by Harmeet | Jan 10, 2023 | Resources
Many people have been looking at alternatives to Google Colab and one great solution is Paperspace. You can create multiple notebooks and run up machines using GPUs that are available for free or charged by the hour. In this post I want to share my workflow of how I...
by Harmeet | Jan 7, 2023 | Resources
One of the ongoing challenges with AI generated art has been its inability to draw hands correctly. They are often deformed or have way too many fingers which really would detract from the artwork. Unless you were going for deformed hands then you are in heaven....
by Harmeet | Dec 12, 2022 | General
In the context of UX design, this technology could potentially be used to help designers quickly generate visual ideas for a design concept. For example, a designer could input a description of a desired user interface and use a text-to-image generation tool like...
by Harmeet | Dec 2, 2022 | Resources
A collection of images from Midjourney that demonstrate the recognised artist styles and their results on Midjourney (v4 model). These should help decide the style to invoke when prompting the AI to create your desired images. Note: these images below are not created...
by Harmeet | Nov 28, 2022 | Resources
Stable Diffusion 2.0 is the newest release from Stability.AI and has been out for couple of weeks. This latest version is out there so I put this post together to help you find related information about it in one place to get started quickly. Important Links Here are...
by Harmeet | Nov 24, 2022 | Resources
Paperspace is a great alternative to Google Colab and I have switched over to this completely while cancelling my Colab subscription. However you might feel disadvantaged because you loose the Google Drive integration which was possible via Colab Notebooks and is not...
by Harmeet | Nov 22, 2022 | General
With the various advancements in Stable Diffusion and AI models, it isn’t a surprise that we start to see specialised models coming out fine tuned to perform specific tasks. One such model called Halloween Diffusion has been created by @proximasan – one of...
by Harmeet | Nov 14, 2022 | General
Stable Diffusion is by far the most popular text-to-image creation model following Disco Diffusion which had been leading the charge until then. The AI space has made incredible leap in the last 10 months since I got started with it, the growth has been exponential...
by Harmeet | Nov 12, 2022 | General
Midjourney is one of the most popular AI Text-to-Image creation applications out there with millions of users world wide. I have been using Midjourney since the closed beta days when they started. However at the pace the platform has evolved in the first year of its...
by Harmeet | Oct 28, 2022 | Resources
CLIP Interrogator let’s you submit an image and have it figure out what prompt could have been used to create an image. CLIP has been used with various models in the past to provide feedback to AI if the image being generated is closely matching to the prompt or...