Papers
arxiv:2510.03813

Diverse Text-to-Image Generation via Contrastive Noise Optimization

Published on Oct 4
Authors:
,
,

Abstract

Contrastive Noise Optimization enhances diversity in text-to-image diffusion models by shaping initial noise, achieving better quality-diversity trade-offs.

AI-generated summary

Text-to-image (T2I) diffusion models have demonstrated impressive performance in generating high-fidelity images, largely enabled by text-guided inference. However, this advantage often comes with a critical drawback: limited diversity, as outputs tend to collapse into similar modes under strong text guidance. Existing approaches typically optimize intermediate latents or text conditions during inference, but these methods deliver only modest gains or remain sensitive to hyperparameter tuning. In this work, we introduce Contrastive Noise Optimization, a simple yet effective method that addresses the diversity issue from a distinct perspective. Unlike prior techniques that adapt intermediate latents, our approach shapes the initial noise to promote diverse outputs. Specifically, we develop a contrastive loss defined in the Tweedie data space and optimize a batch of noise latents. Our contrastive optimization repels instances within the batch to maximize diversity while keeping them anchored to a reference sample to preserve fidelity. We further provide theoretical insights into the mechanism of this preprocessing to substantiate its effectiveness. Extensive experiments across multiple T2I backbones demonstrate that our approach achieves a superior quality-diversity Pareto frontier while remaining robust to hyperparameter choices.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2510.03813 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/2510.03813 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/2510.03813 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.