AI Art Generation for Journalism

Tools like Stable Diffusion and Midjourney are shaking up the art world in large part because they are accessible for almost anyone to use. The limits of what they can create is still being tested. Many journalism articles lack visuals which are essential in today's platform centric media landscape. A tool to automagically generate art for many of those articles could help smaller newsrooms without a budget for visuals (art/photography).

Faculty and Staff Leads

Zach Wise

Associate Professor

Emmy winning interactive producer & Associate Professor @NorthwesternU, @KnightLab. Formerly of The New York Times. Creator of TimelineJS & StoryMapJS

Project Details

2023 Winter
AI Art Generation for Journalism

Description

Tools like Stable Diffusion and Midjourney are shaking up the art world in large part because they are accessible for almost anyone to use. The limits of what they can create is still being tested. Many journalism articles lack visuals which are essential in today's platform centric media landscape. A tool to automagically generate art for many of those articles could help smaller newsrooms without a budget for visuals (art/photography).

Important Questions
  • Can a written article be turned into a descriptive prompt for AI art?
  • What are the implications for concept art generated by AI running with a reported article?
  • What are the limitations of content and concept for generating news art?
Outcome

By the end of the quarter, students will have produced a way to turn an article into a stable diffusion text prompt and return AI generated art recommendations to go with the article.

2023 Spring
AI Art Generation for Journalism

Description

Tools like Stable Diffusion and Midjourney are shaking up the art world in large part because they are accessible for almost anyone to use. Many journalism articles lack visuals which are essential in today's platform centric media landscape. A tool to automagically generate art for many of those articles could help smaller newsrooms without a budget for visuals (art/photography). This project builds off of the previous quarters findings.

Important Questions
  • Can a written article be turned into a descriptive prompt for AI art?
  • What are the implications for concept art generated by AI running with a reported article?
  • What are the limitations of content and concept for generating news art?
  • Can we train the AI to create art that is more editorial in nature?
  • Can we train the AI to create art that is more representative?
Outcome

By the end of the quarter, students will have produced a way to turn an article into a stable diffusion text prompt and return AI generated art recommendations to go with the article.

2023 Fall
AI Art and Tik Tok for Journalism

Description

Many journalistic articles lack visuals which are essential in today's platform centric media landscape. We've been able to train new AI models to be less problematic in creating images for journalistic articles using only GPT and stable diffusion but we need even better models. We want to continue our work in using AI to create Instagram Stories and Reels, as well as Tik Tok videos from articles. This project will build on the progress of previous teams in creating useful tools and methods for turning text articles into visual storytelling for social media.

Important Questions
  • Can we turn articles into effective Instagram Stories and Tik Tok videos using AI?
  • What are the limitations of content and concept for generating news art?
  • Can we train the AI to create art that is more editorial in nature?
  • Can we train the AI to create art that is more representative and less problematic?
Outcome

By the end of the quarter, students will have produced a way to turn an article into a stable diffusion text prompt and return AI generated art recommendations to go with the article.

2024 Winter
AI Art and Tik Tok for Journalism

Description

Many journalistic articles lack visuals which are essential in today's platform centric media landscape. We've been able to train new AI models to be less problematic in creating images for journalistic articles using only GPT and stable diffusion but we need even better models. We want to continue our work in using AI to create Instagram Stories and Reels, as well as Tik Tok videos from articles. This project will build on the progress of previous teams in creating useful tools and methods for turning text articles into visual storytelling for social media.

Important Questions
  • Can we turn articles into effective Instagram Stories and Tik Tok videos using AI?
  • What are the limitations of content and concept for generating news art?
  • Can we train the AI to create art that is more editorial in nature?
  • Can we train the AI to create art that is more representative and less problematic?
Outcome

By the end of the quarter, students will have produced a way to turn an article into a stable diffusion text prompt and return AI generated art recommendations to go with the article.

2024 Spring
AI Art and Tik Tok for Journalism

Description

Many journalistic articles lack visuals which are essential in today's platform centric media landscape. We've been able to train new AI models to be less problematic in creating images for journalistic articles using only GPT and stable diffusion but we need even better models. We want to continue our work in using AI to create Instagram Stories and Reels, as well as Tik Tok videos from articles. This project will build on the progress of previous teams in creating useful tools and methods for turning text articles into visual storytelling for social media.

Important Questions
  • Can we turn articles into effective Instagram Stories and Tik Tok videos using AI?
  • What are the limitations of content and concept for generating news art?
  • Can we train the AI to create art that is more editorial in nature?
  • Can we train the AI to create art that is more representative and less problematic?
Outcome

By the end of the quarter, students will have produced a way to turn an article into a stable diffusion text prompt and return AI generated art recommendations to go with the article.