Fast Personalized Text-to-Image Syntheses With Attention Injection

arXiv:2403.11284v1 Announce Type: new
Abstract: Currently, personalized image generation methods mostly require considerable time to finetune and often overfit the concept resulting in generated images that are similar to custom concepts but difficult to edit by prompts. We propose an effective and fast approach that could balance the text-image consistency and identity consistency of the generated image and reference image. Our method can generate personalized images without any fine-tuning while maintaining the inherent text-to-image generation ability of diffusion models. Given …

abstract arxiv attention balance concept concepts cs.cv edit generated identity image image generation images personalized prompts text text-image text-to-image type