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.
PRO01Transform the input photo into a high-end stylized 3D collectible figure…
PRO02Edit the provided image while preserving the same face identity, shape,…
PRO031. Brand Basics Brand Name: [Fill in, e.g., PRIME STEAK / OCEAN PRIME] Brand Tagline: [Fill in, e.g., Steakhouse…
PRO042x2 grid, do this for 4 famous scientists in history: Design a collector…
PRO05Create a premium "Matcha Brand Touchpoint System" visual board for a mod…
PRO061. Logo Concept Generation Prompt: You are a top-tier logo designer with 20 years of experience, having designed instantly recognizable and deeply meaningful logos for globally renowned brands. Brand name: [your brand name…
PRO07Create a premium, highly realistic 1:1 campaign poster for NOIR, a modern…
PRO08Create a branded technical infographic for [SNACK], combining a real photo or photorealistic render of the product with technical annotation overlays placed directly on top, against a pure white studio background, using...
A 60-second cinematic orchestral score for corporate videos, fundraising pitches, brand story films, and documentaries. It has a clear arc without ever drowning out narration.
Turns a 3-hour interview recording into a 2,000-word brand story, profile piece, or documentary script. Claude selects the key passages, preserves the original voice, and stitches fragmented moments into a narrative with a real arc.
Killer copy for a brand's About / About Us page. Compresses 'who I am, why I started this business, what I believe, who this is for' into about 400 words that read like a real person, not a press release.
15 seconds is the gold-standard length for short-form video ads. Sora 2 handles narrative instructions better than other models — you can give it a three-shot mini-story instead of just a single shot.
Handles the two big requirements for wrapping paper and bag patterns at once: tileability, and staying unobtrusive as a background so a logo doesn't get lost in it. Achieved via low density plus even negative space plus low contrast to leave breathing room for a logo, and by banning directional lighting/shadow and perspective to preserve the tiling. Honest limitation: generative models don't guarantee true seamlessness — check the edge seams in image-editing software using an offset test, patch locally wherever there's a visible seam, and don't expect it to be perfect in one shot.
15 seconds is only enough for people to remember one thing: the brand name. This uses a single hook melody repeated three times, with the brand name appearing at the beginning, middle, and end, quotation marks to lock the wording and prevent mis-singing, and a clean ending landing on the brand name. Suited to in-store announcements, short-video openers, and ad bumpers. Trim the duration with the web app's slider, or cut it yourself after generation.
Generate three OBS stream scenes in one go — starting-soon countdown, be-right-back, and stream-ending outro — sharing the same layout and color scheme with only the status text changing, with space reserved for the webcam and chat overlay, so your channel has one consistent brand look from stream start to sign-off.
Sings your shop name and slogan into a 15-30 second earworm jingle: quotation marks lock the shop name so it doesn't get slurred, plus a hook-rhyme formula, English-language style-field writing tips, and enunciation-rescue steps all included — ready to use for short-video openers and paid ads.
Generate a professional headshot suitable for LinkedIn, a personal website, a business card, or an instructor bio — natural light, a softly blurred background, moderate retouching that still looks real, with variables for outfit and mood, ideal for freelancers, founders, and instructors building a personal brand.
Generates a set of flat, vector-style illustrations in a consistent style for a slide deck — one image per concept, with clean geometry and a unified color palette — so your deck isn't limited to icon libraries and stock photos.
Generate a watercolor-and-paper-collage-style Instagram visual, layering hand-painted bleeds, paper texture, and torn-edge collage together to create a warm background for brand posts and Stories — breaking away from the flat, overly polished AI look that's everywhere right now.
Generates a complete brand mascot character sheet in one shot with GPT Image 2 — the same character shown in multiple expressions and poses, side by side, in a consistent, reusable style, suited to small businesses making LINE stickers, customer-service avatars, or packaging identity.
One prompt produces a 9-panel expression sheet for a brand mascot — the character design stays locked across all nine emotions, each panel labeled with a Traditional Chinese emotion tag, useful for social media managers making stickers, reaction memes, and customer-service avatars.
Renders the same character as three avatar styles in one shot — chibi, flat illustration, and semi-realistic — with consistent facial features across all three, so personal brands, team headshots, and social profile pictures can compare styles before picking one.
Builds a reusable brand mascot for small businesses, producing four marketing poses in one shot — welcoming, pointing the way, recommending, and giving a thumbs-up — each with matching speech-bubble copy, so the same character appears consistently across your website, banners, and posts.
Turn a packaging design into a 3D mockup: a box or bottle shown at a 45-degree angle revealing both front and side faces, with studio lighting at print-ready quality, and the brand name and product name rendered letter-for-letter on the package.