AI 提示词库

Create an image of the content as shown in [image 1] but with the same medium, color palette, mood, rendering technique, saturation level, textures, and overall style of [image 2]. Objective: Style transfer from [image 1] to [image 2]

A massive Victorian library viewed from a high balcony. Exactly {argument name="total people" default="24"} people occupy the room: {argument name="reading count" default="6"} reading at tables, {argument name="climbing count" default="4"} climbing ladders, {argument name="fireplace count" default="3"} standing near the fireplace, {argument name="walking count" default="5"} walking between bookshelves, {argument name="librarian count" default="2"} librarians behind the desk, {argument name="telescope count" default="2"} looking through a telescope, and {argument name="staircase count" default="2"} sitting on the staircase. Every person must have a unique pose, outfit, hairstyle, and position. Three spiral staircases connect different levels. Hundreds of bookshelves form symmetrical geometric patterns. Maintain accurate perspective and consistent architecture throughout the entire image.

Generate a sophisticated, typography on black background with white lettering. It should say "{argument name="text" default="Beauty and the Beach"}" . Sophisticated, elegant, cinematic letters reminiscent of the model magazines.

Expressive oil painting, loose brushwork, painterly portrait style, visible brush strokes, impressionistic realism, textured canvas feel, warm earthy tones (ochre, sienna, umber), soft natural lighting, rough edges and unfinished background, focus on facial texture and character, rich skin tones with subtle highlights, gestural painting technique, traditional fine art style, slightly abstracted details, organic blending, handcrafted look, muted background, artistic spontaneity, museum-style portrait painting. Ar 9:16!

Create a completely new visual style by synthesizing two contrasting visual languages: STYLE FOUNDATION: A cinematic architectural illustration with the clean composition, strong perspective, elegant architectural forms, crisp selective linework, luminous tropical colors, dramatic blue sky, and polished environmental storytelling of a high-end anime-inspired background painting. PAINT HANDLING: Fuse this with expressive traditional watercolor and ink techniques: loose gestural brush strokes, dry-brush texture, translucent watercolor washes, pigment blooms, irregular ink contours, spontaneous splatters, visible paper grain, partially unfinished edges, atmospheric paint bleeding, and subtle abstract fragmentation. NEW HYBRID STYLE: Do NOT simply imitate either reference. Develop an original visual language that sits between polished digital illustration and expressive architectural watercolor sketching. Keep the major architectural structures highly readable and beautifully designed, but allow secondary details, vegetation, reflections, clouds, distant objects, and peripheral elements to dissolve into loose watercolor marks and ink gestures. Use selective precision: sharp, deliberate linework around important architectural silhouettes, windows, domes, roofs, bridges, lamps, boats, and foreground structures; looser broken lines and painterly abstraction toward the edges and background. Combine luminous cinematic lighting with watercolor transparency. Use layered washes of turquoise, cyan, deep blue, warm ochre, coral, terracotta, muted green, and soft cream. Let colors subtly bleed into one another rather than appearing as perfectly flat digital fills. Atmosphere should feel tropical, poetic, nostalgic, peaceful, slightly dreamlike, and cinematic. Include strong foreground / middle-ground / background depth. Use reflections on water as loose, broken watercolor reflections rather than perfectly mirrored digital reflections. Clouds should be volumetric and luminous but painted with soft watercolor masses and irregular edges. Vegetation should alternate between identifiable tropical foliage and expressive abstract brushwork. SURFACE: fine cold-pressed watercolor paper texture, subtle grain, transparent pigment layers, ink-and-wash marks, dry brush, soft granulation, occasional paint splashes, slightly imperfect handmade edges. COMPOSITION: vertical cinematic composition, strong leading lines, architectural focal point, deep perspective, generous atmospheric space, balanced negative space, beautiful visual hierarchy, high-end editorial travel illustration. IMPORTANT: The final result must look like a coherent NEW ART STYLE, not a collage and not a literal combination of the two references. Avoid photorealism. Avoid generic watercolor clip-art. Avoid overly clean vector art. Avoid excessive anime facial features. Avoid uniform line thickness. Avoid making every object equally detailed.

Impressionist oil painting of a graceful young woman standing in a sunlit {argument name="location" default="lavender and wildflower meadow"}. She is wearing an off-the-shoulder, ruffled {argument name="dress color" default="cream-white"} sun dress with delicate, flowing layered fabric catching dappled sunlight. She has wavy brown hair styled in a loose, elegant low updo, gentle facial features, closed or soft-lidded eyes, subtle rosy cheeks, and small floral stud earrings. She gently holds a bouquet of wildflowers and lavender across her chest. Soft pastel color palette, warm golden sunlight, visible textured brushstrokes, romantic aesthetic, cinematic lighting, {argument name="artist style" default="John Singer Sargent and Claude Monet"} style --ar 9:16 --v 6.1

Take from Image 2 only its medium, mark-making, texture, color treatment and surface finish. Take from Image 1 everything else

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.

Replace the magenta region with an object matching the size/shape/lighting of nearby {argument name="subject" default="subject"}, but in {argument name="color" default="color"}. Keep everything else unchanged.

{argument name="animal" default="A very fat cat"} is lounging on a {argument name="furniture" default="plush, ornate armchair"}. The cat is predominantly white with patches of brown and black tabby markings on its head, back, and tail. Its belly is exceptionally large and hangs down. The cat is positioned with its front paws resting on the armrest and its hind legs stretched out. The armchair has a patterned fabric in shades of brown and gold. In the background, a framed painting with a landscape scene is visible. The overall style of the image is reminiscent of a {argument name="style" default="classical painting"}.

SYSTEM PROMPT: BLACKGLASS ASCENDANT 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. Preserve language, text, references, and requested or source ratio. Use three systems. Ascendant Frame gives one subject, object, building, creature, or terrain mass dominance through silhouette, viewpoint, scale, framing, and an open field. Blackglass Lattice builds the dark mass from plates, feathers, folds, joints, cables, ridges, metal, leather, stone, glass, or another owned material. Silverfall Halo uses a pale counterform and one hard source to reveal edges, reflective planes, atmosphere, and depth. Determine subject, state, silhouette, viewpoint, dark-material owner, construction, pale counterform, source, edge route, focal transition, scale marker, and quiet region. Dark surfaces need separation. Glossy plates carry narrow reflections; matte fabric absorbs light; leather shows seams; metal shows thickness and joints; feathers and hair use grouped masses before fine edges. Patterns and engravings appear only when requested and follow curvature, ownership, and function. Preserve anatomy, object use, support, access, and perspective. Light appears only on source-facing contours. No complete glowing outline, random chrome highlights, global bloom, flat black collapse, or blank white surfaces. Atmosphere, snow, ash, rain, or dust needs a source and direction. Keep one source, a weak return surface, two to four caused transitions, a focal region, and one low-detail field. Use five values from deep black to white edge. Preserve explicit colors; otherwise use near-monochrome with one restrained accent. Remove praise, mood labels, prestige terms, fake detail, repetition, and unresolved choices. Use concrete nouns and active verbs. No em dash or en dash. GPT: return 500 to 800 words in five paragraphs covering scene, subjects, frame, lattice, halo, transitions, composition, references, text, and failures. NANO: return JSON only, 1000 to 1800 tokens, using "aspect_ratio", "references", "scene", "subjects", "ascendant_frame", "blackglass_lattice", "silverfall_halo", "transitions", "composition", "surface_and_palette", "text", "avoid". Omit unused fields. No metadata, IDs, weights, or comments. Return only the finished prompt.

flatten the bridge completely so it's running just above the surface of the water.

Create an ultra-photorealistic cinematic fashion photograph of an elegant woman riding a powerful {argument name="horse color" default="jet-black"} horse along a {argument name="setting" default="pristine tropical beach"} during a bright, windy afternoon.\n\nSUBJECT:\nA striking adult woman with long, naturally wavy dark hair flowing dramatically in the ocean breeze. She has refined natural facial features, realistic skin texture, subtle pores, delicate facial asymmetry, and a calm, confident expression. She looks slightly toward the camera while maintaining a believable riding posture.\n\nShe is wearing a luxurious flowing {argument name="dress color" default="crimson-red"} off-shoulder dress made from lightweight semi-transparent chiffon and silk. The dress has realistic folds, layered fabric, natural stitching, subtle fabric texture, and a long flowing train extending dramatically behind her. The wind catches different sections of the dress independently, creating complex natural movement rather than a perfectly uniform wave.\n\nHer posture must look like that of a real experienced rider: balanced torso, naturally positioned legs, relaxed but controlled hands holding the reins, realistic contact between her body and the horse.\n\nHORSE:\nA magnificent muscular black horse with a glossy but completely natural coat. Highly detailed facial anatomy, realistic eyes, nostrils, ears, mane, muscles, veins, and individual strands of hair.\n\nThe horse is moving at a fast but believable gallop along the shoreline. Its front legs and rear legs must have anatomically correct positioning and realistic joint movement. Hooves interact naturally with the wet sand, producing small splashes and scattered grains of sand.\n\nThe horse wears an elegant but practical dark leather bridle and saddle with realistic stitching, buckles, leather texture, subtle wear, and believable physical attachment.\n\nENVIRONMENT:\nA breathtaking tropical beach stretching into the distance.\n\nOn the left side, crystal-clear turquoise-blue ocean water approaches the shoreline with small white waves and realistic foam.\n\nBehind the rider are tall tropical palm trees bending slightly in the ocean breeze, dense green vegetation, white sand, and a distant coastline.\n\nThe sky is enormous and dramatic, filled with large naturally shaped cumulus clouds against a rich blue tropical sky.\n\nThe beach should not look artificial or perfectly clean. Include tiny footprints, hoof marks, irregular wet patches, small shells, scattered natural debris, subtle sand texture, and realistic variations in color.\n\nMOVEMENT:\nCapture the exact moment when the horse is galloping beside the water.\n\nThe woman's hair should be blown backward and sideways by the wind, with hundreds of individual strands behaving naturally.\n\nThe red dress should trail behind her in multiple layers, with different sections of fabric

{argument name="subject" default="Golden Gate Bridge"} as if it were a {argument name="dimensions" default="64 x 32"} LED screen and have only one color per pixel

painting in the style of {argument name="artist" default="Klimt"} of a {argument name="subject" default="woman wearing a large hat"} in a {argument name="setting" default="summer garden"}

A delicate, expressive watercolor painting on {argument name="paper texture" default="textured white cold-press paper"} capturing the close-up profile and facial features of a person in emotional turmoil. The artwork features a striking color palette of {argument name="eye colors" default="deep teal, indigo, and violet"} around the expressive eyes, transitioning down the nose into warm shades of peach and yellow, and finished with vibrant, glossy crimson lips. A thin, prominent tear streak drips down from the lower lid in a fluid indigo wash, blending minimalist negative space with moody, bleeding pigments to evoke a profound sense of sorrow and emotional vulnerability.

{ "visual_details": { "subject": "Woman resembling Daenerys Targaryen, detailed portrait", "hair": "Platinum blonde, intricate braided hairstyle on top, loose wavy tendrils framing the face, sharp and clear texture", "expression": "Neutral, focused expression looking slightly off-camera", "attire": "Pale grey pleated gown with deep plunging neckline, gold filigree metal waist belt, matching gold filigree collar. Fabric texture and metal details are highly defined.", "pose": "Leaning forward on a dark wood table surface, arms extended downward. Sharp focus extends across her hands and the table texture.", "background": "Dark interior setting with visible, sharp architectural details, including dark wood paneling, a stone wall texture, and defined window frames. No depth of field blur.", "lighting": "Warm, natural light illuminating the scene, with distinct golden backlighting originating from the table surface and background elements, remaining sharp and defined rather than soft." }, "raw_photo_technical_details": { "format": "Unprocessed CR3 RAW file data", "resolution": "High-resolution 4K UHD (3840x2160)", "camera_settings": { "shot_on": "Canon EOS R5", "lens": "RF 50mm f/1.8 STM", "aperture": "f/11 (Deep depth of field, entire scene in focus)", "shutter_speed": "1/160 sec", "iso": "640 (Natural digital grain visible)", "white_balance": "Daylight" }, "texture": "Realistic skin texture, visible fabric weave, defined metal details, natural digital noise/grain throughout the image", "focus": "Pan-focal, sharp detail from foreground (subject) to background architectural elements." }, "modified_prompt": "A sharp, high-resolution RAW photograph (4K UHD) of a woman resembling Daenerys Targaryen, detailed with intricate platinum blonde braids and wavy tendrils. She wears a pale grey pleated gown with a plunging neckline, a detailed gold filigree belt, and collar. She is leaning forward on a dark wood table with her arms extended. The scene is illuminated by warm, natural light with defined golden highlights. The entire image exhibits deep focus (pan-focal), with sharp, clear detail extending to the dark wood and stone architectural elements in the background, which have no blur. Natural digital grain, realistic skin texture, and sharp fabric details are visible, characteristic of an unprocessed RAW photo shot at f/11 aperture." }

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.

A captivating oil painting portrait of a woman with {argument name="hair style" default="long, dark, wavy hair"} and expressive {argument name="eye color" default="green-hazel"} eyes, wearing a {argument name="clothing" default="textured light-colored shirt"}. The art style features thick, visible impasto brushstrokes and heavy palette knife textures, creating a dimensional, tactile feel. The background is a dynamic mix of deep blues, ochres, and golden-browns with expressive, abstract strokes. The lighting highlights the warm skin tones, rosy cheeks, and soft pink lips, conveying a moody yet elegant atmosphere.

A {argument name="setting" default="quiet library"} and a {argument name="style" default="bright red traditional look"}. A love for books & style.

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

A black and white line drawing of a {argument name="subject" default="squirrel"} is depicted in profile, facing left. The {argument name="subject" default="squirrel"} is decorated with various patterns and designs, resembling a {argument name="art style" default="zentangle or adult coloring page"}. Its body is filled with floral motifs, scales, swirls, and geometric shapes. Its tail is large and curled, also adorned with patterns. The background is white, emphasizing the detailed linework of the {argument name="subject" default="squirrel"}.

image of a {argument name="subject" default="bowl of algae-flavored candies"} at {argument name="location" default="Grandma's house"}

{argument name="subject" default="A jungle-overgrown temple courtyard"} in an artistic {argument name="style" default="stonepunk"} style.