Guardado en:
Detalles Bibliográficos
Autores principales: Swami, Kunal, Chittersu, Raghu, Adlinge, Pranav, Irny, Rajeev, Doodekula, Shashavali, Shukla, Alok
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2502.10258
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908225481211904
author Swami, Kunal
Chittersu, Raghu
Adlinge, Pranav
Irny, Rajeev
Doodekula, Shashavali
Shukla, Alok
author_facet Swami, Kunal
Chittersu, Raghu
Adlinge, Pranav
Irny, Rajeev
Doodekula, Shashavali
Shukla, Alok
contents We present PromptArtisan, a groundbreaking approach to multi-instruction image editing that achieves remarkable results in a single pass, eliminating the need for time-consuming iterative refinement. Our method empowers users to provide multiple editing instructions, each associated with a specific mask within the image. This flexibility allows for complex edits involving mask intersections or overlaps, enabling the realization of intricate and nuanced image transformations. PromptArtisan leverages a pre-trained InstructPix2Pix model in conjunction with a novel Complete Attention Control Mechanism (CACM). This mechanism ensures precise adherence to user instructions, granting fine-grained control over the editing process. Furthermore, our approach is zero-shot, requiring no additional training, and boasts improved processing complexity compared to traditional iterative methods. By seamlessly integrating multi-instruction capabilities, single-pass efficiency, and complete attention control, PromptArtisan unlocks new possibilities for creative and efficient image editing workflows, catering to both novice and expert users alike.
format Preprint
id arxiv_https___arxiv_org_abs_2502_10258
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PromptArtisan: Multi-instruction Image Editing in Single Pass with Complete Attention Control
Swami, Kunal
Chittersu, Raghu
Adlinge, Pranav
Irny, Rajeev
Doodekula, Shashavali
Shukla, Alok
Computer Vision and Pattern Recognition
Human-Computer Interaction
We present PromptArtisan, a groundbreaking approach to multi-instruction image editing that achieves remarkable results in a single pass, eliminating the need for time-consuming iterative refinement. Our method empowers users to provide multiple editing instructions, each associated with a specific mask within the image. This flexibility allows for complex edits involving mask intersections or overlaps, enabling the realization of intricate and nuanced image transformations. PromptArtisan leverages a pre-trained InstructPix2Pix model in conjunction with a novel Complete Attention Control Mechanism (CACM). This mechanism ensures precise adherence to user instructions, granting fine-grained control over the editing process. Furthermore, our approach is zero-shot, requiring no additional training, and boasts improved processing complexity compared to traditional iterative methods. By seamlessly integrating multi-instruction capabilities, single-pass efficiency, and complete attention control, PromptArtisan unlocks new possibilities for creative and efficient image editing workflows, catering to both novice and expert users alike.
title PromptArtisan: Multi-instruction Image Editing in Single Pass with Complete Attention Control
topic Computer Vision and Pattern Recognition
Human-Computer Interaction
url https://arxiv.org/abs/2502.10258