Open Source OCR Library for Text Recognition in Multiple Languages

Open Source OCR Library for Text Recognition in Multiple Languages

Introduction In the digital age, Optical Character Recognition (OCR) has become a key technology in many application scenarios. From automated document processing to information extraction from images, OCR technology plays an indispensable role. Today, we will delve into a powerful text recognition tool – the EasyOCR library. EasyOCR is an OCR library based on deep … Read more

Doubao User Guide: Make AI Your Super Assistant

Doubao User Guide: Make AI Your Super Assistant

Hello, everyone! This is “Doubao,” an AI application that aims to be an all-around assistant. Speaking of AI assistants, many of you have probably started using “Doubao” in various aspects of your life, such as learning English, creating travel itineraries, analyzing documents, and writing work reports. However, some friends have privately messaged us, reflecting on … Read more

In-Depth Guide To Kimi AI: Mastering Your Smart Assistant!

In-Depth Guide To Kimi AI: Mastering Your Smart Assistant!

Imagine having an assistant that can understand and process text up to 2 million words, accurately interpret the content of over 500 web pages, and within just a few months, attract more than 20.04 million daily active users. The leap from 200,000 words to 2 million words, from ordinary search to AI autonomous deep reasoning, … Read more

A Survey on Generative Diffusion Models

A Survey on Generative Diffusion Models

0. Introduction This article reviews deep generative models, particularly diffusion models, and how they endow machines with human-like imagination. Diffusion models show great potential in generating realistic samples, overcoming the posterior distribution alignment obstacles in variational autoencoders and alleviating the instability of adversarial objectives in generative adversarial networks. Diffusion models consist of two interconnected processes: … Read more

Shanghai Jiao Tong University Team Develops Diffusion Probability Model

Editor | Wang Duoyu Typesetting | Shui Chengwen Deep Learning assisted functional protein design is a novel method that meets the growing demand for new biocatalysts in scientific and industrial production contexts, promoting the rapid discovery and modification of efficient and specialized proteins, and expanding the research boundaries of protein engineering. By harnessing the power … Read more

NetEase AI Creative Workshop: Generate Images Online with Stable Diffusion

NetEase AI Creative Workshop: Generate Images Online with Stable Diffusion

Today, I want to introduce you to a particularly cool tool – the “NetEase AI Creative Workshop”. Recently, it has made our creative journey more convenient and fun by incorporating Stable Diffusion technology. If you are someone interested in image creation, or if you lack artistic talent but yearn to create a beautiful piece of … Read more

StableVideo: Generate Continuous Flicker-Free Videos Using Stable Diffusion

StableVideo: Generate Continuous Flicker-Free Videos Using Stable Diffusion

Source: DeepHub IMBA This article is approximately 2100 words long and is recommended to be read in 7 minutes. This article summarizes the paper by Chai et al., which proposes a new method that enables diffusion models to edit videos with high temporal consistency. Using Stable Diffusion to generate videos has always been a research … Read more

Stable Diffusion Sampling Speed Doubled! Diffusion Model Sampling Algorithm Requires Only 10 to 25 Steps

Stable Diffusion Sampling Speed Doubled! Diffusion Model Sampling Algorithm Requires Only 10 to 25 Steps

Professor Zhu Jun from Tsinghua University’s Computer Science Department, leading the TSAIL team, proposed DPM-Solver (NeurIPS 2022 Oral, approximately the top 1.7%) and DPM-Solver++, which has pushed the rapid sampling algorithm of diffusion models to the extreme: achieving high-quality sampling with only 10 to 25 steps without additional training. This year, one of the most … Read more

Understanding Stable Diffusion Through 35 Images

Understanding Stable Diffusion Through 35 Images

Author|Jay Alammar Translated by|Yang Ting, Xu Jiayu Recently, AI image generation has attracted attention, capable of generating exquisite images based on text descriptions, significantly changing the way people create images.Stable Diffusion is a high-performance model that generates higher quality images, runs faster, and consumes fewer resources and memory, marking a milestone in the field of … Read more

Using Stable Diffusion Image Inpainting to Generate Your Own Object Detection Dataset

Using Stable Diffusion Image Inpainting to Generate Your Own Object Detection Dataset

Click the above “Beginner’s Guide to Computer Vision”, select “star” or “pin” Heavyweight content delivered promptly Author: Rédigé par Gabriel Guerin Translated by: ronghuaiyang Source: AI Park Introduction In some cases, collecting data from various scenes can be challenging. This article presents a method. Deep learning models require a significant amount of data to achieve … Read more