No Longer Trending on Artstation: Prompt Analysis of Generative AI Art
- URL: http://arxiv.org/abs/2401.14425v1
- Date: Wed, 24 Jan 2024 08:03:13 GMT
- Title: No Longer Trending on Artstation: Prompt Analysis of Generative AI Art
- Authors: Jon McCormack, Maria Teresa Llano, Stephen James Krol, Nina Rajcic
- Abstract summary: We collect and analyse over 3 million prompts and the images they generate.
Our study shows that prompting focuses largely on surface aesthetics, reinforcing cultural norms, popular conventional representations and imagery.
- Score: 7.64671395172401
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Image generation using generative AI is rapidly becoming a major new source
of visual media, with billions of AI generated images created using diffusion
models such as Stable Diffusion and Midjourney over the last few years. In this
paper we collect and analyse over 3 million prompts and the images they
generate. Using natural language processing, topic analysis and visualisation
methods we aim to understand collectively how people are using text prompts,
the impact of these systems on artists, and more broadly on the visual cultures
they promote. Our study shows that prompting focuses largely on surface
aesthetics, reinforcing cultural norms, popular conventional representations
and imagery. We also find that many users focus on popular topics (such as
making colouring books, fantasy art, or Christmas cards), suggesting that the
dominant use for the systems analysed is recreational rather than artistic.
Related papers
- GalleryGPT: Analyzing Paintings with Large Multimodal Models [64.98398357569765]
Artwork analysis is important and fundamental skill for art appreciation, which could enrich personal aesthetic sensibility and facilitate the critical thinking ability.
Previous works for automatically analyzing artworks mainly focus on classification, retrieval, and other simple tasks, which is far from the goal of AI.
We introduce a superior large multimodal model for painting analysis composing, dubbed GalleryGPT, which is slightly modified and fine-tuned based on LLaVA architecture.
arXiv Detail & Related papers (2024-08-01T11:52:56Z) - The role of interface design on prompt-mediated creativity in Generative
AI [0.0]
We analyze more than 145,000 prompts from two Generative AI platforms.
We find that users exhibit a tendency towards exploration of new topics over exploitation of concepts visited previously.
arXiv Detail & Related papers (2023-11-30T22:33:34Z) - State of the Art on Diffusion Models for Visual Computing [191.6168813012954]
This report introduces the basic mathematical concepts of diffusion models, implementation details and design choices of the popular Stable Diffusion model.
We also give a comprehensive overview of the rapidly growing literature on diffusion-based generation and editing.
We discuss available datasets, metrics, open challenges, and social implications.
arXiv Detail & Related papers (2023-10-11T05:32:29Z) - ITI-GEN: Inclusive Text-to-Image Generation [56.72212367905351]
This study investigates inclusive text-to-image generative models that generate images based on human-written prompts.
We show that, for some attributes, images can represent concepts more expressively than text.
We propose a novel approach, ITI-GEN, that leverages readily available reference images for Inclusive Text-to-Image GENeration.
arXiv Detail & Related papers (2023-09-11T15:54:30Z) - AI-Generated Imagery: A New Era for the `Readymade' [0.7386189738262202]
This paper aims to examine how digital images produced by generative AI systems have come to be so regularly referred to as art.
We employ existing philosophical frameworks and theories of language to suggest that some AI-generated imagery can be presented as readymades' for consideration as art.
arXiv Detail & Related papers (2023-07-12T09:25:56Z) - StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity
3D Avatar Generation [103.88928334431786]
We present a novel method for generating high-quality, stylized 3D avatars.
We use pre-trained image-text diffusion models for data generation and a Generative Adversarial Network (GAN)-based 3D generation network for training.
Our approach demonstrates superior performance over current state-of-the-art methods in terms of visual quality and diversity of the produced avatars.
arXiv Detail & Related papers (2023-05-30T13:09:21Z) - Language Does More Than Describe: On The Lack Of Figurative Speech in
Text-To-Image Models [63.545146807810305]
Text-to-image diffusion models can generate high-quality pictures from textual input prompts.
These models have been trained using text data collected from content-based labelling protocols.
We characterise the sentimentality, objectiveness and degree of abstraction of publicly available text data used to train current text-to-image diffusion models.
arXiv Detail & Related papers (2022-10-19T14:20:05Z) - A domain adaptive deep learning solution for scanpath prediction of
paintings [66.46953851227454]
This paper focuses on the eye-movement analysis of viewers during the visual experience of a certain number of paintings.
We introduce a new approach to predicting human visual attention, which impacts several cognitive functions for humans.
The proposed new architecture ingests images and returns scanpaths, a sequence of points featuring a high likelihood of catching viewers' attention.
arXiv Detail & Related papers (2022-09-22T22:27:08Z) - A Taxonomy of Prompt Modifiers for Text-To-Image Generation [6.903929927172919]
This paper identifies six types of prompt modifier used by practitioners in the online community based on a 3-month ethnography study.
The novel taxonomy of prompt modifier provides researchers a conceptual starting point for investigating the practice of text-to-image generation.
We discuss research opportunities of this novel creative practice in the field of Human-Computer Interaction.
arXiv Detail & Related papers (2022-04-20T06:15:50Z) - A Framework and Dataset for Abstract Art Generation via CalligraphyGAN [0.0]
We present a creative framework based on Conditional Generative Adversarial Networks and Contextual Neural Language Model to generate abstract artworks.
Our work is inspired by Chinese calligraphy, which is a unique form of visual art where the character itself is an aesthetic painting.
arXiv Detail & Related papers (2020-12-02T16:24:20Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.