“ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models” by Zhang, Dong, Tang, Huang, Huang, et al. …
Conference:
Type(s):
Title:
- ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models
Session/Category Title: Personalized Generative Models
Presenter(s)/Author(s):
Abstract:
Personalizing generative models offers a way to guide image generation with user-provided references. Current personalization methods can invert an object or concept into the textual conditioning space and compose new natural sentences for text-to-image diffusion models. However, representing and editing specific visual attributes like material, style, layout, etc. remains a challenge, leading to a lack of disentanglement and editability. To address this problem, we propose a novel approach that leverages the step-by-step generation process of diffusion models, which generate images from low- to high-frequency information, providing a new perspective on representing, generating, and editing images. We develop Prompt Spectrum Space, an expanded textual conditioning space, and a new image representation method called ProSpect. ProSpect represents an image as a collection of inverted textual token embeddings encoded from per-stage prompts, where each prompt corresponds to a specific generation stage (i.e., a group of consecutive steps) of the diffusion model. Experimental results demonstrate that ProSpect offers better disentanglement and controllability compared to existing methods. We apply ProSpect in various personalized attribute-aware image generation applications, such as image-guided or text-driven manipulations of materials, style, and layout, achieving previously unattainable results from a single image input without fine-tuning the diffusion models. Code: \url{github.com/zyxElsa/ProSpect}.
