Picture for Dongnam Byun

Dongnam Byun

Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative Models

Add code
Dec 03, 2024
Figure 1 for Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative Models
Figure 2 for Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative Models
Figure 3 for Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative Models
Figure 4 for Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative Models
Viaarxiv icon