SDV: Visions Series

SDV (Stable Diffusion Visions) is an art project that seeks to document a chain of AI-generated graphics that are loosely connected. Each vision has a unique ID (an integer, starting at 0) and a title, and will be printed out once.

StableDiffusion: AI Phone Wallpapers

These are high quality AI-generated phone wallpapers made with StableDiffusion (a text-to-image model), using various prompts I’ve found to be aesthetically pleasing. Most have a resolution of ~1500x3000, but they vary slightly.

StableDiffusion: AI Posters (36x24in)

These are high quality AI-generated posters made with StableDiffusion (a text-to-image model), using various prompts I’ve found to be aesthetically pleasing. There are some of different sizes, which are organized on this page:

StableDiffusion: Open-Source Text-To-Image

Stable Diffusion, an open-source AI text-image model, was recently released. It’s notable for being the first “big-boy” (i.e. high fidelity, state-of-the-art quality) model that is completely freely available.

SMCEFR Dataset (Data Challenge)

I was asked to sponsor a dataset for ORNL’s Smoky Mountain Conference, in addition to posing a number of challenge questions. Then, researchers of all levels (undergrad to post-grad and beyond) were invited to investigate the dataset and write papers about their findings.

DALL-E 2 (or, the end of Human Security and Artistic Dominance)

SINGULARITY ALERT - OpenAI recently announced DALL-E 2, which is a revolutionary neural network that can create images given just a plaintext caption. While DALL-E 2 is currently under closed beta (I’m on the waitlist), the results are already impressive and demonstrate just how fast Artificial Intelligence (AI) and Machine Learning (ML) are advancing in 2022.

Art: Fractals

These are some various renderings of fractals that I’ve done, using software I’ve written

Art: ML/AI Generated

These are some results from recent work on generating art using machine learning and artificial intelligence. Most of the following are using VQGAN+CLIP, or just CLIP alone.

Jekyll Project: cade.site

Recently, i’ve been cleaning house on old projects and websites – and i realized i wanted to get this blog going as a technical blog. What better way than by making a blog post about the blog itself? The full source code for my website is available on GitHub, and hosted at cade.site

DIY: Fast 'isprime()' for Primality Testing (using Miller-Rabin)

We’ve all had to include a little isprime() function in our code, right? (well, most people reading my blog probably have). In this article i provide an implementation of a primality test (in C) that is quite a bit faster for larger values, and is still easily embeddable and usable within existing applications

Dense Linear Algebra Algorithms on AMD GPUs

I’m excited to have recently published my first journal paper with ICL! You can check it out on HGPU. TL;DR: we port a math library to AMD GPUs and get much better performance than AMD’s existing vendor libraries

DIY: Gamma and Zeta Function Implementation

in developing my language, kscript, i wanted to have the Riemann Zeta Function and Gamma Function available as part of the standard library. so, i implemented it!