Skip to content

Style Transfer on images using Transformers. Project done as a part of the 'Computer Vision' course in IIIT Hyderabad (Spring 2024)

Notifications You must be signed in to change notification settings

sarthakchittawar/StyTR-reimplementation

Repository files navigation

Reimplementation of Sty-TR

(style transfer using transformers)

Original Paper
Original Codebase

contributors:
Sarthak Chittawar
Sanika Damle

Training

python3 train.py + additional arguments as specified in the file

Using the model with CLIP

python3 style_with_clip.py + change file paths in the file

Calculating loss if content, style and final image given

python3 loss.py + change file paths in the file

Directory Structure

├── README.md
├── transformer files
├── clip
│   ├── finetuneclip.py (finetune clip)
│   ├── metadata.json (metadata of all the wikiart images)
│   ├── styles.txt (different styles)
│   ├── styles_desc.txt (description of styles)
├── content (content images)
├── style (style images)
├── output (output images)
├── videos
│   ├── video_Stabilisztion.ipynb (python notebook with all the relevant code)
│   ├── video files

About

Style Transfer on images using Transformers. Project done as a part of the 'Computer Vision' course in IIIT Hyderabad (Spring 2024)

Topics

Resources

Stars

Watchers

Forks

Packages

No packages published