Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Localizing and Editing Knowledge In Text-to-Image Generative Models
2024-01-16
· ICLR 2024 poster ·
anchor
Findings
IC-982
In Stable Diffusion's UNET, visual attribute knowledge is distributed across multiple components with attribute-specific patterns, concentrated more in the up-block, and cross-attention layers are not the primary causal states
IC-983
In Stable Diffusion's CLIP text-encoder, knowledge about all visual attributes is localized to a single causal state: the first self-attention layer at the last subject token