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…

Official JAX implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion

[CVPR 2024 Oral] MemSAM: Taming Segment Anything Model for Echocardiography Video Segmentation.

Accelerating the development of large multimodal models (LMMs) with lmms-eval

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

[BSQ-ViT] Image and Video Tokenization with Binary Spherical Quantization

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

[CVPR 2024] Official implementation of "VRP-SAM: SAM with Visual Reference Prompt"

[ECCV 2024] Tokenize Anything via Prompting

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

The official Meta Llama 3 GitHub site

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly …

[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale

Inpaint anything using Segment Anything and inpainting models.

A family of lightweight multimodal models.

Open weights LLM from Google DeepMind.

Official JAX implementation of MAGVIT: Masked Generative Video Transformer

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

OMG-LLaVA and OMG-Seg codebase

[ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model

A simple, performant and scalable Jax LLM!

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的可商用开源多模态对话模型