Browse Teach Curate

Latent Diffusion and Stable Diffusion for Text-to-Image Generation

Diffusion generative models that run the noising and denoising process in a compressed latent space rather than pixel space, with a text encoder for conditioning, as popularized by Stable Diffusion, enabling efficient high-resolution image synthesis.

jeremy Video

Text to Image Generation using Conditional Latent Diffusion Models in Python

Diffusion models operate on a stochastic process where data generation is achieved by reversing a defined forward diffusion trajectory that gradually adds Gaussian noise until complete obfuscation. T…