Search Results for author: Dana Arad

Found 2 papers, 1 papers with code

Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines

no code implementations • 9 Mar 2024 • Michael Toker, Hadas Orgad, Mor Ventura, Dana Arad, Yonatan Belinkov

Text-to-image diffusion models (T2I) use a latent representation of a text prompt to guide the image generation process.

Image Generation Retrieval

Paper
Add Code

ReFACT: Updating Text-to-Image Models by Editing the Text Encoder

1 code implementation • 1 Jun 2023 • Dana Arad, Hadas Orgad, Yonatan Belinkov

Text-to-image models are trained on extensive amounts of data, leading them to implicitly encode factual knowledge within their parameters.

Image Generation

8

Paper
Code

Cannot find the paper you are looking for? You can Submit a new open access paper.