Guardado en:
Detalles Bibliográficos
Autores principales: Ohanyan, Marianna, Manukyan, Hayk, Wang, Zhangyang, Navasardyan, Shant, Shi, Humphrey
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2406.04032
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Tabla de Contenidos:
  • We present Zero-Painter, a novel training-free framework for layout-conditional text-to-image synthesis that facilitates the creation of detailed and controlled imagery from textual prompts. Our method utilizes object masks and individual descriptions, coupled with a global text prompt, to generate images with high fidelity. Zero-Painter employs a two-stage process involving our novel Prompt-Adjusted Cross-Attention (PACA) and Region-Grouped Cross-Attention (ReGCA) blocks, ensuring precise alignment of generated objects with textual prompts and mask shapes. Our extensive experiments demonstrate that Zero-Painter surpasses current state-of-the-art methods in preserving textual details and adhering to mask shapes.