MAG-Edit: Localized Image Editing in Complex Scenarios via Mask-Based Attention-Adjusted Guidance (ACM MM2024)

Taming FLUX for Image Inversion & Editing; OpenSora for Video Inversion & Editing! (Official implementation for Taming Rectified Flow for Inversion and Editing.)

Official code for "Probabilistic Concept Bottleneck Models (ICML 2023)"

collection of diffusion model papers categorized by their subareas

🐙 Guides, papers, lecture, notebooks and resources for prompt engineering

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models (LLM-grounded Diffusion: LMD, TMLR 2024)

The official codes for the ICCV2021 Oral presentation "Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework"

Text-To-Image Generation with Chinese Characters

Codebase for Embedding Propagation: Smoother Manifold for Few-Shot Classification. This is a ServiceNow Research project that was started at Element AI.

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

Reproduction of the CVPR'21 paper Distilling Knowledge via Knowledge Review for the ML Reproducibility Challenge 2021

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)

Semi-supervised Semantic Segmentation with Directional Context-aware Consistency (CVPR 2021)

[AAAI 2023] Official PyTorch Code for "Curriculum Temperature for Knowledge Distillation"

A collection of resources and papers on Diffusion Models

Build convolutional neural network (CNN) accelerator based on FPGA

AI projects in python, mostly Jupyter notebooks.

Digital image processing is introduced in detail. all code are implementing by OpenCV 3.4 and C++

recommend now (rec_now) 是一个推荐算法的基础库，目的在于简化推荐模型的开发。 本项目基于tensorflow2和python3实现，兼容使用tensorflow1.x API的[无量训练框架](https://git.woa.com/deep_learning_framework/NumerousTensorFlow)，并在生产环境中得到了充分验证。 其中，基于in-…

A contrastive learning based semi-supervised segmentation network for medical image segmentation

A curated list of awesome papers on dataset distillation and related applications.

ICCV2021 (Oral) - Exploring Cross-Image Pixel Contrast for Semantic Segmentation