Diffusion models are autoencoders – Sander Dieleman
sander.ai · 2,990 words · saved by 1 readers
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
- Diffusion is spectral autoregression – Sander Dielemansander.ai
- What are Diffusion Models?lilianweng.github.io
- What are Diffusion Models? | Lil'Loglilianweng.github.io
- Diffusion Models as a kind of VAE | Angus Turnerangusturner.github.io
- Diffusion models from scratchchenyang.co
- Learning the integral of a diffusion model – Sander Dielemansander.ai
- Diffusion language models – Sander Dielemansander.ai
- Generative modelling in latent space – Sander Dielemansander.ai
- ⭐️ Diffusion Modelsandrewkchan.dev
- Diffusion model - Wikipediaen.wikipedia.org
- Diffusion Meets Flow Matchingdiffusionflow.github.io
- Diffusion is not necessarily Spectral Autoregression | Fabian Falckfabianfalck.com