Bare-bones Diffusion Models

To understand how diffusion models generate images, I wrote code for training a bare-bones diffusion model without all the fanciness (no “epsilon parameterization”, no “Gaussian conditionals”, no sqrt_one_minus_alphas_cumprod). Based on that code, I trained a tiny diffusion model that generates 512×512 botanical images in your web browser. You can play with that demo here. So... how do diffusion models generate images? Why are these images as good as they are, and not better (or worse)? And... if we’re talking about conjuring new images from nothingness, what does “better” even mean? The image generation task is: given only some random noise as input, generate new images. Furthermore, generated images should look “real” (when compared to some reference dataset of, you know, actually-real images). Ideally, we want an image generator to exhibit: An archetypal “boring” task is image classification. It feels contrived (just look at those categories) and it also feels too easy (even a child

Bare-bones Diffusion Models Bare-bones Diffusion Models 05 February 2023 To understand how diffusion models generate images, I wrote code for training a bare-bones diffusion model without all the fanciness (no "epsilon parameterization", no "Gaussian conditionals", no sqrt_one_minus_alphas_cumprod ). Based on that code, I trained a tiny diffusion model that generates 512×512 botanical images in your web browser. You can play with that demo here . So... how do diffusion models generate images? Why are these images as good as they are, and not better (or worse)? And... if we're talking abo

saved by

• Linda
• Julian Quevedo

related reading

• What are Diffusion Models? | Lil'Loglilianweng.github.io
• ⭐️ Diffusion Modelsandrewkchan.dev
• Diffusion models from scratchchenyang.co
• What are Diffusion Models?lilianweng.github.io
• The Illustrated Stable Diffusion – Jay Alammar – Visualizing machine learning one concept at a time.jalammar.github.io
• But how do AI images and videos actually work? | Guest video by Welch Labsyoutube.com
• Diffusion is spectral autoregression – Sander Dielemansander.ai
• The Annotated Diffusion Modelhuggingface.co
• [2010.02502] Denoising Diffusion Implicit Modelsarxiv.org
• [2006.11239] Denoising Diffusion Probabilistic Modelsarxiv.org
• Towards demystifying the creativity of diffusion modelsresearch.google
• Elucidating the Design Space of Diffusion-Based Generative Models | PDFarxiv.org