OpenCV ile görüntü ve video işleme, makine öğrenmesi ve proje uygulamaları için Türkçe kapsamlı bir rehber. 🐙 Adım adım kod örnekleriyle öğrenin ve projeler geliştirin.

An efficient and fully parallelized pure python DFT and electronic structure code with GPU acceleration

Diagnose and Fix CUDA / GPU environments compatibility issues locally, in Docker, and CI/CD. CLI + MCP server available.

Python module and scripts to analyse CRISPRs and off-targets from a genome

A simple side project that uses cagliostrolab/animagine-xl-3.1 and igdb to create images of anime characters with elements of specific games. Can be used as a profile picture generator.

A GUI for transcribing audio and video files using [WhisperX](https://github.com/m-bain/whisperX), with CUDA acceleration for NVIDIA RTX.

Docker implementation of the AudioSeal

Docker implementation of the paper "Watermark Anything with Localized Messages"

Security Research Toolkit — Video and image analysis tool for neural inpainting and AI-generated content detection with SORA signature extraction, temporal consistency analysis, CNN artifact detection, CPU/CUDA device selection, multi-format support, and colorama-styled terminal interface

Intention is a configuration driven Youtube\Twitch downloader, sound file diarizer, transcriber and automatic host match and labeler. It also contains auto-topic classifiers and bias detection.

Docker implementation of the Marker pdf to markdown

Docker implementation of the Surya OCR

A premium AI studio, SignForge, creates architectural signage mockups by using Stable Diffusion XL and a multi-LoRA composition system. It transforms brand assets into hyper-realistic 3D visualizations, offering a high-fidelity React studio, automated performance monitoring, and Docker orchestration.

Enhanced Qdrant MCP Server is a production-ready fork of the original that transforms the basic MCP server into an enterprise-grade solution with GPU acceleration, multi-vector support, and automated deployment infrastructure.

"A neural network to rule them all, a neural network to find them, a neural network to bring them all and verify if is you !!" (Face recognition tool)

A comprehensive pipeline for processing learning videos, generating subtitles, summarizing content, and creating structured documents.

This repository presents a refined video summarization and sentiment analysis pipeline built entirely on video inputs using official Hugging Face models, including BLIP, SmolVLM (2.2B & 500M), XCLIP, and VideoMAE.

Docker implementation of the VideoSeal

Docker implementation of the Tabled OCR

Docker implementation of the Texify OCR