What are Diffusion Models?
Diffusion models are a new type of generative models that are flexible enough to learn any arbitrarily complex data distribution while tractable to analytically evaluate the distribution. It has been shown recently that diffusion models can generate high-quality images and the performance is competitive to SOTA GAN.
[Updated on 2021-09-19: Highly recommend this blog post on score-based generative modeling by Yang Song (author of several key papers in the references)]. [Updated on 2022-08-27: Added classifier-free guidance, GLIDE, unCLIP and Imagen. [Updated on 2022-08-31: Added latent diffusion model. [Updated on 2024-04-13: Added progressive distillation, consistency models, and the Model Architecture section. So far, I’ve written about three types of generative models, GAN, VAE, and Flow-based models. They have shown great success in generating high-quality samples, but each has some limitations…
saved by
related reading
- What are Diffusion Models? | Lil'Loglilianweng.github.io
- ⭐️ Diffusion Modelsandrewkchan.dev
- Diffusion model - Wikipediaen.wikipedia.org
- Generative Modeling by Estimating Gradients of the Data Distribution | Yang Songyang-song.github.io
- Diffusion Models as a kind of VAE | Angus Turnerangusturner.github.io
- Diffusion models from scratchchenyang.co
- https://arxiv.org/pdf/2006.11239arxiv.org
- [2006.11239] Denoising Diffusion Probabilistic Modelsarxiv.org
- Diffusion Models in AI – Everything You Need to Know – Unite.AIunite.ai
- Yang Songyang-song.net
- The Principles of Diffusion Modelsarxiv.org
- The Principles of Diffusion Modelsarxiv.org