PixelArtAI's repositories
Baidu-netdisk-AI-Image-processing-Challenge-demoire
百度网盘AI大赛——图像处理挑战赛：文档图像摩尔纹消除第2名方案
Video-Generation
Video-Generation-Show-Time
All-In-One-Deflicker
[CVPR2023] Blind Video Deflickering by Neural Filtering with a Flawed Atlas
AnimatedDrawings
Code to accompany "A Method for Animating Children's Drawings of the Human Figure"
Awesome-Chinese-LLM
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
bark-audio-tts
🔊 Text-Prompted Generative Audio Model
BiSCI-BNN
A Toolbox for Binarized Spectral Compressive Imaging (NeurIPS 2023)
ChatGLM2-6B
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
ChatPaper
Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文总结+润色+审稿+审稿回复
DragGAN
Online Demo and Implementation of DragGAN - "Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold" （DragGAN 全功能实现，在线Demo，与本地部署试用，代码、模型已全部开源）
dysample
(ICCV'23) Learning to Upsample by Learning to Sample
ERNIE-Bot-SDK
The ERNIE Bot Python library provides convenient access to the ERNIE Bot API.
gradio
Create UIs for your machine learning model in Python in 3 minutes
imgui
Fork from imgui(docking/viewport) with vulkan image rendering support. many widgets and addons.
learning-notebook
个人学习资料整理
MetaPortrait
[CVPR 2023] MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation
nndeploy
nndeploy是一款最新上线的支持多平台、简单易用、高性能的机器学习部署框架，一套实现可在多端(云、边、端)完成模型的高性能部署。
PromptIR
PromptIR: Prompting for All-in-One Blind Image Restoration
pytorch-msssim
Fast and differentiable MS-SSIM and SSIM for pytorch.
Rep-Block-Enhance
SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-Time Performance on Mobile Device, in ICCV 2023
SadTalker
[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
so-vits-svc-4.1-Stable
SoftVC VITS Singing Voice Conversion
so-vits-svc-5.0
Core Engine of Singing Voice Conversion & Singing Voice Clone
The-Art-of-Linear-Algebra
Graphic notes on Gilbert Strang's "Linear Algebra for Everyone"
Track-Anything
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything and XMem.
video2dataset
Easily create large video dataset from video urls
VSET
基于Vapoursynth的图形化视频批量压制处理工具，超分辨率，补帧，vs滤镜一应俱全。