Janus-Series: Unified Multimodal Understanding and Generation Models

KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge ba…

The code for "VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM"

A highly capable 2.4B lightweight LLM using only 1T pre-training data.

Memory-Guided Diffusion for Expressive Talking Video Generation

Let your Claude able to think

Bring portraits to life!

Open-Source Web Automation library with any LLM

SOTA discrete acoustic codec models with 40 tokens per second for audio language modeling

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

PPOCRLabelv2 is a semi-automatic graphic annotation tool suitable for OCR field, with built-in PP-OCR model to automatically detect and re-recognize data.

Examples and tutorials on using SOTA computer vision models and techniques. Learn everything from old-school ResNet, through YOLO and object-detection transformers like DETR, to the latest models l…

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

real time face swap and one-click video deepfake with only a single image

Next generation face swapper and enhancer

The official Implementation of PeriodWave and PeriodWave-Turbo

State-of-the-art 2D and 3D Face Analysis Project

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs

Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

mPLUG-Owl: The Powerful Multi-modal Large Language Model Family

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

[IROS24] Offical Code for "FruitNeRF: A Unified Neural Radiance Field based Fruit Counting Framework" - Inegrated into Nerfstudio