Image generation, photo editing, video, logos, product shots, audio, slides and art direction. 56 copy-ready prompts across 8 categories – fill in the brackets, copy, and paste into ChatGPT, Claude, Gemini or any capable assistant.
Visual models take instructions differently from text models. They do not reason about your request — they weight the words in it. That is why the same prompt gives wildly different results across Midjourney, GPT Image, Flux and Firefly, and why prompt structure matters more here than almost anywhere else.
Every prompt in this pillar names which model it was written for, because a prompt that is not model-specific is a prompt that works properly nowhere.
8 categories
Image Generation
Subject, light, framing and style — in the order each model actually reads.
7 promptsPhoto Editing
Inpainting, background work, retouching and upscaling with predictable results.
7 promptsVideo
Shot descriptions, camera moves and the clip lengths that actually hold together.
7 promptsLogos & Brand Visuals
Concept exploration — with clear eyes about what is not a finished logo.
7 promptsProduct Photography
Lifestyle scenes and backgrounds, and where the honesty line sits.
7 promptsAudio, Music & Voice
Voiceover direction, music briefs and sound design.
7 promptsPresentations & Slides
Structure, narrative and slides that are not bullet lists of your script.
7 promptsArt Direction
Briefs, mood boards and critique — the words around the image.
7 prompts
A good first prompt from each
How to use these prompts
- Pick a category above, or search the whole prompt library.
- Press “Fill in” on any prompt to replace the [BRACKETED] parts in a simple form – or copy it and edit it in your AI tool.
- Read the tip under each prompt. It usually names the thing that goes wrong first.
- Got your own prompt? Run it through the Prompt Improver to see what is missing.