Vibe Spaces for Creatively Connecting and Expressing Visual Concepts

TL;DR

This paper introduces Vibe Space, a hierarchical graph model that enables smooth, semantically meaningful visual concept blending, improving creative and coherent image hybrids over existing methods.

Contribution

The paper presents Vibe Space, a novel hierarchical graph approach for generating creative visual hybrids by learning low-dimensional geodesics in feature spaces like CLIP.

Findings

Vibe Space produces blends rated more creative by humans.

It enables smooth, semantically consistent transitions between concepts.

The framework combines human judgments, LLM reasoning, and a geometric difficulty score.

Abstract

Creating new visual concepts often requires connecting distinct ideas through their most relevant shared attributes -- their vibe. We introduce Vibe Blending, a novel task for generating coherent and meaningful hybrids that reveals these shared attributes between images. Achieving such blends is challenging for current methods, which struggle to identify and traverse nonlinear paths linking distant concepts in latent space. We propose Vibe Space, a hierarchical graph manifold that learns low-dimensional geodesics in feature spaces like CLIP, enabling smooth and semantically consistent transitions between concepts. To evaluate creative quality, we design a cognitively inspired framework combining human judgments, LLM reasoning, and a geometric path-based difficulty score. We find that Vibe Space produces blends that humans consistently rate as more creative and coherent than current methods.