Skip to content

GagDrag/ThreadShift

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

ThreadShift

Segmentation, Image Editing and Generation with the Aid of Stable Diffusion

Course Project (TYITA B1 G2)


Table of Contents


Introduction

ThreadShift is a project that leverages state-of-the-art models like CLIP and Stable Diffusion to perform segmentation, image editing, and generation tasks. This project is part of the TYITA B1 G2 course and aims to utilize advanced deep learning techniques to create and manipulate images with precision and creativity.


Libraries Used

  • ftfy: Fixes broken Unicode text.
  • regex: Advanced regular expressions library for searching and manipulating text.
  • tqdm: Fast, extensible progress bar for loops and iterable objects.
  • diffusers by Hugging Face: Provides pretrained vision and audio diffusion models.
  • transformers by Hugging Face: APIs and tools for downloading and training state-of-the-art pretrained models.
  • scipy: Scientific computing library for optimization, integration, and other mathematical operations.
  • accelerate by Hugging Face: Training and inference at scale made simple, efficient, and adaptable.
  • Xformers: Optimizes transformers architecture.
  • opencv: Library of programming functions for real-time computer vision.

About

ThreadShift leverages advanced segmentation, image editing, and generation techniques with Stable Diffusion.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors