✳flâneur — a map of the web's best reading
What are Diffusion Models?
lilianweng.github.io · 9 words · saved by 5 readers
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.
Explore this link on the map →