Highly Personalized Text Embedding for Image Manipulation by Stable Diffusion
This method addresses the problem of practical image personalization for users by offering a simpler and more efficient alternative to existing approaches, though it appears incremental in improving personalization techniques.
The paper tackles the challenge of preserving and manipulating image content and identity in diffusion models by introducing a highly personalized text embedding approach that decomposes the CLIP embedding space, enabling complex semantic edits with just a single image and target text without model fine-tuning.
Diffusion models have shown superior performance in image generation and manipulation, but the inherent stochasticity presents challenges in preserving and manipulating image content and identity. While previous approaches like DreamBooth and Textual Inversion have proposed model or latent representation personalization to maintain the content, their reliance on multiple reference images and complex training limits their practicality. In this paper, we present a simple yet highly effective approach to personalization using highly personalized (HiPer) text embedding by decomposing the CLIP embedding space for personalization and content manipulation. Our method does not require model fine-tuning or identifiers, yet still enables manipulation of background, texture, and motion with just a single image and target text. Through experiments on diverse target texts, we demonstrate that our approach produces highly personalized and complex semantic image edits across a wide range of tasks. We believe that the novel understanding of the text embedding space presented in this work has the potential to inspire further research across various tasks.