Cross Attention Visualization And Prompt Token Attribution

via “cross-attention visualization and prompt token attribution”

text-to-image model by undefined. 15,28,067 downloads.

Unique: Exposes cross-attention maps from the UNet's attention layers, enabling token-to-pixel attribution; requires custom pipeline code but provides fine-grained insight into prompt-image alignment

vs others: More detailed than saliency maps or gradient-based attribution; requires more engineering effort than black-box approaches but enables interpretability and custom control