This Python script gradually reduces the quality and colors of all .png's in the same directory until a target size is reached.

Use a machine vision model to watch a window.

Short scripts for image-to-text, text-to-sound, etc.

This is a work in progress exploration of generating knowledge graphs with LLMs, inspired by a post I read on towardsdatascience.com.

A Python script for visualizing nodes with the networkx library.

Python script for generating a QR code.

This is a cheat sheet of animations showing what the various 3D translation and rotation settings do in Deforum Stable Diffusion.

My tentative work flow for running Deep Floyd IF locally for image generation.

This is my tentative workflow for using this repository to animate static images using a driving video.

TheraFit is a personal project utilizing a Large Language Model to enhance the process of matching clients with therapists.

Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.

I've notice that a lot of phishing emails use hexadecimal strings to obfuscate their JavaScript. These are some Python scripts useful for identifying where form actions are POSTing to.

GitHub Repository

During installation, I ran into an issue where the CUDA package wasn't found. Had to modify environment.yaml to:

 1name: midas-py310
 2channels:
 3  - pytorch
 4  - defaults
 5dependencies:
 6  - nvidia::cuda-toolkit=11.7.0
 7  - python=3.10.8
 8  - pytorch::pytorch=1.13.0
 9  - torchvision=0.14.0
10 …

"The official Tensorflow 2 implementation of our high quality frame interpolation neural network. We present a unified single-network approach that doesn't use additional pre-trained networks, like optical flow or depth, and yet achieve state-of-the-art results. We use a multi-scale feature extractor that shares the same convolution weights across the scales. Our model is trainable from frame triplets alone."

Stable Diffusion is an image generation technique that uses a diffusion process to iteratively generate images. It starts with a noise image and applies a series of transformations to it, where each transformation adds a little bit of noise to the image. These transformations are repeated over multiple time steps, and the amount of noise added is gradually decreased over time. This process smooths out the noise and generates a high-quality image. The stability of the diffusion process is maintained by scaling the added noise based on the image's current state, preventing the image from diverging or collapsing into a uniform color. Stable Diffusion is a powerful and versatile image generation technique that can produce realistic, high-resolution images with fine details and a wide range of styles.