Kevin L's starred repositories
grokfast-pytorch
Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"
fullcontrol
Python version of FullControl for toolpath design (and more) - the readme below is best source of information
Grounded-Segment-Anything
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
lang-segment-anything
SAM with text prompt
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
OpenVR-Tracker-Websocket-Driver
A driver to connect to SteamVR using a websocket interface and create trackers and get device data.
diffusers_stablediff_conversion
converts huggingface diffusers stablediffussion models to stablediffusion ckpt files usable in most opensource tools
CrossAttentionControl
Unofficial implementation of "Prompt-to-Prompt Image Editing with Cross Attention Control" with Stable Diffusion
Merge-Stable-Diffusion-models-without-distortion
Adaptation of the merging method described in the paper - Git Re-Basin: Merging Models modulo Permutation Symmetries (https://arxiv.org/abs/2209.04836) for Stable Diffusion
stable-diffusion
Optimized Stable Diffusion modified to run on lower GPU VRAM
stable-diffusion
A latent text-to-image diffusion model
imagen-pytorch
Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch
OpenXR-Toolkit
A collection of useful features to customize and improve existing OpenXR applications.
JLC2KiCad_lib
JLC2KICAD_lib is a python script that generate a component library (schematic, footprint and 3D model ) for KiCad from the JLCPCB/easyEDA library.
arduino-audio-tools
Arduino Audio Tools (a powerful Audio library not only for Arduino)
glide-text2im
GLIDE: a diffusion-based text-conditional image synthesis model. Now with example files for local running.
feed_forward_vqgan_clip
Feed forward VQGAN-CLIP model, where the goal is to eliminate the need for optimizing the latent space of VQGAN for each input prompt
Real-ESRGAN
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
VQGAN-CLIP
Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.
ASWX1-FW-MOD
Artillery Sidewinder X1 Firmware Mod based on Marlin 2.0.x