Mochi Liu's repositories
stable-diffusion-docker
this is my personal playground for stable diffusion and related models
salmon-demo
Demos Canny segmentation and tracking
alpaca-lora-docker
Instruct-tune LLaMA on consumer hardware
BVAE-tf
Disentangled Variational Auto-Encoder in TensorFlow / Keras (Beta-VAE)
CLIP-Guided-Diffusion
Just playing with getting CLIP Guided Diffusion running locally, rather than having to use colab.
clip-guided-diffusion-1
A CLI tool/python module for generating images from text using guided diffusion and CLIP from OpenAI.
ControlNet
Let us control diffusion models
disco-diffusion-docker
repo for playing around with dockerized disco diffusion
liu-temporal-processing
Source code associated with Liu et al "Temporal processing and context dependency in C. elegans response to mechanosensation"
disentangled_vae
Replicating "Understanding disentangling in β-VAE"
Dreambooth-SD-optimized
Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion
LinkNode-R4-Controlled-By-Amazon-Alexa
This code will create four FauxMo smart-home devices that emulate Belkin We-Mo switches. The unmodified version of this code is originally by kakopappa and can be found at https://github.com/kakopappa/arduino-esp8266-alexa-multiple-wemo-switch/tree/master/wemos.
local_conv_music_generation
NIPS 2018 Workshop: Music Generation with Local Connected Convolutional Neural Network
magenta
Magenta: Music and Art Generation with Machine Intelligence
matlab-lcr
LightCrafter 4500 API Bindings for MATLAB
MCC
Multiview Compressive Coding for 3D Reconstruction
mochiliu.github.io
:triangular_ruler: Jekyll theme for building a personal site, blog, project documentation, or portfolio.
musicgen-docker
just a docker to play around with musicgen
rectified_from_bag
Take in a set of rosbags and output rectified images
text-generation-webui
A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, Pythia, OPT, and GALACTICA.
VideoMAEv2
[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
VQGAN-CLIP
Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.
VQGAN-CLIP-Docker
Zero-Shot Text-to-Image Generation VQGAN+CLIP Dockerized
wav2vec2-live
A live speech recognition using Facebooks wav2vec 2.0 model.