CoChat
Sign Up
Cited by 10Generative Adversarial Networks and Image SynthesisArtificial Intelligence ApplicationsDigital Media and Visual Art

The DOI matches its Crossref record; the references it cites are not checked yet.

Technology behind text to image generators

Fernandez, Peter·2022·Library Hi Tech News
DOI 10.1108/lhtn-10-2022-0116
Open this paper in CoChat — free account

Abstract

Purpose This column aims to provides an overview of the techniques that make text-to-image generators possible. Design/methodology/approach This column will be the first in a two-part series, exploring the impacts of text-to-image software with an emphasis on libraries. Findings It shows how advances in machine learning and the particular technique of diffusion are critical building blocks for artificial intelligence. Originality/value Understanding these technologies and large data sets, which are often scraped by public users, help information professionals understand how this software may further develop, as well as how to help guide their patrons.

Overview

Integrity signals

Registry

Crossref · 10.1108/lhtn-10-2022-0116

Cites

0 of 11 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

  • Baio, A. (2022), “Exploring 12 million of the 2.3 billion images used to train stable diffusion’s image generator”, Waxy.Org, available at: https://waxy.org/2022/08/exploring-12-million-of-the-images-used-to-train-stable-diffusions-image-generator/

    (n.d.)

    Unresolved

  • Cavender, E. (2022), “For gen Z, TikTok is more than entertainment. It’s a search engine”, Mashable, available at: https://mashable.com/article/gen-z-tiktok-search-engine-google

    (n.d.)

    Unresolved

  • Edwards, B. (2022), “Have AI image generators assimilated your art? New tool lets you check”, Ars Technica, available at: https://arstechnica.com/information-technology/2022/09/have-ai-image-generators-assimilated-your-art-new-tool-lets-you-check/

    (n.d.)

    Unresolved

  • Gershgorn, D. (2021), “Can AI learn from any public code online?”, The Verge, available at: www.theverge.com/2021/7/7/22561180/github-copilot-legal-copyright-fair-use-public-code

    (n.d.)

    Unresolved

  • Hartsfield, T. (2022), “How do DALL-E, Midjourney, Stable Diffusion, and other forms of generative AI work?”, Big Think, available at: https://bigthink.com/the-future/dall-e-midjourney-stable-diffusion-models-generative-ai/ (accessed 8 October 2022).

    (n.d.)

    Unresolved

  • Leetaru, K. (2017), “Common crawl and unlocking web archives for research”, Forbes, available at: www.forbes.com/sites/kalevleetaru/2017/09/28/common-crawl-and-unlocking-web-archives-for-research/

    (n.d.)

    Unresolved

  • Lucier, A.M. (2022), “Questions surround AI-Generated art and copyright authorship | insights | Holland & Knight”, Holland & Knight, available at: www.hklaw.com/en/insights/publications/2022/07/questions-surround-ai-generated-art-and-copyright-authorship

    (n.d.)

    Unresolved

  • Pierce, D. (2022a), “I tried replacing Google with TikTok, and it worked better than I thought”, The Verge, available at: www.theverge.com/23365101/tiktok-search-google-replacement

    (n.d.)

    Unresolved

  • Pierce, D. (2022b), “Google is trying to reinvent search – by being more than a search engine”, The Verge, available at: www.theverge.com/2022/9/28/23375691/google-search-multisearch-visual-keywords

    (n.d.)

    Unresolved

  • Vincent, J. (2022), “TikTok now offers a very basic text-to-image AI generator directly in the app”, The Verge, available at: www.theverge.com/2022/8/15/23306101/tiktok-ai-greenscreen-filter-text-to-image-mainstream

    (n.d.)

    Unresolved

Show all 11 references

Cited by

Sorted by citations

See all 10

Related

Metadata

Authors
Fernandez, P.
Venue
Library Hi Tech News
Publisher
Emerald
Published
2022-11-14
Volume
39
Issue
10
Pages
1-4
ISSN
0741-9058 (ISSN-L)
DOI
10.1108/lhtn-10-2022-0116
OpenAlex
W4309504282
Cited by
9
References
11
Citations by year
2026: 2 · 2025: 1 · 2024: 3 · 2023: 3
FWCI
0.57
Type
journal article
Language
en
Open access
closed
Licence
www.emerald.com/insight/site-policies (tdm)
Locations
Library Hi Tech News (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
  • Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
  • Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Digital Media and Visual Art
Keywords
text-to-image generation, diffusion models, generative AI, machine learning, large language models, web scraping, library services, information professionals

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review