PiCo improves text-to-image alignment by scoring and selecting initial noise seeds with CLIPSeg-based global and concept scores, then modulating cross-attention maps with CLIPSeg pixel masks and exclusive masks.
Training-free layout control with cross-attention guidance,
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
-
PiCo: Enhancing Text-Image Alignment with Improved Noise Selection and Precise Mask Control in Diffusion Models
PiCo improves text-to-image alignment by scoring and selecting initial noise seeds with CLIPSeg-based global and concept scores, then modulating cross-attention maps with CLIPSeg pixel masks and exclusive masks.