Project: specify and test a conditional image generator
Build a diffusion generator for 8×8 pictures in NumPy, ask it for squares, and watch it earn perfect scores by photocopying its training set. Then catch it.
Lesson overview
Build a diffusion generator for 8×8 pictures in NumPy, ask it for squares, and watch it earn perfect scores by photocopying its training set. Then catch it.
What you’ll explore
- Build a tiny class-conditional diffusion generator, and evaluate its outputs separately for following the condition, variety, image quality, and copying of training images.
Original explanations, connected to the research.
Denoising Diffusion Probabilistic Models (Ho, Jain & Abbeel, 2020)Extracting Training Data from Diffusion Models (Carlini et al., 2023)High-Resolution Image Synthesis with Latent Diffusion Models (Rombach et al., 2022)Prepare a project review
Give someone the context to challenge your thinking.
Download the authored brief, deliverables, and review criteria with your notes. Use the worksheet for self or peer review. Project artifacts are ungraded here, and this review does not award mastery credit.
Suggest a correction
A precise note can make an explanation better.
Choose the scene and describe what needs attention. Download a feedback file to share through a channel you already use. This page does not send feedback or connect you with a reviewer.