JEDI minimizes Jensen-Shannon divergence between subject attention maps during diffusion sampling, reducing attribute mixing in generated images.
Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
JEDI: The Force of Jensen-Shannon Divergence in Disentangling Diffusion Models
JEDI minimizes Jensen-Shannon divergence between subject attention maps during diffusion sampling, reducing attribute mixing in generated images.