Name: Max Ku
Type: User
Company: ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
Bio: You're doing what you love.
Isn't that that enough? Isn't that that enough?
Twitter: vinesmsuic
Location: ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
Blog: https://kuwingfung.github.io/
Max Ku's Projects
EIE3109 Assignment Animation Game
This repo will implement a series of anime stylized algorithm. AnimeGAN, White-box Cartoonize.. etc
Perform Video Editing with only one image. Now with gradio demo
A curated list of recent diffusion models for video generation, editing, restoration, understanding, etc.
A fun discord bot built with discord.js, using Heroku to host.
PyTorch implementation of "CartoonGAN: Generative Adversarial Networks for Photo Cartoonization" (CVPR 2018).
PyTorch - FID calculation with proper image resizing and quantization steps
This repository contains the code of the CVPR 2022 paper "Image Segmentation Using Text and Image Prompts".
Let us control diffusion models
Diffusion attentive attribution maps for interpreting Stable Diffusion.
How to setup, or use any depth cameras in ROS (Starter)
Diffusers training with mmengine
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
Enhance Your English Writing
This repository is the implementation of the paper "Flow-Based Image Abstraction" for course CS663 : Digital Image Processing.
👀 Eye Tracking library easily implementable to your projects
Create UIs for your machine learning model in Python in 3 minutes
EIE3320 Lab2
Recycle Kiosk (Java Gui) for school assignment. NetBeans environment.
(ICLR2024) Official Code for "ImagenHub: Standardizing the evaluation of conditional image generation models"
A Image Styliser to turn any image into an artwork. (Using TFHub pretrained model)
InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥
Official Code for "Intelligent Painter: Picture Composition With Resampling Diffusion Model" (ICIP 2023)
The Unified Machine Learning Framework
Japanese Stable Diffusion is a Japanese specific latent text-to-image diffusion model capable of generating photo-realistic images given any text input.