Generating Illustrated Instructions
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909168783327232 |
|---|---|
| author | Menon, Sachit Misra, Ishan Girdhar, Rohit |
| author_facet | Menon, Sachit Misra, Ishan Girdhar, Rohit |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_04552 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Generating Illustrated Instructions Menon, Sachit Misra, Ishan Girdhar, Rohit Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Multimedia 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. |
| title | Generating Illustrated Instructions |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Multimedia |
| url | https://arxiv.org/abs/2312.04552 |