Distribution-Conditional Generation: From Class Distribution to Creative Generation

TL;DR

This paper introduces Distribution-Conditional Generation, a novel approach that models creativity in text-to-image diffusion models by conditioning on class distributions, enabling the synthesis of more diverse and out-of-distribution concepts.

Contribution

It proposes DisTok, an encoder-decoder framework that maps class distributions into tokens for creative image synthesis, improving diversity and semantic alignment.

Findings

DisTok achieves state-of-the-art performance in creative image generation.

The method enhances text-image alignment and human preference scores.

Distribution-conditioned synthesis enables more diverse concept generation.

Abstract

Text-to-image (T2I) diffusion models are effective at producing semantically aligned images, but their reliance on training data distributions limits their ability to synthesize truly novel, out-of-distribution concepts. Existing methods typically enhance creativity by combining pairs of known concepts, yielding compositions that, while out-of-distribution, remain linguistically describable and bounded within the existing semantic space. Inspired by the soft probabilistic outputs of classifiers on ambiguous inputs, we propose Distribution-Conditional Generation, a novel formulation that models creativity as image synthesis conditioned on class distributions, enabling semantically unconstrained creative generation. Building on this, we propose DisTok, an encoder-decoder framework that maps class distributions into a latent space and decodes them into tokens of creative concept. DisTok maintains a dynamic concept pool and iteratively sampling and fusing concept pairs, enabling the generation of tokens aligned with increasingly complex class distributions. To enforce distributional consistency, latent vectors sampled from a Gaussian prior are decoded into tokens and rendered into images, whose class distributions-predicted by a vision-language model-supervise the alignment between input distributions and the visual semantics of generated tokens. The resulting tokens are added to the concept pool for subsequent composition. Extensive experiments demonstrate that DisTok, by unifying distribution-conditioned fusion and sampling-based synthesis, enables efficient and flexible token-level generation, achieving state-of-the-art performance with superior text-image alignment and human preference scores.