A latent text-to-image diffusion model

High-Resolution Image Synthesis with Latent Diffusion Models

Taming Transformers for High-Resolution Image Synthesis

SVBRDF estimation from photographs for three different lighting conditions (directional, natural, and flash/no-flash illumination) is shown by refining a novel SVBRDF diffusion backbone model.

Code release for Inverse Global Illumination using a Neural Radiometric Prior

SVBRDF Estimation using a Physically-based Differentiable Renderer