI-powered application for the study of Redology - briancaffey/RedLM
0
0
1
https://t.co/QawxXdDCij An in-depth blog post about the technology that powers RedLM
briancaffey.github.io
RedLM is an AI-powered application for the study of China's greatest classical novel: Dream of the Red Chamber
1
0
1
RedLM: An AI-powered application for Redology 🪨✨📜🔎🖼️ A project for the #NVIDIADevContest #LlamaIndex @NVIDIAAIDev @llama_index
1
0
8