# Generating Storytelling Images with Rich Chains-of-Reasoning

Source: [Generating Storytelling Images with Rich Chains-of-Reasoning](<https://www.sota2.com/research/paper/6937ad546cfd488761a4ec3c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-09T05:00:05.326Z

Authors: Xiujie Song, Qi Jia, Shota Watanabe, Xiaoyi Pang, Ruijie Chen, Mengyue Wu, Kenny Q. Zhu

Published: 2025-12-08T06:18:44.000Z

## Abstract

A single image can convey a compelling story through logically connected visual clues, forming Chains-of-Reasoning (CoRs). We define these semantically rich images as Storytelling Images. By conveying multi-layered information that inspires active interpretation, these images enable a wide range of applications, such as illustration and cognitive screening. Despite their potential, such images are scarce and complex to create. To address this, we introduce the Storytelling Image Generation task and propose StorytellingPainter, a two-stage pipeline combining the reasoning of Large Language Models (LLMs) with Text-to-Image (T2I) synthesis. We also develop a dedicated evaluation framework assessing semantic complexity, diversity, and text-image alignment. Furthermore, given the critical role of story generation in the task, we introduce lightweight Mini-Storytellers to bridge the performance gap between small-scale and proprietary LLMs. Experimental results demonstrate the feasibility of our approaches.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Storytelling Image Generation on CogBench ISA (test)](<https://www.sota2.com/research/sota/storytelling-image-generation-on-cogbench-isa-test.md>): Storytelling Image Generation; CogBench ISA (test); Story Length (Words): 459.27.

- [Storytelling Image Generation on GPT-image quality: medium 1.0](<https://www.sota2.com/research/sota/storytelling-image-generation-on-gpt-image-quality-medium-1-0.md>): Storytelling Image Generation; GPT-image quality: medium 1.0; Success Rate: 1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2512.07198>)

[PDF](<https://arxiv.org/pdf/2512.07198.pdf>)