Skip to Main Content

AI in information retrieval

Generating images

AI tools can generate images using natural language commands, similar to how ChatGPT generates text. The operation of image generators is not only based on the material used to teach the system; it is equally important to be able to define the prompt in such a way that the desired result is obtained.

How is this done? The AI is guided by a prompt, which generates the image(s). The prompt should describe not only the subject but also the style in which the image is to be created. Terms such as illustration, photorealistic, high definition, pencil drawing, water colour, oil painting, pixel art, 1920's style, etc. can be used as a definition. Some AI tools have predefined styles from which the user can choose the one they prefer. Further tips on how to make good prompts for generating images.

When using an AI generated image, it is important to mention that it was generated by an AI tool. The user should mention which tool and what kind of prompt was used to create the image.

AI tools for images

  • An AI-based image generator model developed by OpenAi that creates images from textual descriptions. 
  • works in the browser 
  • 15 free credits per month, intensive use for a fee
  • requires registration
  • works in the browser
  • the style of the image is selected from a set of predefined options, some styles are only available in the paid version  
  • some functions free, some require payment  
  • paid functions require registration
  • works in the browser
  • free version: watermarked images & ads on the page
  • paid version also available
  • works in the browser
  • 25 free credits, then a fee 
  • requires registration
  • a Discord bot
  • requires a paid subscription, no free trial available (Nov 2023)  
  • requires the user to have a Discord account
  • works in browser & mobile app
  • 5 free credits per day
  • requires registration