DiffusionWorldViewer: Exposing and Broadening the Worldview Reflected by Generative Text-to-Image Models
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_ | 1866913222706069504 |
|---|---|
| author | De Simone, Zoe Boggust, Angie Satyanarayan, Arvind Wilson, Ashia |
| author_facet | De Simone, Zoe Boggust, Angie Satyanarayan, Arvind Wilson, Ashia |
| contents | Generative text-to-image (TTI) models produce high-quality images from short textual descriptions and are widely used in academic and creative domains. Like humans, TTI models have a worldview, a conception of the world learned from their training data and task that influences the images they generate for a given prompt. However, the worldviews of TTI models are often hidden from users, making it challenging for users to build intuition about TTI outputs, and they are often misaligned with users' worldviews, resulting in output images that do not match user expectations. In response, we introduce DiffusionWorldViewer, an interactive interface that exposes a TTI model's worldview across output demographics and provides editing tools for aligning output images with user perspectives. In a user study with 18 diverse TTI users, we find that DiffusionWorldViewer helps users represent their varied viewpoints in generated images and challenge the limited worldview reflected in current TTI models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_09944 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | DiffusionWorldViewer: Exposing and Broadening the Worldview Reflected by Generative Text-to-Image Models De Simone, Zoe Boggust, Angie Satyanarayan, Arvind Wilson, Ashia Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Computers and Society Generative text-to-image (TTI) models produce high-quality images from short textual descriptions and are widely used in academic and creative domains. Like humans, TTI models have a worldview, a conception of the world learned from their training data and task that influences the images they generate for a given prompt. However, the worldviews of TTI models are often hidden from users, making it challenging for users to build intuition about TTI outputs, and they are often misaligned with users' worldviews, resulting in output images that do not match user expectations. In response, we introduce DiffusionWorldViewer, an interactive interface that exposes a TTI model's worldview across output demographics and provides editing tools for aligning output images with user perspectives. In a user study with 18 diverse TTI users, we find that DiffusionWorldViewer helps users represent their varied viewpoints in generated images and challenge the limited worldview reflected in current TTI models. |
| title | DiffusionWorldViewer: Exposing and Broadening the Worldview Reflected by Generative Text-to-Image Models |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Computers and Society |
| url | https://arxiv.org/abs/2309.09944 |