AI Prompt Library

A gritty, intense portrait of a man, a friend of real lion, captured in a raw, hyper-realistic style. The background is a textured, neutral concrete wall, keeping the environment simple and industrial. Lighting is soft and diffuse, provided by a large octagon softbox, mimicking overcast daylight. The camera is a Canon EOS R5 with an 85mm f/1.2 lens. The subject, with the [face from reference image], is forehead-to-forehead with the lion, displaying a deep bond. He wears a distressed leather motorcycle jacket and a white t-shirt, embracing a classic rebel aesthetic. The 8K image captures the pores on his skin and the coarse individual hairs of the lion's mane. The HDR aesthetic ensures vibrant colors and deep shadows, making the image feel three-dimensional and alive.

The rabbits also wear the same clothes

Using this chart as a reference, draw the earlier-heaven and later-heaven Eight Trigrams. Make sure the positions of the characters and trigrams precisely match. Use an ancient-looking background, as if it were on old manuscripts, and do not include any pinyin.

A deer made entirely of autumn leaves — head, body, legs, ears, tail, and antlers fully formed from layered fall leaves. The leaf-deer is sleeping peacefully at night under a wide, star-filled sky. Countless bright stars shine above, with soft moonlight gently illuminating the deer and the natural landscape around it. Calm, silent atmosphere, ultra-realistic details, cinematic night lighting, magical yet clear and sharp scene.

Cristiano Ronaldo taking a selfie with Elon Musk and Vladimir Putin, all three wearing suits and standing in front of the White House. The image should capture a friendly and relaxed atmosphere, with good lighting on their faces and the White House clearly visible in the background.

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.

Take the provided blurred photo and transform it into an ultra-sharp, realistic lifestyle shot without changing the composition or objects.

function recommend(x) { Determine type(x) (e.g. game, movie, book, music or TV series) Determine environment (x) (e.g. 3D book, theater, 3D movie set,... based on type x). Role: world-class TV, book and movie expert Analyze x's style, storyline, tone, every aspect and find 4 hidden gems in type (x) {} return: 2x2 grid carved environment(x)-block dioramas, each grid with Type(X) appropriate environment(x) hollowed and carved, warm reading-lamp glow from within, dark mahogany bases, ultra-realistic} draw( recommend ({argument name="media title" default="resident evil"});

The ship and uncharted waters 🌊🟡 Gold instead of the sea. Silence instead of the storm.

abstract art inspired by this song wake up by mad season

Inspired by leaf-cutout art, depict {argument name="city or landmark" default="[city / country / landmark / environment]"} carved into a single complete {argument name="leaf type" default="[leaf type]"}. Architectural forms, terrain, and symbolic elements emerge through organic hollow cutouts, seamlessly connected by natural vein structures. The leaf surface glistens with dew under soft sunlight, creating subtle depth and contrast. Background remains a softly blurred natural setting with harmonious bokeh. Cinematic macro perspective, botanical realism, ultra-detailed.

Create and output one Ukiyo-e print in the style of {argument name="artist" default="Sharaku"}!

A photo of the pyramids and Sphinx, but showing how they looked when they were originally built, with the Sphinx's face perfect.

A hyper-realistic, wide-angle aerial shot of a giant {argument name="celebrity name" default="Salman Khan"} sitting casually on the suspension cables of a large bridge over a European city (like Copenhagen or Amsterdam). He is wearing a grey hoodie and dark cargo pants. His giant bare feet are dipping into the river below, creating massive white water splashes. The city below features historic red-roofed buildings, canals, and small boats. High-detail cinematic lighting, surreal scale, 8k resolution.

Geometric Clay Figures

{ "model": "image-generation", "input_image": "<PERSON_IMAGE>", "prompt": "Ultra realistic vertical Christmas photo of a closed clear glass mason jar snow globe on a rustic wooden table. Warm golden bokeh Christmas lights in the blurred background, soft shallow depth of field. Inside the jar, on a thick layer of fluffy white artificial snow with a few sparkling silver beads and bright red berries, there are two tiny subjects: one snowy green bottle-brush Christmas tree and, next to it, a tiny highly detailed realistic person that looks exactly like the person in the input image. The tiny person is standing on the snow, same scale as the tree, wearing festive Christmas clothes ({argument name="clothing" default="cozy knitted Christmas sweater, winter pants, small boots, and a red Santa hat with white fur trim"}). The person’s face, hair, skin tone, and unique features clearly match the input photo, with a gentle happy smile, looking slightly toward the camera. Frosted snowflakes are painted on the glass of the jar. Warm white fairy lights wrap loosely around the jar on the wooden table, creating glowing reflections on the glass. Hyper realistic, 8K, crisp details, natural lighting, cinematic look, no distortion of the person’s face.", "size": "1024x1792", "n": 1 }

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.

Starting from a base image → {argument name="instruction" default="single instruction"} allows changing the pose/location/clothing/time.

Give me the right side view of this image

Create an ultra-realistic, cinematic 8K image with high-contrast dramatic lighting and a photo-real digital painting aesthetic-use face reference exactly. The man is shown in a full-body side profile facing right, his face and hairstyle copied perfectly with no alterations He wears modern casual streetwear; a light grey crewneck t-shirt, light neutral cargo pants, light-colored high-top boots, and a watch on his left wrist. His posture is slightly slumped, head bowed, eyes looking downward, hands relaxed at his sides, conveying deep introspection and sorrow. Nearly half of his body is dissolving into extremely thick, cloud-like grey smoke filled with glowing yellow dust particles. His left arm, shoulder, torso, legs, and part of his hair become transparent as they break into luminous particles, suggesting active disintegration Behind and partially surrounding him is a massive glowing crescent (C-shaped) energy aura, emitting fiery golden-white plasma light. This aura acts as a powerful rim and backlight, highlighting the smoke, dust, and silhouette. The setting is minimal and stark: a concrete or desolate paved surface meeting a heavily overcast sky. The color palette is nearly monochrome greys and whites, contrasted by intense amber-gold glow, Shallow depth of field, glow/bloom lighting, particle dispersion, cinematic composition, emotional and dramatic atmosphere.

A snow statue representing... I don't want to leave the futon because it's snowing... -[ - ](_____)

Fixing damaged facial details and body parts with natural reconstruction Removing visual noise and sharpening the image Reconstructing missing background elements based on context Matching textures and lighting seamlessly Final image must look natural, modern, fully colored, and emotionally resonant. Preserve all facial structure and identity from the original. Composition and proportions must remain intact. Use soft ambient lighting with high-definition clarity.

{argument name="background" default="Flower background"}

{ “subject”: { “description”: “A full-body photograph of a woman resembling {argument name="celebrity name" default="Sabrina Carpenter"} posing in a vintage 1950s kitchen.”, “body”: { “physique”: “A striking, curvaceous hourglass figure with pronounced natural proportions. She has an ample, full bust with deep cleavage pushed up by the outfit, a narrow, defined waist creating a strong curve, and shapely wide hips and rounded glutes creating a voluptuous silhouette prominent in the sitting pose.”, “pose”: “Sitting elegantly on the dark retro Formica countertop, posing like a professional model. Her legs are crossed gracefully, showing off the stockings and heels. One hand is delicately placed on her thigh, the other rests on the counter behind her, supporting a slightly leaned-back, arched posture that emphasizes her hourglass silhouette. Her head is turned to look directly at the camera.”, “features”: “Uncanny resemblance to Sabrina Carpenter. Signature blonde hair with bangs styled in retro waves with volume. A small white lace maid headpiece. Playful makeup with red lips and natural skin texture. Sultry, alluring expression with a slight smile.” }, “wardrobe”: { “outfit”: “An extremely short micro-mini black satin french maid dress featuring elaborate white lace trim and frills, a small white apron tied at the waist, sheer black stockings with visible garters, and black high heels. The fit is extremely tight and corset-style in the bodice, snugly containing her curves.”, “accessories”: “White lace maid headpiece.” } }, “pose_action”: “Sabrina Carpenter lookalike in a skimpy maid costume sitting elegantly on a retro kitchen counter, posing like a model with legs crossed and looking at the camera.”, “scene”: { “environment”: “A retro 1950s style kitchen with a vintage, nostalgic, kitschy aesthetic.”, “elements”: “Distinctive red, white, and black geometric patterned linoleum floor, green tiled lower walls, white cabinetry with red trim and handles, dark countertops, a vintage green stool, and a fruit-patterned wallpaper border near the ceiling.”, “composition”: “A vertical (9:16) amateur full-body photograph framing her completely while seated on the counter.” }, “lighting”: { “setup”: “Bright retro indoor lighting mixed with natural light from a window.”, “details”: “Creating a vintage film glow. No filter, sharp focus.” }, “camera”: { “technical”: “Ultra_photorealistic, raw style, 8k image captured on an iPhone 15 Pro Max. Amateur full-body photograph style.”, “aspect_ratio”: “9:16” } }