I am a highschool student studying computer science. I am intrested in the recent developments in Generative AI. At the moment ive been working with Stable difusion inside the Automatic1111 webui.
Recently i have been working on a computer vision based project that uses the YOLLOv8 image detection model. the project will be used as a tool for asisting those with a visual imparment. this project is my personal project this year at school but i also work on it outside of school and even before the personal project.the ultimate goal is to create a tool that can detect objects distance from the camera based on a single video stream. we then combine this with a segmentation model to understand what the object is and where it is in relation to the camera. to comunicate this to the user we will use a combination of auditory feedback filtered by a LLM and haptic feedback through a virtual reality haptic vest. I work quite a bit on video projects that utilize Generative AI wich I post on my Youtube portfolio: https://www.youtube.com/@HensonLiga this is where i showcase my videos. the most recent is a AI Cover song that i made using RVC (Retreval Based Voice Conversion) a recent AI voice conversion repo. the other videos utilize the stable difusion prosses using the Automatic1111 open source webui avalable on github. all of the tools I use will be linked bellow. In some unreleced videos I have been working on using high resolution depth maps to create 3d meshes in blender to create limmited 3d animations that i can costomise with keyframes. https://github.com/FantasticMrCat42/FantasticMrCat42/assets/129550102/4c4f2266-38a4-4ab8-b968-6d43863ff730 ## Robotics Competitions recently i attended GCER or the Global Confrence on Educational Robotics. At this competition aside from competing I met meny teams from around the word. for example the austrian team called RIP is one of the teams I am still in contact with and have asked robotics questions about. with my recent AI knolage I also Plan on Creating depth maps using AI and the CV2 open source computer vison library in my new robot. ## Tools I Use - https://github.com/AUTOMATIC1111/stable-diffusion-webui - https://github.com/facebookresearch/audiocraft - https://github.com/s0md3v/roop - https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/docs