A set of simple notebooks to create a clear understanding on Stable Diffusion aspects like sampling, architecture, CFG, attention layers, inverse scheduler, pivotal inversion, image reconsutrction and prompt2prompt editting which we utilise to achieve hyperreaslitic results to edit any real-world face and build a pipeline to build your own face app.

(You can skip to Chapter 7 if you are already familiar with the basics of SD)

Chapter 1: Using the pipeline to generate an image.
Chapter 2: Stable Diffusion architecture and components.
Chapter 3: Classifier-Free Guidance to enhance image generation.
Chapter 4: Override attention mechanisms to manipulate image generation process.
Chapter 5: Shared cross-attention layers between multiple images.
Chapter 6: DDIM-inversion and pivotal tuning for accurate image reconstruction.
Chapter 7: synthesise learnings to create an advanced facial feature editing system.