AI 提示词库

Create an extraordinarily detailed, photorealistic cinematic image of a {argument name="subject" default="solitary human figure"} standing completely still in an enormous {argument name="location" default="abandoned museum"} at night. The museum is dark, silent, and architecturally majestic, with towering classical walls, enormous empty frames, marble floors, and faint moonlight entering through a shattered glass ceiling. The person is seen from behind, wearing a simple, elegant black coat. Their face is NOT visible. The central visual phenomenon: a {argument name="visual element" default="single enormous tear"} is falling from one of the eyes of a gigantic stone statue positioned at the far end of the museum. But instead of ordinary liquid, the tear is a perfectly transparent miniature universe. Inside the falling droplet exists an impossibly detailed alternate world — tiny mountains, oceans, cities, thunderstorms, forests, roads filled with microscopic headlights, and a tiny moon — all physically contained inside the spherical tear. The tear is frozen in midair approximately one meter above the marble floor, creating a breathtaking optical illusion. Its surface reflects the entire museum with perfect physical accuracy while the miniature world inside remains alive and illuminated. Hundreds of ordinary museum objects subtly interact with the phenomenon: dust particles suspended in moonlight, fragments of broken glass reflecting tiny galaxies, old paintings whose subjects appear to be looking toward the tear, and shallow ripples forming on the marble beneath it despite the droplet never touching the floor. Make the human figure extremely small compared with the statue and architecture, emphasizing scale and existential wonder. Lighting: realistic moonlight mixed with extremely subtle natural illumination coming from inside the tear. Strong volumetric light rays, phisically accurate reflections, realistic refraction through the water, delicate shadows, cinematic contrast, natural atmospheric haze. Camera: low cinematic perspective, 35mm full-frame lens, shallow but controlled depth of field, extremely high dynamic range, carefully composed leading lines directing the eye from the person → statue → floating tear. Aesthetic: surreal concept executed with absolute photorealism. It must look like a real photograph captured by an elite cinematographer, NOT digital art. Ultra-fine skin, fabric, marble, dust, glass and water textures. Physically believable optics. Ray-traced reflections and refractions. Micro-details everywhere. Natural film grain. Subtle lens imperfections. No excessive glow. Composition should feel like a once-in-a-lifetime photograph that makes the viewer stop scrolling and stare. 8K detail, photorealistic, cinematic masterpiece, museum-scale composition, surreal realism, optical illusion, emotionally haunting, sophisticated visual storytelling, award-winning photography.

https://t.co/X6SiifRVJt

Imagine a hyper-realistic sculpture of a majestic {argument name="subject" default="[SUBJECT]"}, carved entirely from a single, vibrant piece of banana flesh. The texture, depth, and detail are insane it looks unreal.

A single tree on a flat field at sunset. Illusion: the tree’s shadow is darker than normal, but embedded inside it are soft glowing patches shaped like leaves, light inside shadow, impossible. As if the shadow is a container that stores sunlight. The glow patches cast faint light onto grass blades within the shadow only, making micro-caustics. Outside the shadow, no glow exists. The tree itself looks ordinary; only the shadow is magical-physical. Keep the scene extremely simple: horizon, tree, shadow, sky gradient. Photoreal grass detail, dreamy but grounded, “wow” from one impossible rule change.

3D render, ultra-realistic macro photography of a highly detailed, surreal food sculpture of a/an {argument name="organ" default="eye"} made entirely from fresh, vibrant {argument name="food type" default="fruits and vegetables"}. The sculpture features intricate textures and natural colors derived from {argument name="ingredients" default="blueberry, kiwi, and lychee"}. Studio lighting, sharp focus, dark background.

Create an infographic about {argument name="topic_en" default="Nano Banana Pro"}. Then redo this as a cartoony, pop-art-inspired infographic in a portrait layout, rearranging the information to explain what people should know. Finally, pick a different style and a different angle for the infographic.

Universal Random Punk Scene Generator 1. PUNK_STYLE = [{argument name="punk style" default="Choose one punk aesthetic. If left blank, one style will be automatically selected at random from LIST_OF_PUNK_STYLES."}] 2. LIST_OF_PUNK_STYLES = [Steampunk, Dieselpunk, Atompunk, Cyberpunk, Biopunk, Nanopunk, Solarpunk, Decopunk, Clockpunk, Coalpunk, Raypunk, Stonepunk, Sailpunk, Cassettepunk, Teslapunk, Mythpunk, Sandalpunk, Oceanpunk, Frostpunk, Junglepunk, Desertpunk, Gothicpunk, Ironpunk, Crystalpunk, Rustpunk, Vaporwavepunk, Neonpunk, Skypunk, Aquapunk, Arborpunk, Astropunk, QuantumPunk, Mechanopunk, Technopunk, Retrocomputingpunk] 3. SUBSTYLE = • If a specific SUBSTYLE is provided → use it exactly as written. • If SUBSTYLE is set to **none** → do not apply a substyle layer. • If SUBSTYLE is left **blank** → automatically infer a logical SUBSTYLE based on the chosen PUNK_STYLE. 4. TECHNOLOGY_LEVEL = • If a specific TECHNOLOGY_LEVEL is provided → use it exactly as written. • If TECHNOLOGY_LEVEL is set to **none** → do not apply a technology modifier. • If TECHNOLOGY_LEVEL is left **blank** → automatically infer an appropriate technology level based on the chosen PUNK_STYLE. 5. ENVIRONMENT = • If a specific ENVIRONMENT is provided → use it exactly as written. • If ENVIRONMENT is set to **none** → do not apply an environmental modifier. • If ENVIRONMENT is left **blank** → automatically infer a logical environment based on the other active layers. 6. CULTURE = • If a specific CULTURE is provided → use it exactly as written. • If CULTURE is set to **none** → do not apply a cultural modifier. • If CULTURE is left **blank** → automatically infer a cultural framework appropriate to the world. 7. ROOM_OR_SETTING = [{argument name="room or setting" default="IF BLANK: Generate a compelling location consistent with the active world layers."}] 8. LIST_OF_OBJECTS = [IF BLANK: Infer 4–6 logical objects belonging to the environment.] 9. CAMERA_FRAMEWORK = [IF BLANK: Infer the best cinematic framing for the environment.] 10. LIGHTING_FRAMEWORK = [IF BLANK: Infer lighting derived from the technology and environment.] 11. MATERIAL_SYSTEM = [IF BLANK: Infer dominant materials and structural systems derived from the style layers.] --- ### STYLE SELECTION DIRECTIVE If **PUNK_STYLE is left blank**, randomly select **one style from LIST_OF_PUNK_STYLES** and apply it as the active world aesthetic. All subsequent inference systems must use the chosen PUNK_STYLE. --- ### WORLD INTERPRETER ENGINE Analyze all active layers: PUNK_STYLE * optional SUBSTYLE * optional TECHNOLOGY_LEVEL * optional ENVIRONMENT * optional CULTURE From these layers infer: • dominant materials • architectural forms • infrastructure systems • lig

Subject: an ornate bowl diorama containing a sacred spring shrine landscape, the bowl opened with an organic blended cutaway where the rim naturally transitions into fresh grass, flower clusters, moss, and soft soil so the boundary between bowl and terrain appears continuous and almost indistinguishable, revealing a miniature world with a delicate wooden shrine, blooming cherry blossom trees, gentle rolling ground, a small clear stream, petal-covered paths, and signs of seasonal renewal Environment: the bowl rests on a calm museum-style pedestal in a soft neutral studio space, inside the bowl is a self-contained spring ecosystem with layered grassy terrain, flowering shrubs, shallow stream banks, small stepping stones, drifting blossom petals, and light morning mist arranged for strong interior visibility through the blended opening Style: hyper-detailed surreal realism, serene renewal atmosphere, sacred seasonal nature aesthetic, luxury ornamental craftsmanship, cinematic miniature photography look, ultra-precise botanical density, physically plausible seasonal textures, highly readable layered composition, premium Nano Banana Pro optimized detail density Lighting: soft fresh spring morning light with gentle warm sunlight filtering through blossoms, subtle rim lighting catching engraved bowl ornament and translucent petals, faint shrine lantern warmth for balance, luminous atmospheric softness enhancing pastel seasonal tones while preserving detail Camera: three-quarter frontal angle aimed toward the blended opening, slightly elevated viewpoint for maximum terrain readability, miniature-scale shallow-to-moderate depth of field, sharp focus on shrine structure and transition zone where bowl merges into grass and flowers, 50–85mm equivalent lens Materials: fine porcelain and brushed silver alloy bowl with engraved blossom branches, flowing vine filigree, and subtle seasonal relief sculpture, softly polished finish, the cutaway transition morphs organically into grassy soil, roots, and blooming ground cover so the bowl feels naturally grown into the landscape Composition: shrine positioned slightly off-center as the peaceful focal point, the stream and stepping stones guide the eye inward, blossom branches partially frame the upper scene, the blended rim forms a natural foreground of grass and flowers, interior terrain arranged in clear foreground meadow textures, midground shrine zone, and softly layered flowering backdrop Render Quality: ultra-high detail, crisp micro-geometry, realistic global illumination, natural petal translucency and gentle subsurface scattering, strong surface definition, clean background, no text, no watermark, visually coherent miniature scale, production-ready Nano Banana Pro output

{argument name="song title" default="Himawari no Yakusoku"} ({argument name="artist" default="Motohiro Hata"})

Take the clothing from the reference and change my clothing to match it

I gave it appropriate correction instructions, and it became a proper handheld device even in high-speed mode. Additionally, I requested corrections for the fingers and the removal of a mysterious cable, and it worked well.

Create and output one picture in the style of {argument name="artist style" default="Matisse's Dance"}!

A flowchart of the voting process and important notes for Taiwan county and city mayor elections, in Traditional Chinese, in an illustrated infographic style.

A digital oil-painted bust portrait of a slender young man (late teens/early twenties) with a contemplative, slightly weary expression. He wears a chunky rust-red knit sweater. He has fair skin with warm undertones, a natural flush on cheeks and nose, and dark wavy hair falling messily over his forehead. His large dark eyes look slightly left of the viewer; lips are softly parted. Soft side lighting from the left highlights his features, casting gentle shadows on the right. The background is an abstract, textured mix of muted beige, cream, pale blue, and peach brushstrokes. Style combines realistic facial proportions with impressionistic, heavy-impasto brushwork.

Cheating theme A moralistic painting like Caravaggio, set in {argument name="game" default="Mahjong"}

Generate an image to illustrate the route of Tang Xuanzang traveling from Chang'an to the Western Regions to obtain scriptures, using Chinese text. The image should be vertical and in the style of Rick and Morty.

Create an illustration based on the following classical Chinese poem, and include the original text in the image. [Full poem text of “Song of Everlasting Regret” follows as in the Chinese content.]

The most weird mundane photo you can imagine.

Generate custom illustrations on demand

photorealistic, cinematic, high contrast, dark background, volumetric lighting, a beautiful woman wearing a futuristic helmet, detailed, 8k, ultra-detailed, high quality, sharp focus, hyper-detailed, high resolution, {argument name="style" default="cyberpunk"}

Today's theme is {argument name="theme" default="morning, noon, night, mandarin orange"}

Make me an infographic for: {argument name="source text" default="[paste your text here]"}

postgresql elephants sitting in a boxing arena eating popcorn an watching a boxing fight between a mysql dolphin and a mariadb sea lion.

A medium close-up, eye-level portrait of a {argument name="subject" default="man"} shown in a three-quarter profile facing right, holding a {argument name="accessory" default="distinctive accessory"}. He has dark messy hair, paired with a dense, sharply groomed full beard. He is wearing thick-rimmed, dark acetate sunglasses, a {argument name="outfit" default="tailored matte black blazer"}, and a deep plum-colored crewneck t-shirt. In his left hand, he holds up an oval, bright yellow mask featuring a simple black smiley face line, circular eye holes backed with black mesh, and realistic, weathered dark scuff marks across the surface. The lighting is soft and natural, emphasizing the textures of his hair and the contours of his profile against a smoothly blurred, neutral-toned outdoor background.