Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
FLIPD
anchor
Findings
IC-330
Low local intrinsic dimension (LIDθ) of the learned manifold predicts memorization in Stable Diffusion v1.5, IDDPM, and StyleGAN2-ADA
[primary]
IC-331
In Stable Diffusion v1.5, specific tokens in text prompts drive memorization, and GPT-4-based perturbation of high-attribution tokens reduces SSIM similarity to training images while maintaining CLIP score
[primary]