A highly specific, constraint-heavy prompt for Nano Banana Pro to generate a photorealistic vertical image of a woman with an extremely exaggerated 'slim-thick' hourglass figure (tiny waist, massive glutes) pumping gas at a brightly lit station at night. The prompt strictly dictates physique, pose (looking over the shoulder), wardrobe (light yellow crop top, grey leggings), scene elements (pink Mini Cooper), and lighting.
{
“subject”: {
“description”: “A vertical photograph of a strikingly beautiful young woman with an exaggerated curvy build, pumping gas into a car at a gas station at night.”,
“body”: {
“physique”: “She possesses an incredibly exaggerated ‘slim-thick’ hourglass figure. Her waist is extremely tiny and snatched, transitioning dramatically into massively prominent, round, and wide glutes and thick, shapely thighs. The contrast between her very small waist and exaggerated lower body is the defining feature.”,
“pose”: “Standing at the gas pump, holding the nozzle into the car. She is twisted slightly, looking back over her right shoulder directly at the viewer, similar to the previous pose. Her stance emphasizes the extreme curve of her lower back and glutes.”,
“features”: “Dark hair pulled up in a casual messy bun with a gold star-shaped hair clip. Her face is strikingly beautiful and gorgeous but with realistic skin texture, natural pores, and genuine features, not looking artificial or like porcelain. Her arms are bare and have NO tattoos.”
}
},
“wardrobe”: {
“outfit”: “She is wearing a {argument name="top color" default="light yellow"} cropped t-shirt that hugs her upper body. On her lower body, she wears fitted {argument name="legging color" default="grey"} athletic leggings that stretch tightly over her exaggerated curves.”
},
“pose_action”: “Filling up her car with gas at a station at night, looking back over her shoulder.”,
“scene”: {
“environment”: “A brightly lit gas station at night.”,
“elements”: “She is standing next to a bright {argument name="car color" default="pink"} Mini Cooper car, inserting the pump nozzle. The background shows the gas pumps, concrete ground, the overhead canopy structure with industrial lights, and brightly lit convenience store signage in the distance against the dark night sky.”,
“composition”: “Vertical 9:16 aspect ratio. A medium-full shot capturing the subject from the knees up while pumping gas.”
},
“lighting”: {
“setup”: “Nighttime mixed lighting: bright overhead fluorescent canopy lights casting strong light and distinct shadows, mixed with the glow of neon signs from the station.”,
“details”: “The artificial lighting highlights the realistic texture of her skin, the fabric of the light yellow top and grey leggings, and the glossy paint of the pink car.”
},
“camera”: {
“technical”: “High-resolution photograph. Sharp focus on the main subject. Realistic, candid style captures during the night.”,
“aspect_ratio": “9:16”,
“constraints”: [
“CRITICAL: The subject must have the specific EXAGGERATED hourglass physique with a tiny waist and massive glutes.”,
“CRITICAL: The face must be incredibly beautiful but REALISTIC, not doll-like.”,
“CRITICAL: There must be NO TATTOOS on her arms.”,
“CRITICAL: Outfit colors must be LIGHT YELLOW top and GREY leggings.”,
“CRITICAL: Scene must be a GAS STATION AT NIGHT with a PINK MINI COOPER.”,
“The final image must be a photorealistic ve”
]
}
}
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.
Cinematic portrait restoration. Strictly preserve original pose, expression, and composition. Add warm golden-hour side lighting casting a defined, dramatic shadow on the wall behind. Upscale to Ultra-HD: sharpen details, enhance realistic skin texture, and reduce noise. Mood: Mysterious, high-contrast, warm highlights, deep shadows, photorealistic.
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!
Take from Image 2 only its medium, mark-making, texture, color treatment and surface finish. Take from Image 1 everything else
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.
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.
部分提示词收录自 X 平台创作者，版权归原作者所有。