AI RESEARCH
FreeGraftor: Training-Free Cross-Image Feature Grafting for Subject-Driven Text-to-Image Generation
arXiv CS.CV
•
ArXi:2504.15958v5 Announce Type: replace Subject-driven image generation aims to synthesize novel scenes that faithfully preserve subject identity from reference images while adhering to textual guidance. However, existing methods struggle with a critical trade-off between fidelity and efficiency. Tuning-based approaches rely on time-consuming and resource-intensive, subject-specific optimization, while zero-shot methods often fail to maintain adequate subject consistency. In this work, we propose FreeGraftor, a