ORACLE: Leveraging Mutual Information for Consistent Character Generation with LoRAs in Diffusion Models
Kiymet Akdemir, Pinar Yanardag

TL;DR
This paper presents a novel framework that leverages mutual information to improve the consistency of character generation in diffusion models, enabling more uniform visual identities across diverse prompts and settings.
Contribution
It introduces a new method that enhances character consistency in diffusion-based text-to-image models using mutual information, addressing a key challenge in creative AI applications.
Findings
Outperforms existing methods in maintaining character consistency
Demonstrates effectiveness through quantitative and qualitative analyses
Enhances the practical utility of diffusion models in creative industries
Abstract
Text-to-image diffusion models have recently taken center stage as pivotal tools in promoting visual creativity across an array of domains such as comic book artistry, children's literature, game development, and web design. These models harness the power of artificial intelligence to convert textual descriptions into vivid images, thereby enabling artists and creators to bring their imaginative concepts to life with unprecedented ease. However, one of the significant hurdles that persist is the challenge of maintaining consistency in character generation across diverse contexts. Variations in textual prompts, even if minor, can yield vastly different visual outputs, posing a considerable problem in projects that require a uniform representation of characters throughout. In this paper, we introduce a novel framework designed to produce consistent character representations from a single…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNatural Language Processing Techniques · Topic Modeling · Handwritten Text Recognition Techniques
MethodsDiffusion
