CVJun 1, 2023

Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion Models

arXiv:2306.00973v383 citationsh-index: 50Has Code
Originality Incremental advance
AI Analysis

This addresses the challenge of open-ended visual storytelling for applications in creative media and AI-generated content, representing an incremental advancement in sequence generation.

The paper tackles the problem of generating coherent image sequences from storylines, proposing StoryGen, an auto-regressive model with a vision-language context module, and shows it generalizes to unseen characters and produces consistent sequences validated by quantitative and human evaluations.

Generative models have recently exhibited exceptional capabilities in text-to-image generation, but still struggle to generate image sequences coherently. In this work, we focus on a novel, yet challenging task of generating a coherent image sequence based on a given storyline, denoted as open-ended visual storytelling. We make the following three contributions: (i) to fulfill the task of visual storytelling, we propose a learning-based auto-regressive image generation model, termed as StoryGen, with a novel vision-language context module, that enables to generate the current frame by conditioning on the corresponding text prompt and preceding image-caption pairs; (ii) to address the data shortage of visual storytelling, we collect paired image-text sequences by sourcing from online videos and open-source E-books, establishing processing pipeline for constructing a large-scale dataset with diverse characters, storylines, and artistic styles, named StorySalon; (iii) Quantitative experiments and human evaluations have validated the superiority of our StoryGen, where we show StoryGen can generalize to unseen characters without any optimization, and generate image sequences with coherent content and consistent character. Code, dataset, and models are available at https://haoningwu3639.github.io/StoryGen_Webpage/

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes