From Wikiprompt, the free prompt encyclopedia
Wikiprompt is a collaborative encyclopedia of AI prompts, featuring curated templates for various AI tools including ChatGPT, Midjourney, DALL-E, Claude, and more. It contains 3213 prompts by 225 community members.
All, Creative, Marketing, Business, Productivity, Coding, Education, Personal, Research, Other
All, GPT Image 2 (800), ChatGPT (298), Model-agnostic (247), Seedance 2.0 (242), Nano Banana Pro (226), Gemini Nano Banana (210), Gemini Nano Banana Pro (182), Grok Imagine (83), Claude (61), Gemini (44), Midjourney v7 (29), Nano Banana 2 (27), Veo 3 (25), Gemini Nano Banana 2 (24), GPT Image 1.5 (24), Midjourney (21), NotebookLM (20), Midjourney v8.1 (14), ChatGPT / Gemini (12), Kling AI 3.0 Turbo (12)
All, cinematic (198), photorealistic (115), editorial (106), portrait (96), commercial (39), fashion (38), minimalist (31), studio (31), luxury (30), product-photography (29), lifestyle (28), golden-hour (26), surreal (25), miniature (23), infographic (21), 3d-render (20), poster (20), candid (19), monochrome (19), macro (18)
All, Creative generation (2567), Template (321), One-shot (226), System prompt (50), Workflow (39), Persona (6), Agent (3)
93 prompts
A tested formula for prompting photorealistic AI images (subject, action, environment, lighting, camera, lens, perspective, composition, imperfections, mood) plus the winning example prompt from a fivβ¦
A meta-prompt that takes any prompt, extracts its intent, generates 20 standalone rephrasings, scores them and returns the top 5 with justifications. A self-contained prompt optimizer for ChatGPT or Cβ¦
A pre-mortem prompt that assumes a feature has already failed and works backwards to surface adoption, technical, second-order and business risks before you build it. Great for product decisions with β¦
A framework for writing prompts that get good output on the first try, built from five parts most weak prompts are missing (goal, context, constraints, output format, examples), with a before/after exβ¦
A backward-looking personal-finance audit for ChatGPT or Claude: paste your income, spending and subscriptions and it hunts the leaks - forgotten subscriptions, duplicate charges, creeping prices - anβ¦
A command code that makes the model name the single most important next action and why it beats the alternatives whenever a message ends in /NEXT.
Candid European travel portrait of a couple sharing a romantic hand-kiss moment at golden hour, preserves both faces from a reference photo.

A Claude/ChatGPT prompt that runs an adaptive diagnostic quiz to surface your blind spots on a topic, then prescribes targeted exercises to fix them.
A neon-lit candid portrait prompt with heart-shaped light reflections in the glasses, compared side by side on ChatGPT and Gemini Nano Banana.

A candid documentary-style kitchen photo prompt used side by side on Gemini Nano Banana 2 and GPT Image 2.0 to compare realism.

A Claude/ChatGPT prompt that turns a competitor's negative app-store reviews into a themed, prioritized list of feature gaps and UX problems worth solving.
Reusable starter prompts plus a planning-first workflow for vibe-coding a third-person 3D fantasy game with AI: scope the world and character in conversation before building.

A studio portrait pairing a real woman with a stylized 3D Pixar-like animated avatar of herself.

A cinematic photorealistic portrait of a man relaxing in a field of white daisies.

A prompt for generating security-focused integration tests that catch auth, IDOR, rate-limiting and injection holes before an API ships. Used in Cursor.
Fine-art watercolor portrait series in a gallery caricature style, made with an AI image model via genflow_ai.

A sticker-pack style collage showing one character in 18 labeled facial expressions, made with an image model.

A one-shot Cursor prompt that audits a codebase for exposed keys, unprotected routes, and missing auth checks before shipping to production.
A casual glamour studio portrait with soft diffused lighting, focused on hair and outfit styling, made with an image model.

A prompt that turns any photo into an intentionally bad, scribbly MS Paint-style redraw, used to compare Grok Imagine and Nano Banana 2 outputs.
