activity
20212023
most citedPrompt-to-Prompt Image Editing with Cross Attention Control

367 citations · 369 across the 4 of their papers we have counts for

collaborators

6 papers

cs.CV20241 cited

PALP: Prompt Aligned Personalization of Text-to-Image Models

Moab Arar, Andrey Voynov, Amir Hertz +5

Content creators often aim to create personalized images using personal subjects that go beyond the capabilities of conventional text-to-image models. Additionally, they may want t…

cs.CV20243 cited

Style Aligned Image Generation via Shared Attention

Amir Hertz, Andrey Voynov, Shlomi Fruchter +1

Large-scale Text-to-Image (T2I) models have rapidly gained prominence across creative fields, generating visually compelling outputs from textual prompts. However, controlling thes…

cs.CV20231 cited

Delta Denoising Score

Amir Hertz, Kfir Aberman, Daniel Cohen-Or

We introduce Delta Denoising Score (DDS), a novel scoring function for text-based image editing that guides minimal modifications of an input image towards the content described in…

cs.CV2023

Word-As-Image for Semantic Typography

Shir Iluz, Yael Vinker, Amir Hertz +3

A word-as-image is a semantic typography technique where a word illustration presents a visualization of the meaning of the word, while also preserving its readability. We present…

cs.CV2022367 cited

Prompt-to-Prompt Image Editing with Cross Attention Control

Amir Hertz, Ron Mokady, Jay Tenenbaum +3

Recent large-scale text-driven synthesis models have attracted much attention thanks to their remarkable capabilities of generating highly diverse images that follow given text pro…

cs.CV20211 cited

GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps

Oren Barkan, Omri Armstrong, Amir Hertz +4

We present Gradient Activation Maps (GAM) - a machinery for explaining predictions made by visual similarity and classification models. By gleaning localized gradient and activatio…