Diffusion Probabilistic Models and Text-to-Image Generation

Photorealistic Generation of Anything You Can Think of

Figure 1. Text-to-Image Generation. Image made by author.

If you are an avid follower of the newest CV papers, you would be surprised at the stunning results of generative networks in creating images. Many of the previous literature were based on the groundbreaking generative adversarial network (GAN) idea, but that’s no longer the case for recent papers. In fact, if you look closely at the newest papers such as ImageN and Staple Diffusion, you will constantly see a unfamiliar term: diffusion probabilistic model.

This article dives in to the very basics of the newly trending model, how it is learnt in a brief overview, and the exciting applications that have soon followed.

Start by Gradually Adding Gaussian Noises…

Figure 2. Overview of Denoising Diffusion Probabilistic Models. Image Retrieved from: https://arxiv.org/abs/2006.11239.

Consider an image to which a small amount of Gaussian noise is added. The image may becomes a little noisy, but the original content can most likely still be recognised. Now repeat the step again and again; eventually the image would become almost a pure Gaussian noise. This is known asthe forward process of a diffusion…