SimpleSD

Simple Self-Distillation

FastVLM

Efficient Vision Encoding for Vision Language Models

DiffuCoder

Core ML Gallery Models

OpenELM Pretrained Models

TiC-CLIP

Benchmark for the design of efficient continual learning of image-text models over years.

Core ML Stable Diffusion

Core ML Depth Anything

AIM

AIM: Autoregressive Image Models

Core ML Segment Anything 2

CLaRa

CLaRa models

MobileCLIP2

MobileCLIP2: Mobile-friendly image-text models with SOTA zero-shot capabilities trained on DFNDR-2B

AIMv2

A collection of AIMv2 vision encoders that supports a number of resolutions, native resolution, and a distilled checkpoint.

OpenELM Instruct Models

MobileCLIP Models + DataCompDR Data

MobileCLIP: Mobile-friendly image-text models with SOTA zero-shot capabilities. DataCompDR: Improved datasets for training image-text SOTA models.

DepthPro Models

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second

Core ML FastViT

DFN Models + Data

CLIP Models trained using DFN-2B/DFN-5B datasets

DCLM

DCLM Models + Datasets