AI 提示词库

a banana, hyper detailed, photorealistic, 8k, professional photo, high quality, high resolution, --ar 16:9 --style raw --v 6.0

{ "prompt": "Use the uploaded image as the primary reference for composition, proportions, pose, objects, and overall layout. Preserve the original identity and facial features accurately. Convert the image into a refined pencil and ink sketch illustration. Use clean hand-drawn line work, controlled cross-hatching, and soft shading to define form and depth. Keep facial features, eyes, and hands sharp and expressive while allowing background details to remain minimal and lightly sketched. Overall look should feel like a professional hand-drawn illustration—elegant, timeless, and artistic (not cartoon).", "negative_prompt": "identity change, face mismatch, cartoon, anime, messy scribbles, heavy black fills, low quality, blur, noise, distorted anatomy, extra limbs, text, watermark, logo", "style": "pencil and ink sketch illustration", "mood": "classic, artistic, calm", "lighting": "illustrative light shading", "texture": "paper grain, pencil strokes", "render_quality": "ultra high resolution, hand-drawn quality", "reference_strength": 0.9 }

{ "type": "image_generation", "style": "cinematic semi-realistic 3D", "prompt": "Inside a small diner, a young female waitress with short brown hair is pouring black coffee from a glass coffee pot into a white mug held by a male customer. The waitress looks sad and emotional, with tears visible on her cheeks and a tired expression. She is wearing a fitted white long-sleeve top and a beige apron. The male customer is standing in front of her, wearing a dark blue suit, shown from a side angle. Other customers are seated in booths in the background. The diner has fluorescent ceiling lights, simple wooden booths, and a calm everyday atmosphere.", "camera": { "shot_type": "medium shot", "angle": "eye level", "focus": "waitress pouring coffee" }, "lighting": "bright indoor fluorescent lighting", "environment": "small diner interior with seated customers", "mood": "quiet, emotional, realistic", "aspect_ratio": "9:16" "quality": "high detail, sharp focus", "negative_prompt": "extra characters, dramatic action, exaggerated emotions, fantasy elements, blur, low quality, text, watermark" }

Draw the formula on the whiteboard, with its graph shown underneath the formula.

Harry Potter style Slander Viking Completely in English (I didn't ask for that, lol) Eiji Voldemort Mizuki Sirius Black 'In the style of XX' is important, lol

Create and output one picture {argument name="style" default="like Da Vinci's Last Supper"}!

Use an {argument name="angle_en" default="extremely low angle"}.

highly detailed vintage-style intaglio illustration of a {argument name="subject" default="surreal fish"} with muscular, articulated legs, confidently striding while wearing ornate {argument name="footwear" default="high-heeled cowboy boots"}, fine engraved linework, cross-hatching and stippling, monochrome ink on aged paper, centered composition with subtle decorative border, 19th-century scientific engraving aesthetic

A colossal {argument name="object" default="[OBJECT]"} reimagined as a complete natural biome. Tiny {argument name="wildlife" default="[WILDLIFE]"} has evolved to inhabit every niche the object provides. Predators hunt across its surfaces, herbivores graze in its cavities, birds nest in its heights, insects swarm its crevices. Food chains have formed around the object's geometry. Migration patterns follow its contours. Seasonal changes affect different zones. The object's materials have weathered into naturalistic terrain while remaining recognizable. Documentary aesthetic, golden wildlife lighting, the manufactured as wilderness.

(Photorealistic:1.3), raw photograph, cinematic lighting, sharp focus on the subject’s face and eyes, crisp skin texture. LAYER 1: BACKGROUND STABILITY (CRITICAL): The entire background environment from the input image remains completely STATIC, FROZEN, CLEAN, and UNCHANGED — no noise, no scanlines, no distortions, no glitches in the background. LAYER 2: FOREGROUND SUBJECT EDGE-CHAOS: The main subject’s core (face/torso) stays clear and undistorted, BUT the outer silhouette boundaries are unraveling violently into long ribbons of (non-glowing physical matter:1.3), showing stretched fabric/leather/latex-like material with realistic strand separation and tearing flow (“Spaghettification”), no gore. LAYER 3: ANALOG GLITCH OVERLAY (EDGE-ONLY): Heavy VHS static, scan lines, color bleed, and screen tearing noise are CONCENTRATED EXCLUSIVELY ON THE UNRAVELING EDGES of the main subject, like an edge mask. No full-frame VHS overlay; the core and background remain clean. LAYER 4: GHOSTLY AFTERIMAGES (BEHIND SUBJECT): Directly BEHIND the unraveling main subject, visible through the gaps, there are TWO translucent, ghostly motion-blur AFTERIMAGES. They are violently twisted into agonizing, struggling postures, dragged by temporal distortion. They remain behind the subject, partially occluded, not separate characters. Negative prompt (optional but recommended): full-frame glitch, background distortion, extra people, duplicate main subject, neon glow, energy beams, particles, blood, gore, exposed organs, messy face, blurry eyes, deformed hands

Viking Kotogemoto Mizukimoto Renamed Eiji Voldemort Mizuki Sirius Black

Subject & Action: A cinematic, painterly portrait of the man from the uploaded image, intensely focused as he paints a large-scale mural of himself. He holds a paintbrush, meticulously adding fine details to a life-sized self-portrait on a white wall. Both the artist and his mural counterpart are wearing identical outfits: a tan double-breasted trench coat over a white t-shirt. Environment & Details: In the lower foreground, a vibrant paint palette, various paint cans, and a bucket overflowing with brushes are visible. Artistic paint splatters mark the ground, showing the creative process. The background features a traditional building with clean white walls and elegant gray roof tiles. Lighting & Style: Cinematic editorial lighting with Rembrandt-inspired shadows that sculpt the face and body. A warm, golden key light balances with subtle fill, creating rich tonal depth and skin textures. Atmospheric and intimate mood, similar to a high-end Vanity Fair magazine cover. Fine-art warmth, soft gradients, and meticulously composed storytelling. --ar 1:1 --v 6.0

Retro-futuristic classics: 1950s muscle car reimagined with neon underglow, holographic dashboards, hovering wheels.

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

Keep the composition, clothing, expression, skin tone, hairstyle, and aspect ratio as they are, and only change the hair color to black.

Write a novel that begins with the line: "When I looked up at the blue sky, the Earth was floating there instead of the white moon."

generate a Hieronymus Bosch–style painting of the state of AI in 2025

使用参考图像作为精确的角色和服装参考，创建一个流畅、逼真的时尚走秀视频。在整个视频中保留她的面部特征、发型、服装、身体比例、颜色以及整体身份一致性。全身取景，电影级时尚摄影风格，自然真实的动作，柔和的日光。 场景 1 – 向前行走：她自信地站立开始，然后以优雅自然的步伐缓慢走向镜头。双手随意插在棒球夹克口袋中，头发随着每一步轻轻摆动。 场景 2 – 侧身姿势：在行走过程中，她稍微将身体转向侧面，短暂看向镜头，露出柔和自信的微笑。头发自然地跟随动作飘动。 场景 3 – 夹克姿势：她停下片刻，将重心移到一条腿上，微微向后挺胸，一只手留在夹克口袋里，另一只手随意调整夹克。 场景 4 – 最终行走与转身：她恢复行走，经过镜头后，轻轻回头越过肩膀，带着含蓄的微笑继续向前走。裙子和头发随动作自然摆动。 平滑的镜头跟踪，微妙的电影感运镜，真实的行走物理效果，自然的面部表情，逼真的布料和头发运动，无突然动作，无身体扭曲，无面部变化，无多余手指或肢体，一致的服装和外貌，高端时尚大片美学，垂直 2:3 比例，8–10 秒。

* Realistic depiction in anime style (animation style). * Colors blend the softness of "watercolor" and the smoothness of "digital illustration." Pay attention to "soft outlines" and "light reflections." * The texture of the person's skin should be "smooth" with "soft shading." It should combine realism with anime stylishness.

Ultra-high-end abstract composition. Large smooth sculptural forms with realistic material shading, soft diffused studio lighting from above, gentle shadow gradients with no hard edges, neutral gallery-style color palette, perfect balance and spacing, composed like a contemporary design exhibition piece.

SCENE IMAGE + FIGURE & HUMAN IMAGE YOU WANT TO INTEGRATE + PROMPT.

Analyze this image and then create a timeline of the events that led to this photograph. Make a storyboard as if it were a motion picture: a 9-panel storyboard grid showing the sequence of events, with each sequence in chronological order.

{   "prompt": "Adult woman with girl-next-door beauty, soft facial features, light freckles, medium brown hair, natural curves, pastel bikini, teasing confident pose, suburban pool setting, cinematic realism with soft depth of field",   "style": "cinematic realism",   "quality": "ultra",   "lighting": "soft afternoon light",   "camera": "50mm lens",   "mood": "playful, teasing",   "negative_prompt": "childlike appearance, nudity, explicit sexual detail" }

A seamless pattern of melting smiley faces in holographic glossy hot-pink against a black background. The smiley faces are distorted and fluid, with curved lines forming the eyes and mouths, some appearing to drip or stretch. The pattern is dense and covers the entire frame, with no discernible beginning or end.