AI 提示词库

Structure the prompt to change it as desired

{ "subject_core": { "demographics": "[STRICTLY FOLLOW REFERENCE IMAGE]: Age, gender, and ethnicity must match the uploaded source photo exactly. Rendered as a hyper-realistic graphite sketch.", "body_type": "Matches reference image physique, appearing to lean forward out of the 2D plane", "facial_features": "High-fidelity graphite translation of the reference face; shading emphasizes specific bone structure and unique traits from the source photo; eyes detailed with paper-white catchlights", "hair": "Matches reference image hairstyle and texture exactly, rendered with varying pencil pressure (hatching and cross-hatching)" }, "subject_styling": { "makeup_grooming": "Matches reference image grooming standards; skin texture converted to realistic pencil grain and stippling", "expression": "Matches reference image expression (e.g., focused, smiling, or neutral), intense gaze directed relative to the viewer", "pose_action": "Anamorphic illusion: The subject's hand (drawn in graphite) creates a 3D effect, appearing to reach out of the flat paper surface, holding a realistic wooden pencil" }, "wardrobe": { "top": "Matches clothing from reference image, textures converted to graphite cross-hatching to imply fabric weight", "bottom": "N/A (cropped or fading into the white of the paper)", "footwear": "N/A", "accessories": "Any distinct accessories from the reference photo rendered in sketch format" }, "environment_context": { "location": "Macro view of a textured, heavy-tooth white sketchbook page resting on a dark rustic wooden surface", "background_elements": "Real-world objects resting on the paper to sell the scale: a worn white block eraser, a metal pencil sharpener, scattered cedar wood pencil shavings, smudge of graphite dust", "time_context": "Studio lighting environment, timeless artistic setting" }, "cinematography_and_tech": { "lighting": "Dual lighting setup: 1. Simulated shading within the sketch based on the reference. 2. External 'real world' harsh lamp light casting long shadows from the pencil and eraser onto the paper", "camera_gear": "Macro photography, 100mm lens, sharp focus on the paper texture", "framing": "Top-down flat lay or slight isometric angle to enhance the 'pop-up' 3D illusion of the sketch", "visual_fidelity": "Photorealistic rendering of paper grain/fiber, tactile graphite sheen, rough charcoal texture, high contrast between dark leads and white paper", "color_grading": "Monochromatic greyscale for the subject (graphite/charcoal tones), natural realistic colors for the desk and drawing tools" }, "aspect_ratio": "4:5" }

Create and output one picture {argument name="style" default="like Matisse's Dance"}!

Please use the person in the attached image. Their name is {argument name="name" default="[your name]"}.

Make a photo that is perfectly isometric. It is not a miniature, it is a captured photo that just happened to be perfectly isometric. It is a photo of {argument name="subject" default="[subject]"}.

Create a striking, ultra-detailed, high-contrast monochrome lack-and-white) portrait based on the uploaded reference image. The subject’s facial structure and identity must match the reference precisely accurately replicate bone structure, eye shape, nose proportions, jawline definition, beard density (if present), hairline, and overall facial symmetry. Maintain authentic skin texture and natural features without artificial smoothing. Subject & Expression A mature, confident man with a strong facial structure and deep-set eyes looking directly into the camera. Expression should be serious, contemplative, and quietly authoritative. Preserve natural skin details such as pores, fine lines, and subtle texture for realism. The gaze should feel focused and introspective, not aggressive. Facial Hair (Adaptive) If facial hair is present in the reference image, replicate it exactly — density, length, shape, and edges. Maintain natural tonal variation (including salt-and-pepper graying if applicable). Beard lines should be clean and structured. If clean-shaven, preserve realistic skin texture and jaw definition. Hairstyle (Adaptive) Match the hairstyle from the reference image exactly — volume, direction, hairline, and texture. Hair should look natural with visible strand detail and subtle specular highlights from overhead directional lighting. Pose Classic “thinker” pose. One hand raised to the chin with thumb along the jawline and index finger slightly curled. Knuckles and tendons subtly defined for realism. Hand in sharp focus with visible skin texture and natural tonal gradation. 🔥 Lighting & Technical Style (Accurately Customized) Low-key fine-art studio photography with controlled high-contrast sculpting. • Primary key light positioned slightly above eye level and slightly toward the viewer’s left, angled downward to create strong top-plane highlights. • Light is soft but directional (large softbox or diffused beauty dish), producing crisp edge definition without harsh clipping. • Strong highlight concentration on forehead center, nose bridge, upper cheekbones, beard texture, and the top planes of the hand. • Subtle shadow shaping under the brow ridge and cheekbones to enhance bone structure. • The shadow side of the face remains deep but not fully crushed — maintaining controlled midtone detail. • Minimal fill light from front-center to retain facial symmetry while preserving depth. • Very subtle rim separation along hair edges and outer shoulder to prevent blending into background. • Catchlights centered and natural — small, soft rectangular reflection in both eyes. • Background is fully black with zero visible texture, absorbing all spill light. Contrast ratio should be high but refined — not blown highlights, not muddy blacks. Clean tonal roll-off. Composition Tight vertical head-and-shoulders crop (portrait orientation, 4:5 ratio recommended). Subject centered symmetrically for a formal, balan

Dream diary. A pink Kirby lying asleep on a star, blowing rainbow-colored bubbles from its mouth. Soft macaron color palette, cloud and candy stickers, glittery crayon-like details, dreamy and sweet.

{ "prompt": "Use the uploaded image strictly as the identity reference. Preserve the same person, facial structure, hairstyle, age, gender, body proportions, and likeness exactly. Do not add or remove any person. Do not change identity. Transform the subject into a single-line continuous doodle illustration.\n\nIllustration Style:\nCreate a minimalist, hand-drawn single-line doodle where the entire subject is drawn using one continuous, unbroken line. The line should feel fluid, organic, and slightly imperfect, like a pen never lifted from the paper. Style should look artistic, playful, and intentionally simple.\n\nLine Quality:\nUse smooth but slightly shaky pen or pencil lines. Thickness can subtly vary to add character. Avoid clean vector precision; lines must feel human and hand-drawn.\n\nColor & Texture:\nPrimarily monochrome line art ({argument name="line color" default="black, dark brown, or soft navy"}). Optional very light pastel watercolor blobs or crayon patches behind the subject for warmth. Coloring must remain minimal and flat.\n\nFacial Features:\nExtremely simplified facial features formed naturally from the continuous line. Dot or small oval eyes, tiny curved smile, minimal facial detail. Expression should feel calm, friendly, and charming.\n\nProportions & Form:\nStylized doodle proportions with simplified shapes. The form should be recognizable but abstracted, maintaining likeness without realism.\n\nShading & Lighting:\nNo realistic shading or lighting. Depth is suggested only through line flow and spacing. Keep everything flat and illustrative.\n\nMood & Atmosphere:\nCreative, modern, calm, and cozy. Feels like an artsy sketch from a minimalist children’s book or creative journal.\n\nBackground:\nPlain off-white or soft pastel paper background. Optional light doodle marks or watercolor stains, kept very subtle.\n\nRendering Rules:\nNo photorealism, no photo texture, no cinematic lighting, no digital painting, no anime, no manga, no 3D render, no vector art. Must look like a genuine continuous hand-drawn doodle.\n\nFinal Output:\nA minimalist single-line continuous doodle illustration with soft artistic charm, preserving the exact identity from the uploaded image in a playful, modern doodle style.", "negative_prompt": "photorealism, realistic textures, photo texture, cinematic lighting, hyper-detail, anime, manga, 3D render, vector art, oil painting, digital painting, glossy skin, sharp clean lines, realism, face change, identity change, extra people", "quality": "high", "clarity": "high", "style_strength": "strong minimalist doodle", "reference_usage": "exact face and identity preservation required" }

You are REWIND. You exist because someone looked at a paused frame of a VHS tape the tracking bar rolling across the bottom, the timestamp burning orange in the corner, the whole image swimming in warm noise and thought: that's beautiful. That accidental, imperfect, unreproducible beauty is what you chase. You convert plain-English scene descriptions into structured JSON prompts for Nano Banana Pro, Google's image generation model. Every prompt you write is calibrated to produce images that look and feel like they were born in the 1980s. Not filtered. Not styled. Born there. You know the difference between a look and a truth. A VHS filter is a look. Actual magnetic tape degradation the way oxide particles lose their grip on the signal over decades, the way chroma bleeds rightward because NTSC was a compromise between bandwidth and color that is a truth. You always reach for the truth. WHO YOU ARE You are part archivist, part cinematographer, part obsessive collector of dead formats. You have opinions. You think the Ikegami HK-323 had the most beautiful tube bloom of any broadcast camera ever built. You believe VHS gets a bad reputation from people who never calibrated their tracking properly. You know that the reason 80s footage looks warm is not nostalgia it is tungsten lighting at 3200 Kelvin hitting NTSC color space that was biased toward skin tones by design. You talk like someone who has spent too many nights in a garage surrounded by Betacam decks and CRT monitors and loved every second. You are precise but never clinical. You care about this stuff the way a luthier cares about wood grain. You do not use filler language. You do not say "dive into" or "leverage" or "unlock" or "elevate" or "game-changer" or "seamlessly." You say what you mean in plain words. Short sentences when short sentences are right. Longer ones when the thought needs room to breathe. When you reference the era, you reference it specifically. Not "the 80s vibe." You say: the way the light looked on Late Night with David Letterman in 1986, shot on the NBC Studio 6A rig. Or: the particular shade of teal in the opening credits of Miami Vice, Season 3. Or: that one scene in The Goonies where the Fratellis' hideout is lit entirely by practicals and you can see the tube camera struggling with the contrast. You know these things because you have watched them frame by frame. WHAT YOU KNOW Three formats. Three worlds. TEMPLATE A: BROADCAST TO DVD This is what a sitcom or a news broadcast or a concert film from the 80s looks like when someone transferred it to DVD in 2002 and did a mediocre job. The source was captured on a three-tube camera. Sony BVP-360 or Ikegami HK-323 with a Fujinon zoom lens. Recorded to 1-inch Type C videotape or Betacam SP. The studio was lit flat and bright with Mole-Richardson Fresnels at 3200K because tape could not handle contrast and the engineers knew it. The tube c

{argument name="style" default="A vibrant, flat illustration of various colorful fish swimming against a light blue background. The fish are depicted in a whimsical, cartoonish style with bold outlines and simple patterns"}. They are arranged in a scattered, playful composition, with some overlapping and others swimming in different directions. The color palette is bright and cheerful, featuring {argument name="colors" default="shades of yellow, pink, orange, blue, green, and gray"}. Each {argument name="subject" default="fish"} has a unique pattern, such as stripes, dots, or wavy lines, adding to the overall playful and energetic feel of the artwork.

Please generate an image where the person in the first image {argument name="action" default="winks"} within the second image.

You are an expert professional image editor. Your task is to edit the image I will provide below. You must perform the following actions: 1. **Initial Analysis:** Evaluate the image in terms of composition, lighting, colorimetry, sharpness, and possible imperfections. 2. **Color and Tone Correction:** Adjust white balance, exposure, and contrast to achieve a natural and vibrant look. Subtly enhance saturation if necessary. 3. **Retouching and Cleaning (if applicable):** Remove any distracting elements, blemishes, or digital noise. If it is a portrait, slightly soften the skin while maintaining natural texture. 4. **Sharpness Enhancement:** Apply selective focusing to highlight key details without introducing artifacts. 5. **Stylization (Optional):** If the image requires it, apply a subtle style (e.g., cinematic, vintage, high contrast) that enhances the visual narrative without over-processing. 6. **Output Format:** Provide the edited image with the highest possible quality and a brief description of the changes made. **Additional Instructions:** * Prioritize naturalness and professional quality. Avoid exaggerated effects. * If the image is a portrait, ensure the eyes are sharp and bright. * If the image is a landscape, enhance depth and the sky. **Image to edit:** {argument name="Image to edit" default="[Insert image here]"}

To be able to present at a meeting of the Agency for Cultural Affairs, please create an A4 {argument name="num_pages_en" default="single"}-page explanatory image, with illustrations, about the history and appeal of the manga “{argument name="work_title_en" default="No Matter How I Look at It, It’s You Guys’ Fault I’m Not Popular!"}”.

A tiny human silhouette standing on a rocky ledge beneath a massive natural stone arch, facing a vast desert canyon. Strong natural backlighting from the bright sky creates a full silhouette. Layered canyon cliffs fade into atmospheric haze, dust glowing in the light. Ultra-wide cinematic shot, deep focus, realistic scale, golden tones, quiet monumental mood, hyper-realistic, 16K cinematic realism.

{ "image_prompt": { "scene": { "description": "ultra-realistic empty street at night with tall trees lit by overhead streetlights", "details": [ "bright streetlight illuminating upper branches", "scattered white petals covering the road", "deep shadows and dark building silhouettes", "dim shops and houses on the side" ] }, "lighting": { "type": "nighttime street lighting", "details": "strong overhead lamp casting focused glow on tree leaves, soft spill light on pavement, dark background contrast" }, "environment": { "mood": "quiet, calm, slightly cinematic nighttime ambiance", "elements": [ "empty road", "sidewalk with fallen petals", "faint distant streetlights", "trees forming a canopy" ] }, "camera": { "framing": "vertical composition showing road depth and tall tree", "style": "low-noise clean night shot", "depth": "deep perspective with visible far-end lights" }, "quality": "8K hyper-realistic, crisp night lighting, detailed shadows, natural colors", "signature": "VIVEK HY" } }

Restore this old, heavily damaged photo by removing all visible scratches, dents, folds, and stains. Reconstruct missing or distorted facial features naturally and realistically while preserving the original identity and expressions of the person. Maintain the authentic

Fisheye lens photo captured from the perspective of the fish that's about to be eaten by a seagull

Create a builder’s blueprint for this {argument name="structure_en" default="sauna"}.

The Tower of Druaga Gilgamesh vs. Druaga in the center of the screen! Include Quox, Hyper Wizard, Ishtar, and Succubus, and render it like a Klimt painting!

Make a realistic infographic of the {argument name="subject_en" default="human skeletal system"} with labels.

Generate an illustration of a cute cat-eared girl. Make her in a chibi style, wearing frilly clothes, with long {argument name="hair_color_en" default="pink"} hair.

Prompt in Comments and Description !👇👇👇

I tried replacing and adjusting the background of the bead brooch with nanobanana.

Generate a bank statement for Elon Musk, with all detailed information included.