Diffusion models are autoencoders – Sander Dieleman

Diffusion models have become very popular over the last two years. There is an underappreciated link between diffusion models and autoencoders.

Diffusion models took off like a rocket at the end of 2019, after the publication of Song & Ermon’s seminal paper . In this blog post, I highlight a connection to another type of model: the venerable autoencoder. Diffusion models Diffusion models are fast becoming the go-to model for any task that requires producing perceptual signals, such as images and sound. They provide similar fidelity as alternatives based on generative adversarial nets (GANs) or autoregressive models, but with much better mode coverage than the former, and a faster and more flexible sampling procedure compared to the la

related reading

• What are Diffusion Models? | Lil'Loglilianweng.github.io
• Diffusion model - Wikipediaen.wikipedia.org
• ⭐️ Diffusion Modelsandrewkchan.dev
• Diffusion models from scratchchenyang.co
• Diffusion is spectral autoregression – Sander Dielemansander.ai
• Diffusion Models as a kind of VAE | Angus Turnerangusturner.github.io
• The Principles of Diffusion Modelsarxiv.org
• The Principles of Diffusion Modelsarxiv.org
• Generative modelling in latent space – Sander Dielemansander.ai
• [2006.11239] Denoising Diffusion Probabilistic Modelsarxiv.org
• Diffusion is not necessarily Spectral Autoregression | Fabian Falckfabianfalck.com
• The Annotated Diffusion Modelhuggingface.co