Skip to yearly menu bar Skip to main content


Poster

Named Entity Driven Zero-Shot Image Manipulation

Zhida Feng · Li Chen · Jing Tian · Jiaxiang Liu · Shikun Feng

Arch 4A-E Poster #418
[ ] [ Project Page ] [ Paper PDF ]
[ Poster
Wed 19 Jun 5 p.m. PDT — 6:30 p.m. PDT

Abstract:

We introduced StyleEntity, a zero-shot image manipulation model that utilizes named entities as proxies during its training phase. This strategy enables our model to manipulate images using unseen textual descriptions during inference, all within a single training phase. Additionally, we proposed an inference technique termed Prompt Ensemble Latent Averaging (PELA). PELA averages the manipulation directions derived from various named entities during inference, effectively eliminating the noise directions, thus achieving stable manipulation. In our experiments, StyleEntity exhibited superior performance in a zero-shot setting compared to other methods. The code, model weights, and datasets are available at https://github.com/feng-zhida/StyleEntity.

Chat is not available.