Head Relevance Vectors, built by counting which attention head best matches each of 34 concept words, reveal concept-specific cross-attention head patterns and enable targeted concept steering in Stable Diffusion.
Zero-shot image-to-image translation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative Models
Head Relevance Vectors, built by counting which attention head best matches each of 34 concept words, reveal concept-specific cross-attention head patterns and enable targeted concept steering in Stable Diffusion.