yosun's repositories
papers
I realized recently that many of my papers are not accessible even if you are a pro subscriber to ACM, and the author of your own paper... i generally never have time to properly publish, and whatever i publish tends to be last minute before deadlines - academic papers i publish should be freely accessible.
character3d
a framework to allow AI devs to use any endpoint with a 3D talking head
AudioGPT
AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
cog-sdxl-lcm
Stable Diffusion XL training and inference with LCM LoRA as a cog model
com.openai.unity
A Non-Official OpenAI Rest Client for Unity (UPM)
com.rest.elevenlabs
A non-official Eleven Labs voice synthesis client for Unity (UPM)
elevenlabs-docs
Documentation for beta.elevenlabs.io
FaceSculpt
FaceSculpt changes the mesh vertices of various canonical-"eigenmodels" based on approximation from a user input image defining the face contours
modal-examples
Examples of programs built using Modal
Obsidian-academic-export
Turn your obsidian notes into academic papers.
obsidian-copy-as-latex
Quick plugin to be able to copy/paste from Obsidian/Markdown into a Latex document
remotevipxr
Remote XR VIP: AR AI Grimes chat bot - Converse in XR with any celebrity
scribble-diffusion
Turn your rough sketch into a refined image using AI
shap-e
Generate 3D objects conditioned on text or images
Snappy.Cards
Simple contact card with qr code generation and the data is only stored in the URL. Nothing will left the browser or can be ready by 3rd.
tarot_rws
The Rider-Waite Tarot Deck
TexPainter
TexPainter: Generative Mesh Texturing with Multi-view Consistency
triposr-texture-gen
Generates a texture for 3D models created by the TripoSR image-to-3D model
UnityApplePencil
Adds proper Apple Pencil support to Unity's InputSystem.
voicebox-pytorch
Implementation of Voicebox, new SOTA Text-to-speech network from MetaAI, in Pytorch
whisper.unity
Running speech to text model (whisper.cpp) in Unity3d on your local machine.