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.
PRO01Two and a half thousand years ago, Plato, Socrates, and Aristotle sat talking on the streets of Athens, and that conversation gave rise to the origins of world civilization. In the background, their conversation can be added, following the timeline, overlaid onto ancient Gree…
免費02Create a 3D Insane detailed exploded assembly drawing of [subject or obj…
PRO03An exquisite illustration in a 3D embroidery style with a low-relief fiber-art effect, on a pure "silk white + milk white" background with delicate thread texture. The scene shows several small birds perched on winding flower branches, accented with blush white, pale peach, coral pink, light…
免費04Generate a long handscroll-style illustration inspired by "Nostalgia at Red Cliff," featuring the full text of Su Shi's "Ode to the Red Cliffs."
免費05Generate a detailed explainer diagram of RAG (Retrieval-Augmented Generation) technology.
免費06Generate an image of a livestream room, with the mood of a beautiful woman dancing under the moonlight, and many viewer comments in the chat.
After a year of role-play system prompts and 14-step frameworks, here's the takeaway: the thing that actually moved the needle on quality was 5 one-line prompts. No roles, no markdown, no "you are an expert."
The 'quote card' format that goes viral on IG — layout-led, minimal background, Chinese and English text coexisting without clashing. Ideogram is currently the only model that renders Chinese and English text together reliably.
30 seconds matches the IG Reels length cap exactly, and lo-fi hip-hop is easy to cut to and never competes with voiceover. The trick is timing the drop at the 4-second mark — that's the moment viewers decide whether to keep watching.
Feed Claude your original resume plus the target job posting, and it rewrites every section of your resume in that company's language — keywords, metrics, and industry terms all aligned — to boost your ATS pass rate.
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.
The payoff in restoration content is the "gap," not the process, so "before-and-after" is stated right at the start of the sentence as the format declar…
"Piece by piece" is the engine of this prompt — it forces the model into a "one part at a time" rhythm instead of suddenly…
The whole prompt is just three things — one action, three hammer strikes plus a quench sizzle, and one light source. Writing the strike count as a number (Three ring...
The selling point of molten material is that it 'glows on its own and can be stretched' — the two verbs `glows and stretches` handle the...
Ray3 responds to 'secondary motion' — the chain reactions a main action triggers, like a skirt hem flaring out or hair flowing; writing that in is what lets it...
`backpack bouncing` and `breathing visible in cold air` are two low-cost switches for realism.
Instead of adjusting performance with adjectives, write 'where she is and how she feels after laughing' — swap the context around the same verb and the model works out the volume, duration, and...
Native-audio models love to auto-add canned laughter — you have to exclude it negatively with (no studio audience) and then...
POV action shots run the biggest risk of subject and threat fighting for focus in the same frame — first-person view naturally turns 'being chased' into an off-screen sense of pressure, using only...
Grok Imagine's native sound effects only land accurately when 'triggered' — the formula is to name the sound (board c...
Even a static portrait can carry drama — exhaling is the only action, and the cold air turns that breath into visible proof; `locked cam...
A vertigo shot is by definition 'dollying in while zooming out' — this line locks down two opposite motions plus a focal-length range (35mm→70mm...
Train subjects are most vulnerable to the camera failing to keep up — `moving alongside` directly specifies a parallel tracking shot at the train's own speed, …