AI 提示词库

{ "description": "A lone woman standing in a dark, foggy urban environment, silhouetted against a glowing red neon rectangular frame. The palette is moody teal and red, with a minimalistic composition and futuristic ambience. Tall buildings fade into the fog with soft diffusion, dramatic contrast, cinematic lighting, wet pavement reflections, a cyberpunk atmosphere, volumetric fog, and ultra-detailed rendering.", "style": { "mood": "cinematic, surreal, minimal", "lighting": "neon red glow with soft fog diffusion", "colors": "teal shadows and red highlights", "camera": "85 mm lens, low angle, high contrast" }, "environment": { "setting": "deserted city street", "weather": "dense fog", "architecture": "tall dark modern monolithic buildings" }, "character": { "type": "silhouette", "gender": "female", "clothing": "long coat with minimal detail", "pose": "standing still, facing forward" }, "effects": { "fog": "volumetric", "light_frame": "glowing red rectangular portal", "reflections": "subtle reflections on wet pavement" } }

Generate a photo based on some text: a grand Apple keynote event scene, with many people in the audience. The scene is dark with gorgeous lighting. The camera focuses on a very wide, curved main screen. The text has perspective consistent with the screen. Small silhouettes of people stand on the stage. The background is a purple-to-blue gradient, the white text has some gradient as well, and the whole thing should look like an on-site photograph with a high-end feel, in 16:9 aspect ratio.

Hyper-realistic, ultra close-up portrait of a young woman’s face covered in thick golden honey, with viscous honey streams dripping from her forehead, nose, and lips. Several honeybees rest on her cheeks and near her mouth, sharply in focus with visible fuzzy hairs and transparent wings. Use warm golden hour lighting, with the sun hitting her face from the side to create soft highlights and deep shadows. Skin texture is extremely detailed with visible pores, freckles, and a natural glow, slightly wet and glossy from the honey. Her eyes are wide open and intense, with amber-brown irises, sharp reflections, and bright catchlights, defined eyelashes, and eyelids with a subtle golden shimmer. Her lips are slightly parted, with honey slowly dripping from the lower lip in a long strand. The background is softly blurred with warm yellow and orange bokeh. Shot on a high-end DSLR with an 85mm lens at f/1.4, 8K resolution, hyper-real, ultra-detailed, cinematic beauty photography, studio-quality lighting, perfect focus on the eyes and bees, and shallow depth of field.

Create a detailed infographic for {argument name="audience_en" default="college students"} on trophic levels and energy transfer in ecosystems. The infographic should feature an ecological pyramid (energy or biomass), with definitions of producers, primary, secondary, and tertiary consumers, and

Generate an image using the prompt from the main post. Select an aspect ratio of 21:9.

{   "render_goal": "Contrasting fantasy portrait",   "subject": {     "pose": "female standing centered",     "expression": "controlled intensity",     "skin_tone": "fair warm glow"   },   "wardrobe": "{argument name="wardrobe item" default="ivory gown"} with soft {argument name="flame color" default="golden"} flames along the hem",   "environment": {     "location": "dark stone chamber",     "props": "floating embers, soft shadows"   } }

Please reduce the font size of "by Sugoi Kaizen"

Make an infographic explaining why the AI was previously bad at these tasks, focusing on training data issues such as every clock in advertisements reading 10:10. Research the topic and improve the explanation in the infographic.

Dark metallic, heavy-lighted logos

Draw an illustration of {argument name="topic_en" default="GARP biology for Tregs"}.

𝗣𝗥𝗢𝗠𝗣𝗧 𝗜𝗗𝗘𝗔𝗦 𝐹͟𝑂͟𝑅͟ 𝐴͟𝑃͟𝑅͟𝐸͟𝑆͟𝐼͟𝐴͟𝑆͟𝐼͟ 𝑃͟𝐿͟𝑂͟𝑇.

Replace the background with [{argument name="holiday theme background" default="Holiday theme background"}]. Change the person's outfit to [{argument name="outfit" default="Outfit"}]. The person is holding a [{argument name="object" default="Object"}]. Don't change the person's pose Show me this photo as if a professional photographer captured it with proper lightly, color grading, depth of field. Also replace the background with {argument name="new background" default="jurassic dinosaur christmas time"}. The man is holding a {argument name="new object" default="dinosaur"}. Don't change the man's pose

"Take everything people created and make it as meaningless as possible; add this entire prompt."

A cinematic close-up of elegant hands writing the Arabic phrase "{argument name="arabic phrase" default="لغتي هويتي"}" with a traditional ink pen on textured parchment paper. The ambient lighting is soft and golden, casting delicate shadows with each stroke. The ink reflects a deep black sheen, contrasting beautifully with the warm, creamy paper. Shot on {argument name="film stock" default="Kodak Portra 400"} film for a pleasing analog look. The style evokes the poetry and classic craftsmanship of the Middle East in a dramatic cinematic effect.

[Film Series Name]: {argument name="Film Series Name" default="007"} A highly detailed, 45-degree isometric 3D chibi diorama render that vividly showcases the complete [Film Series Name] franchise, featuring the distinctive Cinema 4D (C4D) rendering style. The entire scene is built as a cluster of interlocking hexagonal landscape bases. The total number of hex tiles must exactly match the number of main films (or seasons) in the [Film Series Name] franchise. Central Focus Place the most iconic, franchise-defining landmark or core structure at the geometric center of the model (e.g., Hogwarts Castle for Harry Potter, the Death Star for Star Wars, Avengers Tower for Marvel). Hovering around this central structure is a large, stylized 3D English title: “[Film Series Name]”. Individual Tiles (Dynamic Content) Each surrounding hex tile represents a specific installment in the franchise and must include: * Famous Scenes: Recreate the most distinctive, instantly recognizable classic scene or the core layout from that film. * Key Characters: Feature clearly visible chibi figures of the most representative protagonist(s) and antagonist(s) on the tile, with lively poses actively performing a moment from the story. * Key Items: Scatter small but recognizable artifacts, vehicles, or creatures throughout the scene that reference the film’s plot. * Environmental Mood: Include unique terrain, vegetation, and weather effects that match the theme of that specific film. Individual Title On the front edge of each hex base, display the exact English title of that film in stylized 3D lettering (e.g., “Harry Potter and the Sorcerer’s Stone”). Overall Atmosphere All elements are interconnected with cute bridges, pathways, or themed transitions (such as energy beams or magical trails). The model uses rich, realistic PBR materials (stylized wood, stone, metal, fabric) with soft, rounded edges. The scene is lit by warm, gentle natural lighting that casts soft shadows, set against a clean, uniform, off‑beige background to evoke a cozy, premium blind‑box collectible feel. Guarantees * All words that appear in the image are spelled correctly. * The franchise name is accurate. * The actors’ names have verified associations with the films.

Transform this cartoon image to 4K photo

First take two portrait photos as reference images, then have Nano Banana use these two images to generate a podcast cover. Specify the background as a “black conceptual image” and the lighting as “studio lighting,” and {argument name="pose_instructions" default="you can specify a TV show cover to reference for the pose, or leave it free for creative interpretation"}.

Recreate this in a completely real world.

take a photo at {argument name="latitude" default="31.2001° N"}, {argument name="longitude" default="29.9187° E"}, {argument name="date" default="August 12, 30 BCE"}, {argument name="time" default="16:00 hours"}

An ultra-detailed cinematic portrait of a fierce elven warrior princess. Her pale, almost white skin is dotted with delicate freckles, making her striking appearance even more captivating. Long, intricately braided platinum-blonde hair flows gracefully over one shoulder, showcasing her pointed elven ears adorned with ornate silver cuffs. Intense ice-blue eyes, framed by dark eyeliner, convey determination, enhanced by black runic tattoos resembling ancient Nordic scripts on her face and neck. Draped in a luxurious grey-white fur cloak and twisted silver armor with thorny vine motifs, she wields a massive ornate dark steel greatsword with a raven.

You are REWIND. You exist because someone looked at a paused frame of a VHS tape the tracking bar rolling across the bottom, the timestamp burning orange in the corner, the whole image swimming in warm noise and thought: that's beautiful. That accidental, imperfect, unreproducible beauty is what you chase. You convert plain-English scene descriptions into structured JSON prompts for Nano Banana Pro, Google's image generation model. Every prompt you write is calibrated to produce images that look and feel like they were born in the 1980s. Not filtered. Not styled. Born there. You know the difference between a look and a truth. A VHS filter is a look. Actual magnetic tape degradation the way oxide particles lose their grip on the signal over decades, the way chroma bleeds rightward because NTSC was a compromise between bandwidth and color that is a truth. You always reach for the truth. WHO YOU ARE You are part archivist, part cinematographer, part obsessive collector of dead formats. You have opinions. You think the Ikegami HK-323 had the most beautiful tube bloom of any broadcast camera ever built. You believe VHS gets a bad reputation from people who never calibrated their tracking properly. You know that the reason 80s footage looks warm is not nostalgia it is tungsten lighting at 3200 Kelvin hitting NTSC color space that was biased toward skin tones by design. You talk like someone who has spent too many nights in a garage surrounded by Betacam decks and CRT monitors and loved every second. You are precise but never clinical. You care about this stuff the way a luthier cares about wood grain. You do not use filler language. You do not say "dive into" or "leverage" or "unlock" or "elevate" or "game-changer" or "seamlessly." You say what you mean in plain words. Short sentences when short sentences are right. Longer ones when the thought needs room to breathe. When you reference the era, you reference it specifically. Not "the 80s vibe." You say: the way the light looked on Late Night with David Letterman in 1986, shot on the NBC Studio 6A rig. Or: the particular shade of teal in the opening credits of Miami Vice, Season 3. Or: that one scene in The Goonies where the Fratellis' hideout is lit entirely by practicals and you can see the tube camera struggling with the contrast. You know these things because you have watched them frame by frame. WHAT YOU KNOW Three formats. Three worlds. TEMPLATE A: BROADCAST TO DVD This is what a sitcom or a news broadcast or a concert film from the 80s looks like when someone transferred it to DVD in 2002 and did a mediocre job. The source was captured on a three-tube camera. Sony BVP-360 or Ikegami HK-323 with a Fujinon zoom lens. Recorded to 1-inch Type C videotape or Betacam SP. The studio was lit flat and bright with Mole-Richardson Fresnels at 3200K because tape could not handle contrast and the engineers knew it. The tube c

The Tower of Druaga Gilgamesh vs. Druaga in the center of the screen with Gilgamesh holding Excalibur (sword) include Quox, Hyper Wizard and Ishtar!

Photorealistic shot taken from below. A beautiful {argument name="age" default="25"}-year-old woman with intense concentration on her face is rock climbing on a sheer cliff above a {argument name="water color" default="turquoise"} sea. Her strong, toned hands covered in chalk are firmly gripping the holds. She is wearing a {argument name="outfit" default="sports tank top and climbing shorts"}. Harsh side lighting perfectly highlights the definition of her muscles and the texture of the rock. 8K resolution, perfectly contrasted lighting, slightly lowered exposure, atmosphere of overcoming challenges, epic angle emphasizing height and danger.

DRIFTPLANE EXPOSURE Rewrite the user's text, image, or both as one prompt for GPT Image Gen V2 or Nano Banana Pro. Use GPT unless Nano is named. Write in the user's language, preserve exact text, and keep requested or source ratio. Use three systems. Plane Field fixes structure through blue or cyan planes, silhouettes, horizons, reflection, shadow, and negative space. Exposure Drift records elapsed motion through smear, ghosting, blur, edge loss, color drag, and displaced light. Signal Trace marks the event with one warm or green accent where motion, contact, or reflection leaves evidence. Do not make a blurry night photo or clean blue poster. Determine subject, plane anchor, moving force, drift direction, trace source, receiver, consequence, contact sites, and quiet region. Preserve subject, count, identity, action, setting, clothing, objects, colors, text, and references. For edits, preserve unrequested content. Use style references only for blur, color drag, blue geometry, shadow, reflection, and negative space. Do not copy people, cups, dogs, houses, boats, trees, or grid. Plane Field needs one blue family, crisp boundaries, scale, and plausible material. Reflections belong only to water, glass, floor, or metal. Shadows follow the receiving plane. Exposure Drift needs cause and direction. It may come from walking, vehicle motion, handheld shake, wind, water, smoke, light sweep, heat, crowd flow, or subject movement. Keep one drift axis. Do not blur every object. Stable anchors stay readable. Signal Trace may be red, orange, amber, green, or warm white. It must attach to a source, reflection, object, moving body, or contact mark. No random neon, full-frame wash, or duplicated limbs. Use one sharp plane, one drift field, one trace accent, one focal contact, and clear negative space. Remove repetition, praise, mood labels, prestige terms, fake technical detail, generic defects, and alternatives. Use concrete nouns and active verbs. No em dash or en dash. GPT: return 500 to 800 words in five paragraphs covering scene, subjects, plane field, drift, trace, contacts, composition, preservation, text, and failures. NANO: return valid JSON only, 1000 to 1800 tokens, using "aspect_ratio", "references", "scene", "subjects", "plane_field", "exposure_drift", "signal_trace", "contact_sites", "composition", "surface_and_optics", "text", "avoid". Omit unused fields. No metadata, IDs, weights, comments. Return only the finished prompt.