CS492(C): Diffusion and Flow Models
Minhyuk Sung, KAIST, Fall 2025
Programming Assignments
Where to submit: KLMS
Assignment Links
- Assignment1 (DDPM / DDIM): https://github.com/KAIST-Visual-AI-Group/Diffusion-2025-Assignment1-DDPM-DDIM
- Assignment2 (DPM-Solver): https://github.com/KAIST-Visual-AI-Group/Diffusion-2025-Assignment2-DPMSolver
- Assignment3 (Flow Matching): https://github.com/KAIST-Visual-AI-Group/Diffusion-2025-Assignment3-Flow
Please carefully review the README of each assignment before you begin and check what you need to submit for each assignment.
Session Link
Along with the assignment sessions, we offer an additional optional programming session that will be helpful for preparing the course project.
- Session (Distillation / Synchronization): https://github.com/KAIST-Visual-AI-Group/Diffusion-2025-Demo
Prerequisite
You'll need basic programming skills in PyTorch to complete the programming assignments. We do not provide tutorials on PyTorch, but there are plenty of resources available on the Internet.
The programming assignments are designed as a barometer to assess whether you are prepared for the course project. If you find the programming assignments too challenging, this course might not be the right fit for you.
Google Colab
Please refer to the Google Colab quickstart guide at the following link:
AI Coding Assistant Tool Policy
You are allowed (and even encouraged) to utilize AI coding assistant tools, such as ChatGPT, Copilot, Codex, and Code Intelligence, for your programming assignments and projects. Utilizing AI coding assistant tools will not be deemed as plagiarism. However, it is still strictly prohibited to directly copy code from the Internet or from someone else. Doing so will lead to a score of zero and a report to the university.
Grading
- Check out the submission guidelines and grading policy of each assignment in the respective GitHub repository.
- Late submission: A 20% penalty for each late day.