EfficientViT is a new family of vision models for efficient high-resolution vision.

MAT: Mask-Aware Transformer for Large Hole Image Inpainting

Segment Anything in High Quality [NeurIPS 2023]

SSSegmentation: An Open Source Supervised Semantic Segmentation Toolbox Based on PyTorch.

High-resolution models for human tasks.

An official implementation of "Hulk: A Universal Knowledge Translator for Human-Centric Tasks"

🧑‍🚀 全世界最好的LLM资料总结 | Summary of the world's best LLM resources.

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

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

Use PEFT or Full-parameter to finetune 400+ LLMs (Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, ...) or 100+ MLLMs (Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, Inter…

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

This repo contains code and a pre-trained model for clothes segmentation.

A curated publication list on open vocabulary semantic segmentation and related area (e.g. zero-shot semantic segmentation) resources..

DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data (NeurIPS 2023 Spotlight) / / / / When Does Perceptual Alignment Benefit Vision Representations? (NeurIPS 2024)

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

Official PyTorch implementation of "ML-Decoder: Scalable and Versatile Classification Head" (2021)

Official Pytorch Implementation of: "Asymmetric Loss For Multi-Label Classification"(ICCV, 2021) paper

Official implementation of paper "Query2Label: A Simple Transformer Way to Multi-Label Classification".

Official code release for ICCV2023 paper AG3D: Learning to Generate 3D Avatars from 2D Image Collections

Pytorch demo code and models for Multi-HMR

💬 An extensive collection of exceptional resources dedicated to the captivating world of talking face synthesis! ⭐ If you find this repo useful, please give it a star! 🤩

[CVPR 2024] Official Code for "AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation

A generative speech model for daily dialogue.

SMPLitex – Official implementation

Person Image Synthesis via Denoising Diffusion Model (CVPR 2023)

Implementation code：Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models