Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜

This repo has all the basic things you'll need in-order to understand complete vision transformer architecture and its various implementations.

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

Efficient vision foundation models for high-resolution generation and perception.

This repository provides the code and model checkpoints for AIMv1 and AIMv2 research projects.

dinov2 features aligned with CLIP

Code for paper https://arxiv.org/abs/2409.02958