Rhetorical Text-to-Image Generation via Two-layer Diffusion Policy Optimization

• URL: http://arxiv.org/abs/2505.22792v1
• Date: Wed, 28 May 2025 19:03:37 GMT
• Title: Rhetorical Text-to-Image Generation via Two-layer Diffusion Policy Optimization
• Authors: Yuxi Zhang, Yueting Li, Xinyu Du, Sibo Wang,
• Abstract summary: Rhet2Pix is a framework that formulates rhetorical text-to-image generation as a multi-step policy optimization problem.<n>Our model outperforms SOTA MLLMs such as GPT-4o, Grok-3 and leading academic baselines across both qualitative and quantitative evaluations.
• Score: 6.169979847774362
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating images from rhetorical languages remains a critical challenge for text-to-image models. Even state-of-the-art (SOTA) multimodal large language models (MLLM) fail to generate images based on the hidden meaning inherent in rhetorical language--despite such content being readily mappable to visual representations by humans. A key limitation is that current models emphasize object-level word embedding alignment, causing metaphorical expressions to steer image generation towards their literal visuals and overlook the intended semantic meaning. To address this, we propose Rhet2Pix, a framework that formulates rhetorical text-to-image generation as a multi-step policy optimization problem, incorporating a two-layer MDP diffusion module. In the outer layer, Rhet2Pix converts the input prompt into incrementally elaborated sub-sentences and executes corresponding image-generation actions, constructing semantically richer visuals. In the inner layer, Rhet2Pix mitigates reward sparsity during image generation by discounting the final reward and optimizing every adjacent action pair along the diffusion denoising trajectory. Extensive experiments demonstrate the effectiveness of Rhet2Pix in rhetorical text-to-image generation. Our model outperforms SOTA MLLMs such as GPT-4o, Grok-3 and leading academic baselines across both qualitative and quantitative evaluations. The code and dataset used in this work are publicly available.

Related papers

• Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models [54.052963634384945]
  We introduce the Image Regeneration task to assess text-to-image models. We use GPT4V to bridge the gap between the reference image and the text input for the T2I model. We also present ImageRepainter framework to enhance the quality of generated images.
  arXiv  Detail & Related papers  (2024-11-14T13:52:43Z)
• TheaterGen: Character Management with LLM for Consistent Multi-turn Image Generation [44.740794326596664]
  TheaterGen is a training-free framework that integrates large language models (LLMs) and text-to-image (T2I) models. Within this framework, LLMs, acting as "Screenwriter", engage in multi-turn interaction, generating and managing a standardized prompt book. With the effective management of prompt books and character images, TheaterGen significantly improves semantic and contextual consistency in synthesized images.
  arXiv  Detail & Related papers  (2024-04-29T17:58:14Z)
• Unlocking Pre-trained Image Backbones for Semantic Image Synthesis [29.688029979801577]
  We propose a new class of GAN discriminators for semantic image synthesis that generates highly realistic images. Our model, which we dub DP-SIMS, achieves state-of-the-art results in terms of image quality and consistency with the input label maps on ADE-20K, COCO-Stuff, and Cityscapes.
  arXiv  Detail & Related papers  (2023-12-20T09:39:19Z)
• ITI-GEN: Inclusive Text-to-Image Generation [56.72212367905351]
  This study investigates inclusive text-to-image generative models that generate images based on human-written prompts. We show that, for some attributes, images can represent concepts more expressively than text. We propose a novel approach, ITI-GEN, that leverages readily available reference images for Inclusive Text-to-Image GENeration.
  arXiv  Detail & Related papers  (2023-09-11T15:54:30Z)
• Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering [79.44443231700201]
  Multi-modal keyphrase generation aims to produce a set of keyphrases that represent the core points of the input text-image pair. The input text and image are often not perfectly matched, and thus the image may introduce noise into the model. We propose a novel multi-modal keyphrase generation model, which not only enriches the model input with external knowledge, but also effectively filters image noise.
  arXiv  Detail & Related papers  (2023-09-09T09:41:36Z)
• HumanDiffusion: a Coarse-to-Fine Alignment Diffusion Framework for Controllable Text-Driven Person Image Generation [73.3790833537313]
  Controllable person image generation promotes a wide range of applications such as digital human interaction and virtual try-on. We propose HumanDiffusion, a coarse-to-fine alignment diffusion framework, for text-driven person image generation.
  arXiv  Detail & Related papers  (2022-11-11T14:30:34Z)
• IR-GAN: Image Manipulation with Linguistic Instruction by Increment Reasoning [110.7118381246156]
  Increment Reasoning Generative Adversarial Network (IR-GAN) aims to reason consistency between visual increment in images and semantic increment in instructions. First, we introduce the word-level and instruction-level instruction encoders to learn user's intention from history-correlated instructions as semantic increment. Second, we embed the representation of semantic increment into that of source image for generating target image, where source image plays the role of referring auxiliary.
  arXiv  Detail & Related papers  (2022-04-02T07:48:39Z)
• Improving Generation and Evaluation of Visual Stories via Semantic Consistency [72.00815192668193]
  Given a series of natural language captions, an agent must generate a sequence of images that correspond to the captions. Prior work has introduced recurrent generative models which outperform synthesis text-to-image models on this task. We present a number of improvements to prior modeling approaches, including the addition of a dual learning framework.
  arXiv  Detail & Related papers  (2021-05-20T20:42:42Z)

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.