A layout-free method that predicts subject regions from initial noise and refines them via guidance, improving multi-subject prompt alignment and layout diversity.
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
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
-
Be Decisive: Noise-Induced Layouts for Multi-Subject Generation
A layout-free method that predicts subject regions from initial noise and refines them via guidance, improving multi-subject prompt alignment and layout diversity.