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.
Table 11 lists the 12 animals and 10 colors used to generate these prompts, with the full prompt list available in our core codebase
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.