facebookresearch / dinov2
PyTorch code and models for the DINOv2 self-supervised learning method.
☆9,694Updated 5 months ago
Alternatives and similar repositories for dinov2:
Users that are interested in dinov2 are comparing it to the libraries listed below
- Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and …☆15,633Updated 4 months ago
- [ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"☆7,257Updated 5 months ago
- [NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"☆4,462Updated 5 months ago
- An open source implementation of CLIP.☆10,864Updated 3 weeks ago
- LAVIS - A One-stop Library for Language-Vision Intelligence☆10,193Updated 2 months ago
- Segment Anything in High Quality [NeurIPS 2023]☆3,782Updated last month
- The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoi…☆48,643Updated 4 months ago
- Official repo for consistency models.☆6,233Updated 10 months ago
- Painter & SegGPT Series: Vision Foundation Models from BAAI☆2,545Updated last month
- EVA Series: Visual Representation Fantasies from BAAI☆2,400Updated 5 months ago
- Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).☆2,178Updated last year
- An open-source framework for training large multimodal models.☆3,805Updated 4 months ago
- Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI…☆6,589Updated 7 months ago
- ImageBind One Embedding Space to Bind Them All☆8,486Updated 5 months ago
- [ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"☆2,457Updated 6 months ago
- Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"☆11,177Updated last month
- Fast Segment Anything☆7,664Updated 5 months ago
- PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation☆4,981Updated 5 months ago
- Efficient vision foundation models for high-resolution generation and perception.☆2,583Updated this week
- The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained mode…☆13,798Updated last month
- Open-source and strong foundation image recognition models.☆3,048Updated 5 months ago
- Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"☆6,752Updated 7 months ago
- Code release for ConvNeXt model☆5,851Updated 2 years ago
- Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.☆3,868Updated 5 months ago
- PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO☆6,543Updated 6 months ago
- [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters☆5,801Updated 10 months ago
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆17,087Updated this week
- Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.☆2,538Updated last month
- High-Resolution Image Synthesis with Latent Diffusion Models☆12,256Updated 11 months ago
- An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary alg…☆2,869Updated 9 months ago