AI 提示词库

A tranquil digital landscape featuring a vibrant, glowing sunset over distant mountains, with the sun casting {argument name="reflections" default="pastel reflections of pink, purple, and turquoise"} across a calm lake. Two small, forested islands with tall pine trees frame the foreground, and the overall mood is serene and dreamlike, with soft gradients and minimalistic composition set against a muted, hazy background. A surreal landscape featuring a lone figure standing beneath a large tree with {argument name="tree details" default="glowing purple leaves"} on a cliff edge, overlooking a distant mountain at sunset. A stream of luminous turquoise water flows down the cliff, emitting magical sparkles. The scene is bathed in soft pastel colors, creating a tranquil and mystical atmosphere.

Subject Description: A cinematic female warrior inspired by {argument name="inspiration" default="Mulan"}, strong, noble, and restrained beauty, calm yet determined expression Outfit: Elegant red ancient Chinese warrior costume inspired by traditional Han-style armor and flowing fabrics, minimal ornamentation, realistic textile texture, battle-worn yet refined Detail/Prop: Holding a long steel sword firmly in hand, simple and practical design, subtle reflections on the blade, heroic stance Setting: Quiet forest at early morning, soft mist among tall trees, muted natural colors, cinematic depth Style & Mood: High-end cinematic fantasy, realistic lighting, dramatic shadows, film still, epic yet poetic atmosphere, 35mm film look, cinematic color grading

Subject inserts a glowing Ridewatch into the Ziku-Driver and spins it 360 degrees. A 'mechanical reveal' begins as white and gold armor plates materialize piece-by-piece, snapping onto the torso, shoulders, and legs with robotic precision. Rapidly rotating golden clock hands and glowing orange pixelated data streams wrap around her body against a giant glowing crescent moon background. The sequence concludes with the helmet visor flashing pink katakana eyes as she shifts into a powerful combat stance, executing a sharp martial arts strike with her white cape flowing majestically.

A detailed technical blueprint of a high-performance AI GPU cluster placed on a polished brass drafting table, with a photorealistic miniature AI server system self-assembling from it — multiple GPU accelerator units (sleek black and metallic modules with neon green accents) rising from the dimension lines, high-speed interconnect bridges threading through the tolerance annotations, and dense compute nodes forming from the grid layout. Stacks of GPU cards slide into server chassis above the parts list, each unit locking in with precision. NVLink-style connectors and high-bandwidth interconnects assemble seamlessly between GPUs, forming a powerful parallel compute network. Rack-mounted AI servers emerge vertically, with layered compute blades building upward in perfect alignment. A liquid cooling system forms from exploded-diagram callouts — transparent cooling pipes with glowing coolant flowing through them, cold plates attaching to GPUs, and radiators assembling with high-performance fans. Heat dissipation fins and airflow channels dynamically shape around the system. A tiny engineer in futuristic protective gear stands on a GPU module inspecting circuits with a holographic diagnostic interface, while another miniature technician connects high-speed data cables into a switch unit. Fiber optic lines glow faintly, representing active data transfer. Functional details illuminate — GPU core lights pulsing softly, status LEDs blinking in synchronized patterns, data streams visualized as glowing lines moving between nodes, and monitoring panels activating during assembly. Signature tools of the trade — precision screwdriver, thermal paste applicator, anti-static tools, fiber connectors, and a digital diagnostic tablet — rest across the blueprint’s title block, partially integrated into the scene. All elements grow organically from the blueprint like a 3D mechanical diorama — circuit traces rising from printed schematics, GPU modules emerging from drawn outlines, cables threading through pencil grid lines. Seamless transformation from 2D blueprint into a fully operational AI infrastructure. LIGHTING: Soft studio lighting combined with strong neon green and cool blue glows from GPUs and data pathways. Subtle reflections from the brass surface and volumetric light enhancing depth. CAMERA & LENS: Shot on a full-frame camera, 35mm lens. Slight low-angle perspective to emphasize scale and power. Cinematic depth of field with focus on central GPU cluster. COMPOSITION: Vertical 2:3 format. Central stacked GPU cluster rising upward with symmetrical balance. Clean negative space around edges with layered depth. STYLE & MOOD: Futuristic, cinematic, high-end AI infrastructure aesthetic inspired by NVIDIA design language. Powerful, clean, and cutting-edge. DETAILS: Ultra-detailed textures — matte black metal, glowing accents, micro circuitry, cooling liquid reflections, cable braiding, LED indicators. 8K resolution, HDR,

一幅风格化的数字动漫插画，描绘了一位神情严肃、目光坚定的东亚少女，双臂交叉抱在胸前。她留着凌乱的黑色短发，部分扎成松散的丸子头，几缕发丝垂在脸颊两侧；她有着深邃传神的双眸和白皙的皮肤。她身穿一件宽松的深森林绿武术和服，内衬为浅鼠尾草绿，袖口宽大且有折叠设计，腰间系着黑色腰带（obi），胸前饰有醒目的金黄色闪电图案。背景采用大胆的黑色、白色和鲜艳的暖黄橙色调，呈现动态的墨迹飞溅效果。作品融合了矢量艺术与漫画插画风格，采用赛璐珞阴影、锐利的轮廓线、写意的笔触、戏剧性的光影以及高对比度，竖构图肖像 --ar 1:2 --v 6.0

Highly detailed caricature figurine of {argument name="subject" default="[SUBJECT]"} as a cute but intense bobblehead-style collectible statue, exaggerated oversized head with hyper-realistic facial features, deep wrinkles, fierce intense expression, slightly open mouth showing teeth, sitting relaxed in a vintage armchair, wearing {argument name="outfit" default="[OUTFIT]"}, dramatic colorful studio lighting, {argument name="background" default="[BACKGROUND]"}, modern collectible toy photography style, sharp focus, cinematic depth of field, extremely intricate sculpting details, realistic skin texture, professional product photography, 8k quality

{argument name="subject" default="Cyclops"} with an {argument name="accessory" default="eye patch"}

{ "prompt": "A highly detailed digital painting of the Joker in a menacing close-up portrait. He has pale white skin with classic clown makeup: black diamond shapes around his intense yellow-green eyes, a red nose, and an exaggerated wide red smile revealing teeth. His hair is wild, curly, and green-tinted. He wears a large {argument name="hat color" default="purple"} cowboy hat with a wide brim and a green hat band. His outfit consists of a purple suit jacket with a Joker playing card pinned to the lapel, a colorful patterned shirt, and a loose green cravat tie. The background is an abstract, textured blend of warm and cool colors including purples, yellows, oranges, and teals with visible brush strokes and subtle star shapes. Dramatic lighting emphasizes his sinister grin and facial details. Oil painting style with rich textures, vibrant colors, high contrast, and a dark, chaotic atmosphere." }

Create a high-quality 3D avatar of the person in the uploaded image with a cheerful, expressive face. The character should have a warm smile, bright eyes, and soft facial features that feel friendly and approachable. Render in a Pixar-style aesthetic with smooth textures, subtle skin shading, and slightly exaggerated proportions for a cute, animated look. Lighting should be soft and even, creating a clean studio look with gentle shadows for depth.

An image explaining the internal structure of a robot. Analyze the internal structure of the machine. Be sure to correctly display the skeleton and frame. Always keep the surface and maintain the background.

lego explorer minifigure driving a mini snowmobile across icy terrain chased by a massive roaring polar bear, snow spraying dramatically behind, frozen mist in the air, intense cinematic backlight, dynamic tilted camera shot, blockbuster action style, exaggerated comic motion, crisp lego plastic texture, dramatic cold color grading

A close-up shot of a man with scissors, claymation, stop motion animation, miniature diorama, realistic clay texture, visible fingerprints, warm lighting, high detail, 8k

{argument name="subject" default="dark dragon"} VS. {argument name="opponent" default="vegetations"}

WHIMSICAL MONO-PUNK FLOATING MINIATURE DIORAMA PROMPT (Automatic Background Optimization, Smart Micro-Detail System, Procedural Activity Layer, Natural Irregularity Layer, Atmospheric Depth Layer, Procedural Scene Generator, Procedural Prop Generator, Procedural Architecture Generator, Procedural Lighting & Atmosphere Generator, Procedural Character & Population Generator, Procedural Diorama Base Generator) VARIABLE GUIDE GLOBAL_COMPLEXITY = Possible values: 'low','medium','high','ultra'. Controls density of buildings, props, characters, and environmental detail. If blank choose randomly between 'medium' and 'high'. PUNK_STYLE = If PUNK_STYLE is empty, then one style is randomly selected from LIST_OF_PUNK_STYLES, otherwise what is in the PUNK_STYLE variable is chosen 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, Cattlepunk, Hopepunk SUBSTYLE = If specified use exactly. If set to none disable. If blank infer logically from PUNK_STYLE. TECHNOLOGY_LEVEL = If specified use exactly. If set to none disable. If blank infer from PUNK_STYLE. ENVIRONMENT = If specified use exactly. If set to none disable. If blank infer logically from active layers. CULTURE = If specified use exactly. If set to none disable. If blank infer culturally appropriate framework. PROCEDURAL_SCENE_GENERATOR = 'on' PROCEDURAL_PROP_GENERATOR = 'on' PROCEDURAL_ARCHITECTURE_GENERATOR = 'on' PROCEDURAL_LIGHTING_ATMOSPHERE_GENERATOR = 'on' PROCEDURAL_CHARACTER_POPULATION_GENERATOR = 'on' PROCEDURAL_DIORAMA_BASE_GENERATOR = 'on' FOCAL_INTEREST_LAYER = off MATERIAL_COHESION_LAYER = 'on' VISUAL_CLARITY_OPTIMIZER = 'on' MICRO_LIFE_LAYER = 'on' COMPOSITION_ENGINE = 'on' EDGE_DEFINITION_LAYER = 'on' COLOR_HARMONY_LAYER = 'on' DIORAMA_CRAFTSMANSHIP_LAYER = 'on' PSG LAYER Implement only if PROCEDURAL_SCENE_GENERATOR='on'. Generate core scene structure using: LANDSCAPE_STRUCTURE (floating island, cliff terraces, canyon basin, harbor cove, forest clearing, mountain ridge, giant tree canopy, desert oasis, ice shelf, volcanic ridge) SETTLEMENT_TYPE (village, harbor town, trading port, monastery complex, research outpost, fortress town, sky dock, industrial district, hidden enclave) INFRASTRUCTURE_ELEMENTS (bridges, windmills, rail lines, cable lifts, aqueducts, airship docks, solar arrays, reactor towers, waterwheels) CIVILIAN_ACTIVITY (market trading, fishing, cargo loading, harvesting, machine repair, patrol movement, festival gathering, workshop crafting) MICRO_NARRATIVE (delivery arrival, festival beginning, storm approaching, caravan arrival, wildlife encoun

Character sheet, multiple angles of a sci-fi tactical soldier in full body {argument name="armor color" default="matte-black"} armor. He wears a faceless helmet with a thin, dim {argument name="visor color" default="white"} horizontal glowing visor line. Gritty, brutalist design, heavy Kevlar and carbon fiber textures. Clean studio lighting, white background, ultra realist, front view, side view. --ar 16:9

Cinematic portrait of a young girl with messy {argument name="hair color" default="vibrant ginger hair"} tied in a loose bun and subtle freckles across her nose, gazing upward with a wistful, thoughtful expression. She wears cracked vintage welding goggles pushed up onto her forehead with fractured blue circular lenses. Wearing a heavily distressed, oversized {argument name="hoodie color" default="mustard-yellow hoodie"} covered in paint splatters, frayed seams, patched denim fabric on the sleeves, and a faded embroidered skull patch on the forearm, along with rugged, dusty work gloves. Background is a weathered, peeling wall with {argument name="wall color" default="chipped turquoise and faded yellow paint"}. Soft dramatic directional lighting, gritty post-apocalyptic aesthetic, 85mm lens, shallow depth of field, hyper-detailed fabric textures.

Rorona-style girl, {argument name="age range" default="18-20 years old"}, {argument name="hair description" default="soft pink-gold long wavy hair"}, {argument name="eyes and face" default="large gentle eyes, slightly round face"}, {argument name="skin" default="fair bright skin"}, {argument name="outfit" default="light magical-academy outfit in white and pink-gold accents"}, {argument name="outfit details" default="delicate gold patterns, thin pendant, small waist pouch"}, {argument name="atmosphere" default="elegant and soft atmosphere"}, expressions: {argument name="expressions" default="warm smile / calm confidence / spiritual clarity"}, consistent character, same face every frame, {argument name="line art style" default="thin line art"}, {argument name="rendering style" default="webtoon style"}, {argument name="shading" default="soft gradients"}, {argument name="detail level" default="high detail"}, {argument name="overall style" default="Japanese fantasy modern style"}, {argument name="color tone" default="clean and bright color tone"}

This is a Nano Banana Pro prompt for generating siblings of a character based on a reference illustration. It works by simply specifying sister or brother within the prompt. It is likely possible to specify mother or grandfather as well. It allows specifying multiple people, not just one. It also allows specifying individual characteristics. The first image was output with the following: {argument name="Siblings to generate" default="One sister (funky), one sister (Jirai-kei), one brother (muscle-head), one sister (shut-in)"} Sizes can also be customized, such as vertical, horizontal, or square, not just the original.

unwrap the UVs of the 3D model shown in the image. About one-third of the image should be a reference view displaying the 3D model itself.The remaining area should include the UV layout for the head, body, and limbs.Unwrap the surface of the 3D model and flatten it into a single 0–1 two-dimensional UV space.

Cute stylized 3D collectible figurine inspired by a football star, with stylized hair and a sporty outfit, sitting casually on a tiny gaming chair holding a game controller. A small gaming setup with RGB keyboard, monitor, and headphones sits beside him. The scene is arranged on a wooden desk with warm ambient lighting, shallow depth of field, cozy gamer room background with blurred neon lights, Pixar-style 3D render, glossy collectible toy finish, cinematic lighting, ultra-detailed designer toy photography.

A detailed character design sheet for a male mage titled "The Arcanist's Ledger." The character has {argument name="hair" default="short, tousled auburn hair"}, pointed ears, and {argument name="horns" default="crystalline blue horns"}. He wears an ornate, floor-length {argument name="robe color" default="navy blue"} robe decorated with glowing celestial constellations and gold embroidery. The layout includes full front and back views, a side-profile headshot, and close-up technical drawings of his magical accessories: a crystal-tipped staff, a circular geometric pendant, and intricate ear cuffs. The aesthetic is a clean, vintage parchment style with structured annotations and calligraphic headings.

KNIGHT MECHA GIRL Re : No.9 Crimson Vindicator {argument name="scale" default="1/7 scale"} plastic model {argument name="style" default="line art setting material style"}

Replace {argument name="original object" default="the simple arrangement of rectangular parallelepipeds"} with {argument name="new subject" default="a group of buildings"} while keeping the UI as it is.

Generate a surface normal map from the input artwork image. Output one RGB image where each pixel encodes the surface normal direction in standard tangent-space format: • R = X direction • G = Y direction • B = Z direction Requirements: • Maintain the same resolution and aspect ratio as the input image. • Normal directions must follow the local geometry implied by brush strokes, shading, and contours. • Do NOT add new artistic elements or repaint the scene. • Only infer plausible micro-geometry and surface orientation. • Ensure smooth, consistent normal transitions without noise. Generate a depth map from the input artwork image. Output a single grayscale depth map where: • White = near to the viewer • Black = far from the viewer Requirements: • Maintain the same resolution and aspect ratio as the input image. • Depth must be smooth, continuous, and physically plausible. • Infer only geometric depth that could reasonably exist in the original artwork. • Do NOT add new objects or details. • Do NOT stylize, repaint, or reinterpret the scene. • Avoid texture noise; focus solely on depth structure.