My hands-on Generative AI learning journey. A personal collection of notebooks, mini-projects, prompt engineering experiments, and notes tracking my progress from foundational LLMs...
ComfyUI custom node bridging MiniMax-H3 Ref2VA through a local SGLang server (2x RTX 4090, TP=2, layerwise offload). Dynamic image/video/audio reference inputs, native VIDEO output...
AI 驱动的漏洞自动验证平台：提交仓库与漏洞描述，在隔离沙箱中白盒审计、搭靶场复现并出具中文报告。
A workspace where people and multiple AI agents work together.
One-click Stable Diffusion installation for Windows with AUTOMATIC1111 WebUI. Pre-configured with best checkpoints, LoRAs and extensions.
Dataset abierto de modelos de HuggingFace: metadatos curados y normalizados, licencias clasificadas, parámetros reales, tumbas de modelos retirados y ficha técnica en castellano po...
Open source SDK for building data-quality, processing, enrichment, and curation pipelines for robotics and Physical AI.
Attribute an image to the model that generated it — from raw pixels, with a ~6M-parameter CNN (RPA).
A knowledge-linked local AI harness with macOS support and a Windows Beta launcher.
Turn any website into a compact CLI tailored for AI agents. Browse the web in hundreds of tokens, not tens of thousands.
A multi-modal Generative AI studio combining conversational assistance and AI-driven image synthesis, powered by Groq and xAI APIs.
Tool calling in 48M parameters — small enough to specialize per domain. Adapt it to your own tool catalog in a few hours; JSON structure and argument keys are grammar-guaranteed. S...
Emotion Ball 是一套面向 AI 助手的表情引擎:32 种状态表情全部由纯 SVG 与原生 JavaScript 实时驱动,零框架、零图片资源。AI 侧只需输出一个 emotionId,小球即可切换到对应表情,可直接用作聊天机器人、桌面宠物、悬浮助手的情绪表达层。
Code and evaluations for "Where a New Concept Must Enter: Entry Point Gates Cross-Task Usability in Unified Multimodal Models"
Open-source AI demos you can understand, run, and remix — small, reproducible builds for vision, multimodal models, local or hosted inference, and more.
Official RMD implementation for cross-resolution diffusion distillation and accelerated video generation.
A local, offline metadata cleaner and AI-tag remover for images, text/Markdown, HTML, and Office documents, written in Rust. Strips EXIF, GPS, XMP, IPTC, C2PA, and AI-generator sig...
Hands-on notebooks: Walmart Generative AI Training for Engineering Managers
Sprix AI at 屿智同行 — state-aware SELF/COLLABORATE/HANDOFF routing for A2A agent networks.
Turn story ideas into validated four-panel comics with DeepSeek and pluggable image providers.
Learn LLM Inference Engineering step by step - from KV cache, PagedAttention, and continuous batching to vLLM, SGLang, and GPUs.
Turn any video into a Mixamo-rig animation - GVHMR estimator, spec-driven retarget, FK apply in Blender via MCP. Works with any Mixamo character; built to be operated end-to-end by...
Sub-GHz IoT attack emulation + explainable ML detection — Flipper Zero + RTL-SDR + SIEM purple-team platform
AI pothole reporter for Bengaluru: on-device Android app that detects potholes, finds the responsible corporation officer and road contractor from public records, and drafts compla...