Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
2024-01-16
· ICLR 2024 spotlight ·
anchor
Findings
IC-1202
Stable Diffusion 1.5 and 2.1 exhibit a cropping failure mode where synthesized objects are cut off at image boundaries
IC-1203
Stable Diffusion 1.5 and 2.1 receive low user-preference win rates (7.91% and 6.71%) in a four-way comparison against SDXL
IC-1204
SD-VAE 1.x and SD-VAE 2.x achieve lower reconstruction quality than the new SDXL-VAE on COCO 2017