We introduce a method for composing object-level visual prompts within a text-to-image
diffusion model. Our approach addresses the task of generating semantically coherent …

Personalized text-to-image generation has gained significant attention for its capability to
generate high-fidelity portraits of specific identities conditioned on user-defined prompts …

Recent advances in text-to-image personalization have enabled high-quality and
controllable image synthesis for user-provided concepts. However, existing methods still …

Large Vision Language Models (LVLMs) have significant potential to deliver personalized
assistance by adapting to individual users' unique needs and preferences. Personalization …

Text-to-image generation models can create high-quality images from input prompts.
However, they struggle to support the consistent generation of identity-preserving …

Recent advancements in image generation models have enabled personalized image
creation with both user-defined subjects (content) and styles. Prior works achieved …

We present BootComp, a novel framework based on text-to-image diffusion models for
controllable human image generation with multiple reference garments. Here, the main …

Finetuning-free personalized image generation can synthesize customized images without
test-time finetuning, attracting wide research interest owing to its high efficiency. Current …

Recent advancements in deep learning have significantly enhanced content-based retrieval
methods, notably through models like CLIP that map images and texts into a shared …