Generating Illustrated Instructions
This addresses the problem of creating personalized visual instructions for users, enabling applications beyond static web articles, though it appears incremental as it combines existing LLMs and diffusion models.
The paper tackled the task of generating illustrated instructions customized to user needs, resulting in a model that outperforms baselines and state-of-the-art multimodal LLMs, with users preferring it to human-generated articles in 30% of cases.
We introduce the new task of generating Illustrated Instructions, i.e., visual instructions customized to a user's needs. We identify desiderata unique to this task, and formalize it through a suite of automatic and human evaluation metrics, designed to measure the validity, consistency, and efficacy of the generations. We combine the power of large language models (LLMs) together with strong text-to-image generation diffusion models to propose a simple approach called StackedDiffusion, which generates such illustrated instructions given text as input. The resulting model strongly outperforms baseline approaches and state-of-the-art multimodal LLMs; and in 30% of cases, users even prefer it to human-generated articles. Most notably, it enables various new and exciting applications far beyond what static articles on the web can provide, such as personalized instructions complete with intermediate steps and pictures in response to a user's individual situation.