To make images with AI, pick a generator (ChatGPT, Gemini, Midjourney or Firefly), describe what you want in detail, then refine the prompt. Mind the commercial-use rules before you publish.

Choose a tool and prompt it

For free and easy, use ChatGPT’s image generator or Gemini’s (generous free allowance). For top artistic quality, Midjourney (paid). For commercially safer images, Adobe Firefly. Describe your image clearly — subject, style, mood, lighting, composition — and refine based on results.

Write better image prompts

Be specific: ‘a watercolour illustration of a fox in a snowy forest, soft morning light, muted colours’. Add style references, aspect ratio and detail. Iterate — adjust one element at a time. For text inside images (logos, posters), use Ideogram, which is best at legible text.

Use images legally

A purely AI-generated image, song or video may not be protected by copyright (US law generally requires human authorship), and many free tiers forbid commercial use, require attribution, or make your outputs public. Always check a tool’s licence and your plan’s terms before using AI work commercially. Avoid generating recognisable trademarked characters (Midjourney faces active litigation), check whether your plan allows commercial use, and note that some free tiers make images public or require attribution. For commercial work, Adobe Firefly is marketed as the safer choice.

If you find yourself juggling a separate subscription for chat, automation, transcription and image generation, one option worth knowing is a single platform that runs them together — osFoundry is one such agentic AI platform that consolidates chat, agents and internal apps in one workspace, with a bring-your-own-key model so you choose the underlying AI.

This article is general information, not professional, legal or financial advice. AI tools, prices and availability change fast — verify current details on the official source before you rely on them.