Understanding what happens under the hood when you run your spaCy code — About this article This article is part of the supporting material for the story — ‘Understanding NLP — from TF-IDF to transformers’ This article goes in detail on how to get started with spaCy. We will be focusing on the internals and not just writing some code and executing it. It means —…

An intuitive understanding of the torchvision library — basics to advanced ( Part 1/3 ) — What is torchvision? Torchvision is a library for Computer Vision that goes hand in hand with PyTorch. It has utilities for efficient Image and Video transformations, some commonly used pre-trained models, and some datasets ( torchvision does not come bundled with PyTorch, you will have to install it separately. )

What’s new in Midjourney v5 , How does the new version compare to the older ones ? — In this article, we will have a quick overview of what has changed and how the image output quality has evolved over these versions with some sample prompts and outputs. What’s new in v5 ? So here’s the official version of what’s new … and later in the article, we mention our unofficial findings on…

Quick Guide on creating flexible body pose using PoseMy.Art — Context If you are creating some graphic novels or comics, you will definitely want more control in determining the pose of your characters. Here is a quick way to create your own custom pose. But before that, here is a sample output. A sample This is the prompt we used for the above…

Using ControlNets with Stable Diffusion to get more control on the generated output images — What this Article is about ! Goodnews !! (for all AUTOMATIC1111 Stable diffusion UI users) There is now a plugin/extension for the ControlNet compatible with AUTOMATIC1111 . Here, we will walk you through what ControlNets are, what it can be used and detail out the initial guide to getting your Stable Diffusion ( SD ) working…

Some sample text-to-image prompts to get extraordinary results. — Why are we doing this ? We are so in love with the v4 ( version 4 ) of MidJourney . The quantum leaps with every version is phenomenal. Thanks team MidJourney ! ( We are so in love that, for every image we generate, we eat a petal of rose … and every day by…

How to get your work faster and more efficiently with the help of OpenAI’s ChatGPT — A few lines about GPT3.5 and ChatGPT A couple of days ago Elon Musk-Sam Altman backed OpenAI (founded 2015) released its latest release of the GPT LLM — now called GPT3.5 and along with it ChatGPT ( or sometimes called GPTChat ) . GPT3.5 is trained on ‘a blend of text and code’ published prior to Q4…

5 important developments in AI that prove that we haven't seen anything yet, explained. — Just in the last month ( November 2022 ) , the AI offerings have gone berserk !! It has become increasingly hard to catch up with the new and improved offerings AI has given. Here are 5 major break throughs which happened just last month ! 👉 Scroll down for…

Open source Image Editor with support for Stable Diffusion — About lama-cleaner Lama Cleaner is the latest opensource project that uses some of the text-to-Image tools like Stable Diffusion for Image editing. Their custom trained model is far superior to the traditional OpenCV methods. Now you can do context-aware-image editing which was…