FreeGraftor performs subject-driven text-to-image generation without training by cross-image feature grafting via semantic matching, position-constrained attention fusion, and a noise initialization strategy that preserves reference geometry.
Freecustom: Tuning-free customized image generation for multi-concept composition,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FreeGraftor: Training-Free Cross-Image Feature Grafting for Subject-Driven Text-to-Image Generation
FreeGraftor performs subject-driven text-to-image generation without training by cross-image feature grafting via semantic matching, position-constrained attention fusion, and a noise initialization strategy that preserves reference geometry.