1328 hand-tested AI prompts across image, video, and music — each with full context, variables, and a sample output. Content is authored in Traditional Chinese; the UI here is English.
PRO01A 3D render of a cute kawaii {argument name="subject" default="cloud"} c...
PRO02Create an explanatory slide, with the diagram format set via an argument (default: ponchi-e diagram style)...
PRO03Create an explanatory slide, with the diagram format set via an argument (default: ponchi-e diagram style)...
PRO04A realistic photo of a Chinese high school math exam paper, printed inbl…
PRO052026 China City Series promotional poster, themed around [Beijing]. A modern, colorful, bright, and airy Guochao (China-chic) style, vertical 9:16 format. A large area of white textured negative space in the background, with a red silk ribbon spiraling from bottom-right to top-left…
PRO06Based on [Topic], generate a high-quality vertical "Science Encyclopedia Illustration." This image is not an ordinary poster, nor a simple illustration, but a modular science visual that combines the feel of a field guide, an encyclopedia, structured information, and a collectible…
PRO07Generate a vertical, phone-screenshot-style image with an aspect ratio close to 9:16. Slightly above center is a real-life cosplayer portraying the anime character from the uploaded reference image. The character is rendered in a realistic style, but with facial features that are slightly…
PRO08Automatically generate a collector's-edition epic narrative poster based on [THEME]: a towering, elegant character-profile silhouette forms the outer contour, and within the silhouette grows a complete world matching the theme — landmark scenes, characters…
PRO09Generate a high-definition photorealistic poster in the style of a "soccer-themed movie poster": Inter Milan defender Bastoni stands at the center of the San Siro stadium celebrating passionately, arms raised high and draped in the Bosnia and Herzegovina flag, his expression fired-up, resolute, and confident…
Breaks a piece of content into N key points, laid out as a Traditional Chinese infographic card with a title, bullet points, and labels, all rendered correctly.
A signboard for a Taiwanese night market food stall, with a vertical-text menu, prices, and bold hand-lettered type — unmistakably Taiwanese with no garbled characters.
A repeatable Traditional Chinese cover-card system with a fixed color scheme and type hierarchy — swap in a new headline and the whole account's visual identity stays consistent.
GPT Image 2 (which replaced DALL-E 3 in 2026 and renders text well) turns a written explanation into a clean infographic ready for slides or social posts.
For a startup SaaS homepage hero: flat illustration in your brand's primary color.
A product-vs-competitor comparison table — 2-3 columns by N rows, with checkmarks, X marks, pricing, and feature comparisons. Commonly used on B2B marketing and ecommerce decision pages.
A timeline of brand milestones, historical events, or product evolution — GPT Image 2 combines Chinese year labels, event descriptions, and icons into one integrated graphic.
Simulates a SaaS dashboard screenshot — for use on landing pages, the 'here's what the product looks like' slide of a pitch deck, or a feature-overview hero image.
Turns abstract concepts into visuals — diagrams for psychology theories, economic models, or design principles. Used for book illustrations, study cards, and knowledge-focused Instagram posts.
GPT Image 2's most underrated ability is making infographics. Its Chinese character rendering is 10x more reliable than Midjourney's; feed it data plus structure and it produces an infographic ready for an annual report, a deck, or LinkedIn.
The biggest pain point with Chinese posters is that every image model garbles the characters. GPT Image 2 currently renders Traditional Chinese better than anything else, and this prompt is built for "Chinese headline + layout + zero errors," print-ready out of the box.