Distribution-Conditional Generation: From Class Distribution to Creative Generation

• URL: http://arxiv.org/abs/2505.03667v1
• Date: Tue, 06 May 2025 16:07:12 GMT
• Title: Distribution-Conditional Generation: From Class Distribution to Creative Generation
• Authors: Fu Feng, Yucheng Xie, Xu Yang, Jing Wang, Xin Geng,
• Abstract summary: DisTok is an encoder-decoder framework that maps class distributions into a latent space and decodes them into tokens of creative concept.<n>DisTok achieves state-of-the-art performance with superior text-image alignment and human preference scores.
• Score: 39.93527514513576
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Models [1.9129789494874188]
  We introduce Discrete Latent Code (DLC), an image representation derived from Simplicial Embeddings trained with a self-supervised learning objective.<n>DLCs are sequences of discrete tokens, as opposed to the standard continuous image embeddings.<n>They are easy to generate and their compositionality enables sampling of novel images beyond the training distribution.
  arXiv  Detail & Related papers  (2025-07-16T15:12:17Z)
• Redefining <Creative> in Dictionary: Towards an Enhanced Semantic Understanding of Creative Generation [39.93527514513576]
  Creative'' remains an inherently abstract concept for both humans and diffusion models.<n>Current methods rely heavily on reference prompts or images to achieve a creative effect.<n>We introduce CreTok, which brings meta-creativity to diffusion models by redefining creative' as a new token, texttCreTok>.<n>Code will be made available at https://github.com/fu-feng/CreTok.
  arXiv  Detail & Related papers  (2024-10-31T17:19:03Z)
• Distilling Vision-Language Foundation Models: A Data-Free Approach via Prompt Diversification [49.41632476658246]
  We discuss the extension of DFKD to Vision-Language Foundation Models without access to the billion-level image-text datasets. The objective is to customize a student model for distribution-agnostic downstream tasks with given category concepts. We propose three novel Prompt Diversification methods to encourage image synthesis with diverse styles.
  arXiv  Detail & Related papers  (2024-07-21T13:26:30Z)
• Training-free Composite Scene Generation for Layout-to-Image Synthesis [29.186425845897947]
  This paper introduces a novel training-free approach designed to overcome adversarial semantic intersections during the diffusion conditioning phase. We propose two innovative constraints: 1) an inter-token constraint that resolves token conflicts to ensure accurate concept synthesis; and 2) a self-attention constraint that improves pixel-to-pixel relationships. Our evaluations confirm the effectiveness of leveraging layout information for guiding the diffusion process, generating content-rich images with enhanced fidelity and complexity.
  arXiv  Detail & Related papers  (2024-07-18T15:48:07Z)
• SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow [94.90853153808987]
  Semantic segmentation and semantic image synthesis are representative tasks in visual perception and generation. We propose a unified framework (SemFlow) and model them as a pair of reverse problems. Experiments show that our SemFlow achieves competitive results on semantic segmentation and semantic image synthesis tasks.
  arXiv  Detail & Related papers  (2024-05-30T17:34:40Z)
• Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesis [62.07413805483241]
  Steered Diffusion is a framework for zero-shot conditional image generation using a diffusion model trained for unconditional generation. We present experiments using steered diffusion on several tasks including inpainting, colorization, text-guided semantic editing, and image super-resolution.
  arXiv  Detail & Related papers  (2023-09-30T02:03:22Z)
• Exploring Compositional Visual Generation with Latent Classifier Guidance [19.48538300223431]
  We train latent diffusion models and auxiliary latent classifiers to facilitate non-linear navigation of latent representation generation. We show that such conditional generation achieved by latent classifier guidance provably maximizes a lower bound of the conditional log probability during training. We show that this paradigm based on latent classifier guidance is agnostic to pre-trained generative models, and present competitive results for both image generation and sequential manipulation of real and synthetic images.
  arXiv  Detail & Related papers  (2023-04-25T03:02:58Z)
• Semantic Image Synthesis via Diffusion Models [174.24523061460704]
  Denoising Diffusion Probabilistic Models (DDPMs) have achieved remarkable success in various image generation tasks.<n>Recent work on semantic image synthesis mainly follows the de facto GAN-based approaches.<n>We propose a novel framework based on DDPM for semantic image synthesis.
  arXiv  Detail & Related papers  (2022-06-30T18:31:51Z)
• Cross-Modal Discrete Representation Learning [73.68393416984618]
  We present a self-supervised learning framework that learns a representation that captures finer levels of granularity across different modalities. Our framework relies on a discretized embedding space created via vector quantization that is shared across different modalities.
  arXiv  Detail & Related papers  (2021-06-10T00:23:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.