Name: 凪咲
Type: User
Company: MaidLand
Bio: Student, interested in origami (making paper ball), beginner on programming, beginner on Japanese. / 学生,喜欢折纸,编程初学者,日语初学者 / 学生、趣味は折り紙、プログラミング初心者、日本語初心者
Location: Guangzhou, China
Blog: https://space.bilibili.com/7528659
凪咲's Projects
Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
Unofficial Implementation of Animate Anyone
A High-Quality Real Time Upscaler for Anime Video
A high performance anime upscaler
Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, etc. Also support StyleGAN2, DFDNet.
gitbook格式的博客
Python client for Baidu Yun (Personal Cloud Storage) 百度云/百度网盘Python客户端
A webui for chatbot
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
A programme calculates the combination in python
Let us control diffusion models
[CVPR 2023] DPE: Disentanglement of Pose and Expression for General Video Portrait Editing
Official Code for DragGAN (SIGGRAPH 2023)
Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution
Code for "The Face of Art: Landmark Detection and Geometric Style in Portraits"
Using modified BiSeNet for face parsing in PyTorch
FcaNet: Frequency Channel Attention Networks
This repository contains the source code for the paper First Order Motion Model for Image Animation
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
[ICLR 22] Latent Image Animator: Learning to Animate Images via Latent Space Navigation
Official implementation of "LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching"
A reference containing Styles and Keywords that you can use with MidJourney AI. There are also pages showing resolution comparison, image weights, and much more!
Minum Path Sum Problem
An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
The best way to write secure and reliable applications. Write nothing; deploy nowhere.