[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization

[CVPR 2024] Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models

Code for the ACL paper "No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling"

Implementation of seq2seq model for Visual Storytelling Challenge (VIST) http://visionandlanguage.net/VIST/index.html

[Neurips 2025 NextVid Workshop Oral✨] Official Implementation of VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention

An implementation of the paper "Contextualize, Show and Tell: A Neural Visual Storyteller." presented at the Storytelling Workshop, co-located with NAACL 2018.

Agentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent debate to multimodal generation (intelligence lives in the agent; the diffusion model just renders). Image-based today, video next.

将故事和角色图像转化为电影分镜脚本，生成专业的画面提示词和图生视频提示词。

自由画布叙事创作系统 — AI-powered story canvas for novels, screenplays & world-building. Supports multi-timeline narratives, 35 block types, 35 story cards. 在画布上摆放、连接、组织叙事元素，AI 协助将结构转化为高质量正文。支持小说、剧本、史诗级世界构建，对标魔兽世界·冰与火之歌·从零开始的异世界生活的创作体量。

Visual Storytelling with Cross-Modal Rules

A list of research papers on knowledge-enhanced multimodal learning

We designed an end-to-end framework that encourage interactive narrative experience based on keyword control and image generation.

Official Codebase for "Kahani: Culturally Nuanced Visual Storytelling Pipeline for Non-Western Cultures"

TACL 23: Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences

DATA-X: m130 - Introduction to Visual Principles Using Matplotlib and Seaborn. Provides users with the necessary foundations for building and understanding current state of the art visualizations. An additional aim is to provide users with an understanding of both the theory and techniques of various visualization paradigms. Finally, this series…

Graph convolution-based visual storytelling

A high-impact landing page design exploring advanced CSS compositing. Features dynamic video masking, interactive 'mix-blend-mode' typography, and a hardware-accelerated cinematic UI architecture.

GROOViST: A Metric for Grounding Objects in Visual Storytelling – EMNLP 2023

PyTorch code for Automatic generation of comic dialogues. The purpose of this project is to generate subsequent dialogues given a multimodal context.

Not (yet) the whole story: Evaluating Visual Storytelling Requires More than Measuring Coherence, Grounding, and Repetition – EMNLP 2024 (Findings)