Skip to content

Joejoedesu/CS236_analy

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 

Repository files navigation

CS236_analy

the analysis code for CS236 project

The machine learning training and inference were conducted on the Web UI platform: https://github.com/AUTOMATIC1111/stable-diffusion-webui The LoRA model and the report for the pixel-art style is in this shared Google Drive: https://drive.google.com/drive/folders/16BTs-uk4XDWfeYNcp65Tfj4kDn654zTf?usp=sharing

image_processing.py

frequency_analysis: compute the intensity of the high-frequency signals in the image using FFT. The input is the image name of the analysis target.

compute_gradient: use the Sobel filter to detect the edge for the given image.

plot_gradient: process, analyze, and visualize the edges detected in the image.

LoRA_analysis.py

It processes the LoRA training results in the safetensor file format and computes the subspace similarity between the selected targets.

Pixel_style_process.py

It converts a 512x512 image generated by the diffusion model into a 64x64 image usable as the game asset.

About

the analysis code for CS236 project

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages