Papers
arxiv:2505.19166

JEDI: The Force of Jensen-Shannon Divergence in Disentangling Diffusion Models

Published on May 25
Authors:
,
,

Abstract

JEDI enhances diffusion models' subject separation and compositional alignment at test time using a Jensen-Shannon divergence based objective and adversarial optimization.

AI-generated summary

We introduce JEDI, a test-time adaptation method that enhances subject separation and compositional alignment in diffusion models without requiring retraining or external supervision. JEDI operates by minimizing semantic entanglement in attention maps using a novel Jensen-Shannon divergence based objective. To improve efficiency, we leverage adversarial optimization, reducing the number of updating steps required. JEDI is model-agnostic and applicable to architectures such as Stable Diffusion 1.5 and 3.5, consistently improving prompt alignment and disentanglement in complex scenes. Additionally, JEDI provides a lightweight, CLIP-free disentanglement score derived from internal attention distributions, offering a principled benchmark for compositional alignment under test-time conditions. We will publicly release the implementation of our method.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2505.19166 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2505.19166 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2505.19166 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.