752 citations · 1.4k across the 13 of their papers we have counts for
Showing 2021Show all
3 papers · 1 filter
cs.CY2021
Ownership and Creativity in Generative Models
Omri Avrahami, Bar Tamir
Machine learning generated content such as image artworks, textual poems and music become prominent in recent years. These tools attract much attention from the media, artists, res…
cs.CV2021★ 752 cited
Blended Diffusion for Text-driven Editing of Natural Images
Omri Avrahami, Dani Lischinski, Ohad Fried
Natural language offers a highly intuitive interface for image editing. In this paper, we introduce the first solution for performing local (region-based) edits in generic natural…
cs.LG2021★ 5 cited
GAN Cocktail: mixing GANs without dataset access
Omri Avrahami, Dani Lischinski, Ohad Fried
Today's generative models are capable of synthesizing high-fidelity images, but each model specializes on a specific target domain. This raises the need for model merging: combinin…