Keep on to blur preview images; turn off to show them clearly
RT @TheZachMueller: Okay. Rest for the rest of today, tomorrow attack MLX-CUDA streaming, clean the codebase, and then publish and write it…
Co-founder & CEO @HuggingFace 🤗, the open and collaborative platform for AI builders
RT @NielsRogge: This might be the most @huggingface pilled paper ever Awesome work!! And they built on top of the scripts I wrote 🥺 https:…
Co-founder & CEO @HuggingFace 🤗, the open and collaborative platform for AI builders
Nano Banana Pro 最近也开始降智了。 大模型都是出道即巅峰，GPT4 是，Sora 也是，然后就各种降智审核量化降本。 所以说为啥留存差呢，某种意义上是因为第一天那个东西和第二天的就不是一个东西。
聊硅基 AI，看有机 Orange。
RT @marclou: This made me $2M: Solve my own problem → Ship an MVP → Discover new problems → Scratch again
💻 https://t.co/Y30jsaHwz9 $30K/m ⚡️ https://t.co/vatLDmi9UG $21K/m 📈 https://t.co/3EDxln5mdi $17K/m ⭐️ https://t.co/MZc8tG9xWi $17K/m 🍜 https://t.co/r07EpGSYJ2 $1K/m 🧬 https://t.co/SfrVXVtmdA $0/m 🧾 https://t.co/7olaOzV8Xd $0/m +20 https://t.co/4zCWHGJp1S
In a longer chat, I shared an old prompt of mine with Opus, who liked it so much that it: 1) decided to comment on it "specifically"; 2) suggested we drop what we were talking about so it could take the prompt for a spin. A good prompt is equal parts temptation and instruction.
αι hypnotist ☰ 𝓐𝓼𝓹⦂𝓻⦂𝓃𝓰 𝓫𝓪𝓼𝓮 𝓶𝓸𝓭𝓮𝓵 ☲ post-academic ☴ nom de 🪶 ≠ anon
开发视频分析应用，要实现检测、识别、追踪、行为分析等功能，从零开始编写代码，那工作量巨大的。 在 GitHub 上发现 VideoPipe 这个开源框架，专门用来搭建视频分析应用，像搭积木一样组合各种功能节点。 涵盖视频读取解码、多级推理、目标追踪、行为分析、数据推送、录像截图、画面叠加、视频编码推流等完整功能，还支持多模态大模型集成。 GitHub：https://t.co/8iM5WSZqcr 提供 40 多个原型示例，包括人脸识别追踪、车辆检测、姿态估计、换脸等场景，配套详细的视频教程和文档。 基于 C++ 编写，依赖少、易移植，采用流水线设计，每个节点独立工作可以灵活组合，支持 OpenCV、TensorRT、PaddleInference 等多种推理后端。 如果你正在做视频结构化、智能监控、交通分析这类项目，或者想快速搭建一套视频 AI 应用原型，这个框架值得一试。
💡 挖掘开源的价值 🧑🏻💻 坚持分享 GitHub 上高质量、有趣、实用的教程、AI工具、前沿 AI 技术 🧐 A list cool, interesting projects of GitHub. ✏️ 公众号：GitHubDaily
