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.
A character moving through outfit poses: 12 seconds with 3 held poses.
A J-pop ballad theme: piano + strings + an explosive chorus.
A 90-second epic orchestral piece: gradual build to climax, then landing.
A reusable podcast intro bumper: theme plus transition.
Put Gemini's 1M-token context to work — feed in an entire PDF or cross-reference multiple documents at once
Upload an image for structured analysis: design reviews, UX audits, and competitive screenshot comparisons.
Drop the entire repo into Gemini → get an architectural overview + improvement suggestions
A pure text wordmark logo for a brand — Ideogram handles letter spacing and font weight far better than Midjourney. Good for exploring initial directions and quickly aligning on style with a designer.
Cover design for business, self-help, and career books — unlike literary covers, these need to be bold, with a large title and a supporting subtitle line.
Commemorative ticket stub design — works for music festivals, talks, exhibition physical tickets, and digital NFT ticket stubs. Combines a vintage ticket feel with modern text rendering.
Front packaging for food, skincare, and curated retail products — Ideogram renders product names, ingredients, and certification text on packaging 10x more reliably than other models.
Title cards for YouTube videos, documentaries, and short films — using Ideogram for text-led title cards is faster than animating one in After Effects (add animation in post with other tools).
Course thumbnails for Hahow / Udemy / Skillshare — text-led design keeps the title readable even at thumbnail size. Ideogram handles font contrast better than Midjourney.
Chinese-English bilingual restaurant menus — Ideogram can render both scripts together without garbling. Best suited for fine dining, curated cafés, and bars.
An annual event's logo series — a main logo paired with a subtitle (e.g., an 'LF26' main logo with a 'Chapter One' subtitle). Ideogram's handling of letterform relationships keeps the whole set visually consistent.
Outdoor billboards / subway ads / pop-up backdrops — text needs to stay readable from 10 meters away. A minimal composition with extra-large type is the only solution.
A flowchart for educational content — GPT Image 2 is the most reliable tool for diagrams combining Chinese text, arrows, and numbered steps. Works well for social posts, slide decks, and book illustrations.
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.
A software/SaaS architecture diagram showing the relationships between frontend, backend, database, and third-party services — built for engineers, not marketing fluff.
Turns your 5–8 most common customer questions into a single graphic — question, short answer, and an icon for each. Retains readers roughly three times better than a long text-based FAQ page.
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.
A user journey map for product/UX design — visualizing touchpoints, emotions, and pain points. Built for design critiques and pitch decks.