Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching

Wan: Open and Advanced Large-Scale Video Generative Models

Superscale is a plug-and-play super-resolution toolkit. Run the latest 6 SOTA models with a single line of Python or via a zero-setup GUI.

Simple LLM package for ios devices.

[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

Flutter plugin for Ultralytics YOLO

Ultralytics YOLO iOS App source code for running YOLO in your own iOS apps 🌟

HunyuanVideo: A Systematic Framework For Large Video Generation Model

simple usage of yolov8 on android device

All my self trained & released AI upscaling models. After gathering and applying over 600 different upscaling models, I learned how to train my own models, and these are the results.

[CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution

pretrained tflite models.

Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)

Converted CoreML Model Zoo.

[ICLR 2025] HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models

A collection of samples for using various AI models on iOS.

easyportrait run on swift sample

iPhone/iPad version of lama cleaner

LaMa for Core ML

Implementation of 3D computer vision

GLPanoDepth: Global-to-Local Panoramic Depth Estimation

PyTorch codes for "Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors", ACM MM2022 (Oral)

Fast Segment Anything

LAVIS - A One-stop Library for Language-Vision Intelligence

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.