# Text-to-image

> AI that draws a brand-new picture from a written description.

- Level: Basic
- Topics: AI
- URL: https://tidbit.legios.com.ar/text-to-image/
- In Spanish: [Texto a imagen](https://tidbit.legios.com.ar/es/text-to-image/)

A **text-to-image** model creates a picture from a sentence. You type "a capybara reading the newspaper in a Buenos Aires café, watercolor" and seconds later you get an image that never existed before. DALL·E, Midjourney, Stable Diffusion, Google's Imagen and the image features built into chatbots like ChatGPT and Gemini all do this.

These models learn from huge collections of images paired with captions. Most of them are a diffusion model: the system starts from pure random noise and removes it step by step, guided at each step by the meaning of your text, until a coherent picture appears. Some newer systems generate images inside a multimodal model, with an approach closer to how an LLM writes text.

They are handy for sketches, illustrations, mockups and ads, and they raise real questions. Many artists object that their work was used for training without permission, and there are lawsuits over copyright. Realistic fake photos, or deepfakes, can spread misinformation or be used to harass people, so many tools add a watermark or metadata marking the image as AI-made, and laws like the EU AI Act require that kind of labeling. They also still trip on some details, like exact lettering on a sign, though each generation gets better at it.

## An analogy

A sketch artist working from a witness's description who has studied millions of paintings and photos. The more precise your description, the closer the drawing gets to what you had in mind.

## Keep in mind

- You write a description (a prompt) and get a new image.
- Most use diffusion: noise refined step by step into a picture.
- Trained on huge sets of captioned images, which fuels copyright debates.
- Many tools mark their output as AI-generated.

## Go deeper

- [Text-to-image model on Wikipedia](https://en.wikipedia.org/wiki/Text-to-image_model)
- [Image generation (OpenAI docs)](https://platform.openai.com/docs/guides/image-generation)

## Related terms

- [Midjourney](https://tidbit.legios.com.ar/midjourney/): A small AI lab whose service turns a written description into an image.
- [Google](https://tidbit.legios.com.ar/google/): The search company that gives most products away and makes its money on ads.
- [Chatbot](https://tidbit.legios.com.ar/chatbot/): A program you talk to by typing or speaking, as if it were a person.
- [ChatGPT](https://tidbit.legios.com.ar/chatgpt/): OpenAI's chat assistant, the app that brought AI chatbots to the general public.
- [Gemini](https://tidbit.legios.com.ar/gemini/): Google's family of AI models, and the assistant app that carries the same name.
- [Diffusion model](https://tidbit.legios.com.ar/diffusion-model/): An image generator that starts from random noise and cleans it up, step by step.
- [Multimodal AI](https://tidbit.legios.com.ar/multimodal-ai/): AI that works with more than one kind of data at once: text, images, sound, video.
- [LLM](https://tidbit.legios.com.ar/llm/): A neural network trained on huge amounts of text to predict the next word.