Dale Decatur
@daledecatur.bsky.social
CS PhD student @ UChicago
https://ddecatur.github.io/
https://ddecatur.github.io/
While our method can be applied to general purpose image generation, our method achieves the most dramatic savings (saves >75% vs standard diffusion) when examples are structurally similar. Some applications of this are style variation, subject variation, and virtual try-on.
6/
6/
October 22, 2025 at 8:23 PM
While our method can be applied to general purpose image generation, our method achieves the most dramatic savings (saves >75% vs standard diffusion) when examples are structurally similar. Some applications of this are style variation, subject variation, and virtual try-on.
6/
6/
Excited to share our #ICCV2025 work Reusing Computation in Text-to-Image Diffusion for Efficient Generation of Image Sets!
Our method generates large sets of images using significantly less compute than standard diffusion.
📎https://ddecatur.github.io/hierarchical-diffusion/
1/
Our method generates large sets of images using significantly less compute than standard diffusion.
📎https://ddecatur.github.io/hierarchical-diffusion/
1/
October 22, 2025 at 8:23 PM
Excited to share our #ICCV2025 work Reusing Computation in Text-to-Image Diffusion for Efficient Generation of Image Sets!
Our method generates large sets of images using significantly less compute than standard diffusion.
📎https://ddecatur.github.io/hierarchical-diffusion/
1/
Our method generates large sets of images using significantly less compute than standard diffusion.
📎https://ddecatur.github.io/hierarchical-diffusion/
1/