ljdang

CLIPAway

A novel framework manipulating CLIP embeddings via projection to remove objects using Stable Diffusion prior.

RTranslator

Open source real-time translation app for Android that runs locally

Native-LLM-for-Android

Demonstration of running a native LLM on Android device.

ollama

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

Qwen2

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

ChatTTS

A generative speech model for daily dialogue.

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

IC-Light

More relighting!

llama3

The official Meta Llama 3 GitHub site

ai-hub-models

The Qualcomm® AI Hub Models are a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.

roop

one-click face swap

Depth-Anything

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

inswapper

One-click Face Swapper and Restoration powered by insightface 🔥

InstantID

InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥

PhotoMaker

PhotoMaker [CVPR 2024]

Fooocus

Focus on prompting and generating

EfficientSAM

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

AnyText

Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

StreamDiffusion

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

OutfitAnyone

Outfit Anyone: Ultra-high quality virtual try-on for Any Clothing and Any Person

ChatGLM3

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

ml-neilfpp

DocShadow-SD7K

[ICCV 2023] A large-scale high-resolution dataset satisfies all important data features about document shadow, covers a large number of document shadow images.

facechain

FaceChain is a deep-learning toolchain for generating your Digital-Twin.

sd-webui-EasyPhoto

📷 EasyPhoto | Your Smart AI Photo Generator.

MiDaS

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

ZoeDepth

Metric depth estimation from a single image

Firefly

Firefly: 大模型训练工具，支持训练Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

ml-fastvit

This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization" ICCV 2023