AI image generation
Definition
AI image generation is the use of an AI model to create a new picture from a written description, or to edit an existing image by describing the change you want. You describe the subject, style and format in plain words, then refine the result in follow-up messages.
By Ronan Liedmeier, fractional head of growth and course author · Published 17 October 2026 · Last updated 17 October 2026
Also called: text-to-image, AI image generator
At work it is a fast way to get drafts, such as a blog header or a rough mockup to show a designer. The results hold up well for drafts and informal use and much less well for anything that needs precision.
How it works
Image models are trained on very large collections of images paired with text descriptions, and learn to produce a new image that matches a prompt. Many current tools are multimodal: OpenAI's image models, for example, accept text and images as input, so you can upload a photo and ask for a change instead of starting over.
A useful prompt names the subject, the style, the mood and the format (for example portrait, with empty space at the top for a headline). Then you refine in conversation by asking for specific changes to the same image. Reading and describing images is a separate skill, called vision.
Example
A café owner needs a poster for a Saturday tasting. She asks for "a flat illustration of coffee cups on a wooden counter, warm autumn colors, portrait format, empty space across the top". After two edits ("fewer leaves", "lighter background") she has a usable background. She then adds the date, time and address herself in a design tool.
Common mistake
Asking the model to write exact text into the image. Dates, prices and names often come out misspelled or garbled, and logos and real people's faces are unreliable as well. Generate the image without text, then add the words in a design tool where you control them.
Learn it in AI Academy
- Working With ImagesBeginner · 10 min
Related terms
- Generative AI
- Generative AI is software that creates new content, such as text, images, audio, video or code, from a plain-language request. It learns patterns from large amounts of existing examples and produces fresh output that follows those patterns.
- AI vision (image understanding)
- AI vision is the ability of an AI model to look at an image you give it, such as a photo, screenshot, chart or scanned document, and describe it, read the text in it or answer questions about it.
- Multimodal AI
- Multimodal AI is AI that can work with more than one kind of input or output, such as text, images, audio and video, in the same conversation. You can show it a photo or screenshot and ask about it, or describe a picture and get one made.
- Prompt
- A prompt is the instruction or question you give an AI model to tell it what you want. It can be one line or a full brief with background, examples and the format you need back, and the answer is shaped by everything in it.