Stars
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
Generative Models by Stability AI
A unified framework for 3D content generation.
Image-to-Image Translation in PyTorch
This is the third party implementation of the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.
you can replace some objects of input image according to the description of objects
Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) by way of Textual Inversion (https://arxiv.org/abs/2208.01618) for Stable Diffusion (https://arxiv.org/abs/2112.10752). Tweaks focuse…
A latent text-to-image diffusion model
General AI methods for Anything: AnyObject, AnyGeneration, AnyModel, AnyTask, AnyX
Stable Diffusion web UI
Official implementation of our RAL'24 paper: Multi-Camera Unified Pre-training for Autonomous Driving
Effortless data labeling with AI support from Segment Anything and other awesome models.
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
YOLOv10: Real-Time End-to-End Object Detection
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
[CVPR 2023 Best Paper Award] Planning-oriented Autonomous Driving
本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Commonsense Prototype for Outdoor Unsupervised 3D Object Detection (CVPR 2024)
[NeurIPS'23 Spotlight] Segment Any Point Cloud Sequences by Distilling Vision Foundation Models
This is a complete package of recent deep learning methods for 3D point clouds in pytorch (with pretrained models).
A comprehensive list of pytorch related content on github,such as different models,implementations,helper libraries,tutorials etc.
PyTorch code and models for the DINOv2 self-supervised learning method.
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
A lightweight tool for labeling 3D bounding boxes in point clouds.