SCDiff adds a parametric spatial weighting module and dual similarity-diversity loss to diffusion-based text-to-image models to increase visual novelty while preserving semantic alignment.
Sdxl-lightning: Progressive adversarial diffusion distillation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Self-Creative Text-to-Object Generation using Semantic-Aware Spatial Weighting
SCDiff adds a parametric spatial weighting module and dual similarity-diversity loss to diffusion-based text-to-image models to increase visual novelty while preserving semantic alignment.