Fast Personalized Text-to-Image Syntheses With Attention Injection
This addresses the need for fast and editable personalized image generation for users of AI art tools, though it appears incremental as it builds on existing diffusion models.
The paper tackles the problem of slow and overfitting in personalized text-to-image generation by proposing a method that generates personalized images without fine-tuning, balancing text-image and identity consistency.
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 a prompt and a reference image, we merge the custom concept into generated images by manipulating cross-attention and self-attention layers of the original diffusion model to generate personalized images that match the text description. Comprehensive experiments highlight the superiority of our method.