- Pisa
-
18:18
(UTC +02:00) - yitaverse
- @yitaverse
- @yitaverse
- https://codepen.io/yitaverse
Starred repositories
ClearML Agent - MLOps/LLMOps made easy. MLOps/LLMOps scheduler & orchestration solution
zunzuncito — Gemma-4 26B-A4B colibrì engine for a small-RAM machine
The official code for “Deep Unrestricted Document Image Rectification”, TMM, 2023.
The official code for “Recurrent Generic Contour-based Instance Segmentation with Progressive Learning”, TCSVT, 2024.
The official code for “DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction”, ACM MM, Oral Paper, 2021.
The official repo for “DocScanner: Robust Document Image Rectification with Progressive Learning”, IJCV, 2025.
A comprehensive list of awesome document image rectification papers.
The official code for “DeepEraser: Deep Iterative Context Mining for Generic Text Eraser”, TMM, 2024.
AI model safety scanner built on NVIDIA garak
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…
Implementation of Band Split Roformer, SOTA Attention network for music source separation out of ByteDance AI Labs
Strip background music from YouTube videos
A modular Python toolkit for creating MCP modules tailored to chemical engineering and chemistry workflows.
A Chemistry Toolkit that turns your AI assistant into a Chemistry coscientist..
MCP server for Claude: molecule names or SMILES → publication-style 2D structure drawings (PNG/SVG, offline via RDKit), reaction schemes, curved-arrow mechanisms and schematic spectra. Optional Che…
Self-host the powerful Chatterbox TTS model. This server offers a user-friendly Web UI, flexible API endpoints (incl. OpenAI compatible), predefined voices, voice cloning, and large audiobook-scale…
Android Project to show dynamic app icons.
Virtual whiteboard for sketching hand-drawn like diagrams
thecodacus / llama.cpp
Forked from ggml-org/llama.cppLLM inference in C/C++
GLM-5.2, a 744 billion parameter mixture of experts model, in a pure C inference engine: quantized to int4, experts streamed from disk, deployed and benchmarked. Generates in 16 GB of RAM.
A robust Jupyter Notebook for rendering Blender projects on Google Colab GPUs with automatic FFmpeg video encoding and Google Drive integration.
Render Blender 5.x scenes with Google Colaboratory
ComfyUI custom nodes and web utilities for real-time AI generation and interaction
ObjRemover is a simple local AI object-removal tool powered by LaMa ONNX. It runs directly in your browser and is designed for local use, with no image upload required.
LOGOS (Language Of Generative Objects in Science) is the first multi-domain generative foundation model for the natural sciences built on a unified scientific grammar, enabling unified generative m…
A theme generator for your favourite syntax highlighters