AI 提示词库

A highly detailed 3D cartoon sculpture of three whimsical children stacked on top of each other on a small rustic house. The children have exaggerated features: large round eyes, big ears, small noses, and rosy cheeks. The top child has wild, messy hair, wearing a blue checkered dress, looking excited with mouth open showing teeth. The middle child has short hair, a brown sweater, gray pants, a gray cap, looking surprised. The bottom child has wavy hair, wearing a muted patterned dress, looking worried and nervous. Each child has oversized shoes and expressive poses. The tiny house at the bottom is textured with stone walls, wooden windows, and a blue door, slightly crooked. Realistic shading and textures, ultra-detailed, cinematic lighting, depth of field, hyper-realistic clay sculpture style. Optional style tags: hyper-detailed, cinematic lighting, whimsical, clay sculpture, 3D cartoon, expressive characters, ultra-realistic textures, soft shadows

生成一段 6 秒、9:16 竖屏、4K 超写实真人实拍的古风人像视频。 主体为一位明显成年的东亚女性，身着华丽、清晰、轻盈的唐制汉服，站在夜色中的花树前。 人物拥有自然柔和的鹅蛋脸，下颌线条小巧流畅，五官精致但保持真实比例，无网红模板脸，无西式骨相。 黑色浓密长发盘成高耸复杂的唐式发髻，饱满且富有层次，顶部及两侧装饰有： 浅粉色花卉发簪 浅蓝色花卉饰物 翠绿色叶片 串珠 珍珠流苏 金属发钗 长款垂坠耳环 两侧保留长直黑发，自然垂落至胸前。 额前有少许柔和碎发。 妆容精致而通透： 桃粉色眼影 自然黑色眼线 根根分明的睫毛 原生自然眉形 浅粉色腮红 水润珊瑚粉唇色 略带花钿感的妆效 皮肤白皙、通透、柔软，但不具塑料感，保留轻微毛孔、细腻的皮肤纹理变化及自然的面部不对称性。 ⸻ 服饰 角色身着非常华丽的浅青蓝 + 薄荷绿 + 淡粉 + 象牙白多层唐制襦裙。 外层为半透明薄纱披帛与广袖。 袖子宽大飘逸。 袖口、领口及衣襟处有精致的： 花卉刺绣 金线镶边 浅粉蓝色植物纹样 胸部区域采用唐制高腰襦裙结构。 胸口位置有大面积精致花卉刺绣。 腰部系有蓝绿色束带。 裙身具有明显的丝绸与纱质分层。 材质需体现： 真实丝绸光泽 轻纱半透明度 绣线细节 衣袖自然垂坠感 避免廉价影楼汉服质感。 ⸻ 场景 背景为夜晚或暗环境下的盛开花树。 大量白色、浅粉色及淡紫色花朵分布于人物身后。 整体背景偏暗。 花朵在柔光下形成浅色点缀。 人物与背景层级分明。 无仙侠特效。 无大量粒子效果。 无月亮。 无宫殿大场景。 重点在于： 人物特写 + 暗色花树背景。 ⸻ 0–1s | 正面凝视 开场人物正对镜头。 身体微侧，但面部几乎正对相机。 双眼直视镜头。 嘴角带有极轻微、柔和的微笑。 右手自然置于胸前附近。 左手隐藏于广袖之下或身体下方。 整个人保持静谧优雅。 相机使用胸部以上的中近景。 ⸻ 1–2s | 手托下巴 角色缓慢将一只手从胸前抬起。 手腕保持柔和弯曲。 手指自然舒展。 不僵硬。 手背略微朝向镜头。 手部动作缓慢地从胸前经过颈部区域移至下巴下方。 形成古典仕女优雅的托腮动作。 角色眼神仍注视镜头。 微笑略微加深。 ⸻ 2–3.2s | 手继续移向发髻 手在下巴处停留时间不长。 继续缓慢沿脸部侧面向上移动。 经过： 脸颊 太阳穴 耳侧 最终抬升至头顶发髻附近。 食指、中指和无名指轻柔地靠近发饰。 动作柔和克制。 不要用力抓头发。 更像是轻轻扶住发簪或调整发髻。 随着手臂抬起，广袖自然下垂。 薄纱袖口形成美丽的层次感。 ⸻ 3.2–4.5s | 扶发 + 微转身 角色保持一只手轻扶发髻。 同时身体和头部开始小幅度转动。 大约： 5–10 度。 面部从完全正面变为轻微的 3/4 角度。 眼睛仍注视镜头。 嘴角保持柔和微笑。 另一只手自然置于身前。 衣袖和披帛出现轻微摆动。 发簪上的珍珠流苏也产生极小的自然晃动。 ⸻ 4.5–6s | 侧颜微笑结尾 角色保持手在发髻附近。 头部倾斜度略微增加。 形成优美的浅 3/4 肖像角度。 眼睛仍注视镜头。 表情比开场时稍显柔和。 微笑自然。 无露齿大笑。 广袖保持自然垂坠。 耳环、珠串和发饰轻微摇曳。 结尾保持约 0.5 秒静止。 ⸻ 相机与运动 使用： 70–85mm 等效人像镜头 胸部以上特写。 相机高度略低于或与角色视线平齐。 角色始终位于画面中心。 视频基本保持固定机位。 仅允许： 极其细微的推进 约 3%-5% 的微弱前进。 同时存在轻微的： 电影感呼吸起伏 无平移。 无快速变焦。 无环绕拍摄。 无大幅横向移动。 ⸻ 灯光 采用柔和经典棚拍布光 + 夜间花树背景。 角色面部使用柔和的前侧光。 面部整体非常明亮。 鼻梁、颧骨和嘴唇上有柔和的高光。 头发边缘可有轻微轮廓光。 背景保持黑暗。 花朵被轻微照亮。 形成： 明亮人物 + 黑暗背景 + 浅色花朵 高级对比度。 整体色彩建议： 浅青蓝 薄荷绿 淡粉 珍珠白 深黑背景

Take this screenshot and edit it. The graphics are too modern. please make this look like a 90s boomer shooter.

{ "scene_type": "photorealistic fantasy", "setting": { "location": "vast ancient cavern", "floor": "rugged stone floor", "lighting": { "primary": "dim", "ambient": "soft pink light", "source": "distant stone archway", "additional": "natural shadows, lifelike lighting, soft light refraction" }, "atmosphere": [ "scattered flowers", "broken stone", "drifting dust particles", "cinematic depth of field" ] }, "main_character": { "type": "fairy woman", "skin_tone": "fair-skinned", "hair": { "color": "white", "style": "long, flowing" }, "facial_features": { "freckles": "subtle", "ears": "pointed" }, "wings": { "type": "large butterfly wings", "properties": [ "translucent", "iridescent", "shimmering blue-green hues", "visible veins", "soft light refraction" ] }, "clothing": { "style": "emerald medieval-inspired", "pieces": [ { "type": "cropped top", "material": "richly textured fabric" }, { "type": "high-waisted bottoms", "material": "richly textured fabric" } ], "details": [ "realistic gold filigree", "engraved ornaments", "worn metallic highlights" ] }, "pose": "seated on the stone floor", "expression": "calm" }, "companion": { "type": "massive muscular bear", "fur": { "description": "dense, coarse", "detail_level": "ultra-sharp" }, "eyes": "striking icy blue", "armor": { "type": "{argument name=\"bear armor type\" default=\"faint green rune-like markings\"}", "location": ["head", "shoulders"], "effect": "glowing softly" }, "pose": "leaning calmly beside the fairy", "relationship": "conveying trust and companionship" }, "interaction": { "description": "Her arm rests gently over the bear’s head" }, "technical": [ "ultra-realistic textures", "photorealistic rendering", "cinematic depth of field", "natural shadows", "lifelike lighting" ] }

Please create a fighting pose for the attached character based on the character sheet. Faithfully reproduce the character's details and coloring. Recreate the scene with a camera angle from a diagonal side view, depicting the character posing on a cliff overlooking the sea. Use a realistic photo style, and output the aspect ratio as 16:9.

A hyper-realistic cinematic close-up portrait of a battle-worn shirtless male fighter, head bowed downward in exhaustion or grim determination after a brutal fight. He has thick dark disheveled hair — soaking wet, matted, and falling forward over his bowed forehead in heavy clumps. A full thick dark beard covers his jaw and chin. His face is tilted down at roughly a 45-degree angle, showing mostly the top and side of his head, his powerful thick neck, and broad bare shoulders filling the lower frame. His skin is drenched in rain and sweat, glistening intensely. His face and neck show visible battle damage — multiple small cuts, lacerations, and blood streaks across the forehead, brow, cheek, and shoulder, skin reddened and bruised from impact. Rain falls visibly around him — individual rain streaks caught sharp against the background, hitting his skin and hair and scattering into fine mist. The background is a blurred cool grey-green misty environment — suggesting an outdoor arena, rainy battlefield, or open fight setting — with diffused white light sources creating a hazy atmospheric glow behind him. The lighting is dramatic and cinematic — a cool blue-grey ambient light wraps the scene while a subtle warmer tone catches the skin highlights on the brow ridge, nose, cheekbone, and shoulder. Color palette: deep charcoal black, cool grey-green, muted olive, warm blood-red accents, wet skin highlights. Art style: hyper-realistic dark cinematic concept art or video game cutscene quality — The Last of Us / God of War aesthetic, extreme surface detail on skin, hair, and water, volumetric rain atmosphere, 8K. Use the provided face reference image — preserve the exact facial bone structure, nose shape, jawline, beard pattern, skin tone, and overall facial identity of the reference subject. Apply the battle damage, rain, and exhaustion treatment on top while keeping the core facial identity completely recognizable.

Using 100% likeness of (reference) objects, transformed into a {argument name="style" default="dynamic, semi-realistic digital illustration style"} with a cinematic concept art aesthetic, combining sharp anime-inspired rendering and high-end game splash art. Strong, angular brushstrokes with confident hand-painted strokes, clean yet expressive line accents, and artistic layered shading. High-contrast lighting with bright warm highlights and deep neutral shadows, creating dramatic depth and intensity. The color palette is dominated by {argument name="colors" default="warm ivory, soft beige, sand, light gray, charcoal, and bright orange"} as the main accents, with subtle black details. Smooth gradient transitions mixed with sharp edge highlights, realistic material rendering for metal, fabric, and hard surfaces. Energetic composition, {argument name="detail level" default="highly detailed textures"}, bold and smooth silhouettes. No text, no logo, no watermark. AR 9:16.

A clean 4-panel split composition featuring four stylized 3D cartoon figures, each standing in their own section. Panel 1: A clown-inspired villain character with green slicked-back hair, white face paint, red suit, yellow vest, holding a cane, playful yet mischievous expression. Panel 2: A dark masked vigilante in a sleek black suit with a cape, minimalistic armor details, confident stance. Panel 3: A billionaire tech hero in a futuristic red and gold armored suit, glowing chest core, standing upright with arms slightly open. Panel 4: A purple-skinned cosmic villain in golden armor, muscular build, standing with dominance and a slight smirk. Style: highly detailed 3D toy-like characters, smooth plastic texture, Pixar-style rendering, soft studio lighting, vibrant pastel gradient backgrounds (each panel different color), ultra clean composition, sharp focus, cinematic lighting, minimal shadows. Layout: perfectly divided 4 equal vertical panels, each character centered in their panel, consistent framing and scale. Quality: ultra high resolution, 8k, Octane render, Unreal Engine style, professional product render look.

[{argument name="subject" default="Subject"}], stylized 3D rubberhose character, smooth 3D render, Solid {argument name="color" default="Color"} color background, dynamic pose, soft ground shadow, bright soft lighting, modern playful design

Please use the attached reference image as the base character. Create a single high-resolution collage containing at least 20 cute sticker-style illustrations of the same female character. Ensure the face, skin tone, hairstyle, and overall appearance perfectly match the reference image. Art Style: {argument name="art style" default="3D Pixar-style / Disney-style cartoon"}, soft cinematic lighting, smooth pastel colors, large expressive eyes, rounded cute facial proportions, ultra-detailed 3D rendering. Character Details: – Lightly permed black hair – Large expressive eyes – Beige cardigan – Cute, slightly chubby proportions Expressions and Reactions (all distinct): Happy smile, surprised, shocked, shy smile, angry, confused, crying, sleepy, winking, peace sign, blowing a kiss, holding a cell phone, thinking, covering face, holding coffee, covering mouth while laughing, annoyed, excited, affectionate expression, cute neutral pose (over 20 total). Sticker Design: – Each reaction as a separate sticker – Clean white border on all stickers – Soft drop shadow – No text, no watermark Layout: – All stickers neatly arranged in one collage – Balanced grid layout – Soft beige/pastel-toned background – Instagram/WhatsApp-style sticker pack design Quality: Ultra-high definition, high resolution, smooth 3D finish, professional-grade sticker pack style, lovingly expressive.

A vintage magical study portrait with 1990s aesthetics, featuring glowing objects and a woman in an elegant yellow dress.

dynamic mid-air explosion effect, {argument name="target" default="object"} breaking apart into multiple fragments, pieces flying outward in all directions, suspended debris and particles floating in space, cinematic slow motion freeze frame, realistic physics, small dust particles and crumbs scattering, dramatic depth of field, high-speed photography style, sharp focus on central object, fragments rotating in mid-air, motion energy burst from the center, ultra detailed, volumetric lighting, photorealistic, 8k

“A stylized illustration of [{argument name="character type" default="CHARACTER TYPE"}] with [{argument name="distinct feature" default="DISTINCT FEATURE / ACCESSORY"}]. Simplified shapes, expressive body language with heavy facial details. Illustration style: [{argument name="illustration style" default="FLAT / CEL-SHADED / SOFT 3D"}]. Color palette: [MUTED / VIBRANT / MONOCHROME]. Background minimal and abstract”

Take the character image from the anime's official website and give it to Nano Banana Pro. Instruct it to "Generate an image of a 3DCG woman wearing the hair and clothes from the anime drawing."

Keep this character’s appearance the same but change only their clothes.

1980s color RPG manual illustration.

Do this for a random character: <instruction> Split Identity Vinyl Toy Engine: Input A is a Character with duality. Select 4 lesser-known characters with internal conflict. Sculpt each toy split vertically or horizontally into two contrasting halves. Each half represents a different narrative state. Layout: 2x2 grid, toys centered, perfectly symmetrical framing, name underneath Style Stack: Anchor: [Split vinyl art toy]::3.5 Morphology: Bulbous toy proportions, clean bisected geometry::3 Material: Soft vinyl, contrasting matte colors::2.5 Render: Product photography lighting, neutral backdrop::1 Negative: [organic gore, realism, asymmetry]::-1

legendary dragon emerging from glitch storm, pixel sorting distortion, RGB color split, fragmented wings, epic cinematic atmosphere, highly detailed

Whimsical miniature world depiction of a {argument name="subject" default="grand botanical greenhouse conservatory"} imagined and rendered in an {argument name="art style" default="artistic clockpunk"} style.

the classic Japanese Bosozoku ({argument name="gender" default="M"}) in the style of a 3D model asset

"Make it in LEGO version. Include the typical LEGO features (yellow skin, shrunken person size, and square edges and pixels)"

The wings are composed of {argument name="material" default="mother-of-pearl"} wings, iridescent shell surface wings, pearlescent reflections on the wings, overlapping mother-of-pearl plates on the wings, layered decorative plates on the wings, wing-inspired plate work, decorative feather structure, stacked decorative plates on the wings, layered plate structure of the wings, luxurious decorative craftsmanship on the wings, three-dimensional layered details on the wings, and elegant decorative composition of the wings.

Variable Guide 1. OVERALL_DIORAMA_THEME = {argument name="diorama theme" default="Scenes from Adventures of Sherlock Holmes by Arthur Conan Doyle, in the order in which they are presented in the book"} 2. CUPBOARD_BASE_MATERIAL = 3. CUPBOARD_LINING_MATERIAL = 4. RACK_MATERIAL = 5. ORNAMENTATION_STYLE = [e.g., Gothic carved wood, Art Deco brass, Elven interlaced vines] 6. ART_STYLE = Hyper-Realistic Render 7. TOP_SHELF_SCENE = {argument name="top shelf scene" default="[Describe specific actions of miniature figures defining the scene]"} 8. MIDDLE_SHELF_SCENE = [Describe specific actions of miniature figures defining the scene] 9. BOTTOM_SHELF_SCENE = [Describe specific actions of miniature figures defining the scene] 10. LIGHTING = 11. CAMERA_ANGLE = A straight-on, front-facing view, captured from a moderately high angle looking distinctly downward. 12. ASPECT_RATIO = 3:4 Generation Directives (Note: If any variable is left blank, intelligently infer the most appropriate detail based on the OVERALL_DIORAMA_THEME) Directive 1: Framing & Composition (Highest Priority) A direct, front-facing photograph captured from CAMERA_ANGLE. The composition must perfectly center the open display structure, looking down at a distinct angle into the shelves to clearly reveal the floor plates and top-down depth of the miniature objects within the dioramas, while ensuring the exterior side panels remain completely hidden. The entire free-standing structure must be completely visible with negative space around it against a simple background. The aspect ratio is 3:4. Directive 2: The Main Structure (Strict Constraints) Render the image in the style of ART_STYLE. The central object is a highly detailed, permanently open-front curio display structure. It must not possess doors, hinges, or door frames of any kind. The exterior is constructed from CUPBOARD_BASE_MATERIAL and detailed with ORNAMENTATION_STYLE. The interior back wall is lined with CUPBOARD_LINING_MATERIAL, and the individual shelves are made of RACK_MATERIAL. Directive 3: The Miniature Dioramas & Figures The structure houses a cohesive miniature world divided across three shelves, adhering to the OVERALL_DIORAMA_THEME. Crucially, each shelf must contain miniature figures engaged in a specific narrative action. * Top Shelf: Miniature figures are depicted [TOP_SHELF_SCENE]. * Middle Shelf: Miniature figures are depicted [MIDDLE_SHELF_SCENE]. * Bottom Shelf: Miniature figures are depicted [BOTTOM_SHELF_SCENE]. Ensure the scale clearly reads as miniature dioramas housed within a furniture piece. Directive 4: Atmosphere & Lighting The scene is illuminated by LIGHTING. The lighting should cast appropriate micro-shadows within each shelf to emphasize the depth, the figures, and the miniature scale of the dioramas.

the {argument name="subject part" default="dog's mouth"} is {argument name="state" default="closed"}.