Papers
arxiv:2411.05473

Improving image synthesis with diffusion-negative sampling

Published on Nov 8, 2024
Authors:
,

Abstract

A new diffusion-negative prompting strategy bridges the semantic gap between human intuition and diffusion models by generating negative prompts through diffusion-negative sampling.

For image generation with diffusion models (DMs), a negative prompt n can be used to complement the text prompt p, helping define properties not desired in the synthesized image. While this improves prompt adherence and image quality, finding good negative prompts is challenging. We argue that this is due to a semantic gap between humans and DMs, which makes good negative prompts for DMs appear unintuitive to humans. To bridge this gap, we propose a new diffusion-negative prompting (DNP) strategy. DNP is based on a new procedure to sample images that are least compliant with p under the distribution of the DM, denoted as diffusion-negative sampling (DNS). Given p, one such image is sampled, which is then translated into natural language by the user or a captioning model, to produce the negative prompt n*. The pair (p, n*) is finally used to prompt the DM. DNS is straightforward to implement and requires no training. Experiments and human evaluations show that DNP performs well both quantitatively and qualitatively and can be easily combined with several DM variants.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2411.05473 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/2411.05473 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/2411.05473 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.