Official implement of TEASR: Training-Efficient Any-Step Diffusion Transformer for Real-World Image Super-Resolution (ECCV2026)
A skill for AI agents: search the web with SearXNG, browse with Camofox, bypass protections with CloakBrowser. Self-hosted, free, unlimited.
Machine-learning ZeroLink platform featuring Event-driven-architecture technology and advanced Real-time-processing for modern Mesh
50 open-source skills that teach your AI coding agent to make motion graphics, animation & video — kinetic typography, data-viz, explainers, TikTok/Reels, WebGL, Manim. 14 installa...
Open reimplementation of Sakana Fugu — the 'one model to command them all' LLM orchestrator. Read → run → train → serve.
Hand-drawn kawaii avatar engine for your app. No AI, no API calls.
Generative AI Project - AI SQL Assistant
Official implementation of "GeoFace: Consistent Multi-View Face Generation with Geometry-Constrained Diffusion"
The first AI agent harness native to the browser. A Chrome/Firefox extension that runs the agent loop in your browser — drives your tabs, spins up sandboxed compute (JS notebooks, ...
Meet Reviewer 2 before they meet you ！ A Claude Code skill that red-teams your paper draft — a simulated peer-review panel + an evidence-grounded fix list, before you submit.
Cloud-agnostic HashBridge orchestrates real-time machine learning with adaptive auto-scaling, a resilient Distributed Control Nexus Gateway.
Context-agnostic ChainForge integrates machine learning, microservices, and concurrent execution to create a highly resilient orchestrator.
VoxPolish - a TTS dataset cleaner. Remove noise, trim silence, normalize loudness for text-to-speech training data in one command.
A project-based curriculum that teaches PyTorch by rebuilding it from scratch. Start with scalar backpropagation, create a reverse-mode autodiff engine, expand it into tensors, the...
[ECCV 2026] Official implementation of Hi-DiT: Hybrid Latent-Pixel Diffusion Transformer for Image Generation
Local-first AI image gallery and metadata browser for Stable Diffusion, ComfyUI and A1111 outputs.
Manvo TV — 想到什么就生成什么 · AI 原生创作平台(无限画布 + 漫剧剧本工厂) | https://manvo.tv
A lightweight deep learning framework for rotated object detection in aerial and satellite imagery
Official implementation of DiGS-Avatar: Single-Image Animatable 3D Human Reconstruction via UV-Space Diffusion
Discrete-diffusion protein language model with ESM-2 conditioning: implementation and honest evaluation.
Lightweight, explainable VAD that beats Silero and WebRTC on noisy audio. No GPU required.
An AI storyboard tool: generate ordered sequences of images with ComfyUI text-to-image models (Ideogram-first), with a structured JSON layout editor and draggable bounding boxes
Enterprise-scale cloud security portfolio showcasing AWS-native security architectures, Security Operations Centers (SOC), DevSecOps platforms, governance frameworks, automated inc...