Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
- ocr
- chineseocr
- pdf2markdown
- pp-ocr
98,836 visible repositories in the index
1–24 of 504 · Most stars
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video production studio.
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
AirLLM 2.8T LLM inference with single 4GB GPU
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Code and documentation to train Stanford's Alpaca models, and generate the data.
Open-Sora: Democratizing Efficient Video Production for All
Invoke is a leading creative engine that uses image and video generation models to empower professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry-leading application interface, and serves as the foundation for multiple commercial products.
The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.
Fully open reproduction of DeepSeek-R1
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
AI video skill for Claude Code & Codex — cinematic, editable product promos with Remotion: 124 shot recipe cards, 150 motion previews, beat sync, sound design, Motion Workbench & JianYing (CapCut CN) export.
[ECCV 2026 Best Paper Award Candidate] LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction
Instant neural graphics primitives: lightning fast NeRF and more
CVAT is a leading data annotation platform for image, video, audio, and 3D datasets. It offers open-source, cloud, and enterprise products, as well as labeling services, with AI-assisted labeling, quality assurance, team collaboration, analytics, and developer APIs.
🦉 Data Versioning and ML Experiments
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
TranslatedIndustry-first professional AI Agent platform for controllable film & video production. From shorts to live-action with Hollywood-standard workflows. (The Chinese part states: the first industrial-grade, full-pipeline AI film and video production platform.)
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.
Minimal reproduction of DeepSeek R1-Zero
COLMAP - Structure-from-Motion and Multi-View Stereo