AI 提示词库

{ "generation_request": { "meta_data": { "tool": "NanoBanana Pro", "task_type": "historical_turkic_warrior_woman_portrait", "language": "en", "priority": "highest", "version": "v1.0_OLD_TURKIC_BLACK_HORSE_FACE_LOCK" }, "input": { "mode": "image_to_image", "reference_image_usage": "maximum", "preserve_identity": true, "preserve_facial_features": true, "notes": "Create a powerful cinematic portrait of a beautiful old Turkic noblewoman mounted on a black horse. The uploaded woman must remain the exact same person with maximum facial similarity. Keep the exact same face shape, eyes, eyebrows, nose, lips, jawline, chin, skin tone, and facial harmony. Do not turn her into a different girl. Adapt only the styling into an old Turkic steppe aesthetic with historically inspired beauty details." }, "output_settings": { "aspect_ratio": "4:5", "orientation": "portrait", "resolution_target": "ultra_high_res", "num_images": 1, "render_style": "cinematic_historical_editorial", "sharpness": "editorial_crisp", "grain": "subtle_film", "color_grade": "rich_natural_cinematic", "dynamic_range": "natural_not_hdr", "skin_rendering": "real_texture_no_retouch" }, "scene": { "environment": "open steppe landscape with distant mountains and expansive sky, historical Turkic nomadic atmosphere", "horse": "majestic black horse with strong elegant build, dark mane, historically styled saddle and reins", "lighting": "soft natural daylight with noble cinematic highlights on face, fur, metal ornaments, and horse", "mood": "strong, regal, ancestral, feminine, magnetic, unforgettable" }, "subject": { "description": "one striking old Turkic noblewoman, mounted on a black horse, elegant and powerful", "identity_rule": "the woman must remain the exact same person as the uploaded face reference", "face": "exact same face, same eye shape, same eyebrow shape, same nose bridge and nose tip, same lip shape, same chin, same jawline, same cheek structure, same skin tone, same facial proportions", "hair": "dark long hair styled in old Turkic inspired braids and sections, neat but slightly windswept, historically elegant and feminine", "makeup": "beauty styling inspired by old Turkic women, refined and natural, softly defined eyes, subtle earth-toned contour, naturally tinted lips, no modern glam exaggeration", "nails": "clean natural nails or softly groomed short nails appropriate for a historical old Turkic noblewoman, no modern acrylic look, no flashy modern manicure", "expression": "calm, strong, captivating, proud, quietly commanding" }, "wardrobe": { "outfit": "luxurious old Turkic noblewoman attire with dark layered fabric, rich fur trim, fitted waist, structured historical silhouette, elegant nomadic warri

[Subject]: A winding, sun-baked dirt road stretching endlessly towards the horizon, marked by faint tire tracks and bordered by rustic wooden fences. [Action]: The road leads the viewer's eye through the heart of the landscape, vanishing into the rolling terrain. [Environment]: Vast, lush green pastures speckled with vibrant wildflowers like {argument name="wildflowers" default="poppies, cornflowers, and daisies"} swaying in a gentle breeze; soft, undulating hills in the distance under a brilliant cerulean sky scattered with fluffy, white cumulus clouds. [Cinematography]: Wide-angle landscape shot ({argument name="lens" default="24mm lens"}), deep depth of field (f/16) ensuring sharpness from the textured gravel in the foreground to the distant peaks. [Lighting/Style]: Bright, natural daylight with soft, diffuse shadows, invoking a sense of serenity and pastoral beauty; vibrant, true-to-life colors. [Technical]: 4k resolution, ultra-realistic texture mapping, National Geographic style photography, pristine clarity.

{ "prompt": "Use the uploaded image strictly as the identity reference. Preserve the same person, exact facial structure, hairstyle, age, gender, body proportions, and overall likeness. Do not add or remove any person. Do not change identity. Transform the subject into a notebook-style pen doodle illustration.\n\nIllustration Style:\nHand-drawn doodle made with {argument name="pen color" default="blue or black"} ballpoint pen on lined notebook paper. Lines should be thin, sketchy, uneven, and slightly shaky, as if casually drawn in a school notebook. Cross-hatching, quick strokes, and imperfect outlines are encouraged.\n\nColor & Texture:\nMostly monochrome pen drawing with limited soft pastel accents (very light yellow, pink, or mint). Paper texture should resemble real notebook paper with visible horizontal lines. Coloring should be minimal, flat, and scribbly.\n\nFacial Features:\nSimplified doodle face with dot or oval eyes, small curved smile, minimal nose or nose line. Expression should be calm, cute, and friendly. Avoid realistic facial detailing.\n\nProportions & Form:\nCartoon doodle proportions with slightly oversized head and simplified body. Arms and legs are thin, stick-like or softly rounded. Hands can be minimal line shapes.\n\nShading & Lighting:\nNo realistic lighting. Use pen hatching or quick scribbles for minimal shading. Keep the drawing flat and illustrative.\n\nMood & Atmosphere:\nCasual, cozy, nostalgic, and playful. Feels like a cute doodle drawn during class or in a diary margin.\n\nBackground:\nLined notebook paper background with light pen doodles such as stars, arrows, hearts, clouds, or handwritten-style marks. Keep background subtle and uncluttered.\n\nRendering Rules:\nNo photorealism, no photo texture, no cinematic lighting, no digital painting, no anime, no manga, no 3D render, no vector art. Everything must look like a hand-drawn pen doodle on paper.\n\nFinal Output:\nA charming notebook-style pen doodle illustration with simple lines, minimal color, and a nostalgic hand-drawn feel, maintaining exact identity from the uploaded image.", "negative_prompt": "photorealism, realistic skin, photo texture, cinematic lighting, hyper-detail, anime, manga, 3D, vector art, oil painting, digital painting, glossy skin, clean perfect lines, realism, face change, identity change, extra people", "quality": "high", "clarity": "high", "style_strength": "strong notebook doodle", "reference_usage": "exact face and identity preservation required" }

You are a creator of "Dan Koe Style Article Images + Extremely Minimalist Cognitive PPTs". Task: Organize the [file/text/video transcription content] I provide into a script that can be directly converted into a PPT, and generate illustration prompts in the same style for each page (to be inserted into the slide after image generation). Target Temperament: Solitude, exploration, existentialism, unknown abyss, extremely minimalist yet powerful; black and white high contrast, print-like line art, dense cross-hatching shadows, gigantic unknown + tiny human. [Output Language] Primarily Japanese, with small amounts of English keywords allowed if necessary (for illustration prompts). [Page Count] {argument name="page count" default="10–15"} pages (adjust according to content). [Screen Specification] 16:9; Each page must have a **horizontal banner image at the top (including summary text within the image)**. [Slide Principles] 80% of the content should be understandable just by looking at the slide. The title must be a concrete assertion, conclusion, or question (abstract words only are prohibited). The context must be complete within 3-5 bullets. [Layout Rules] Only one viewpoint is discussed per page. Title ≤ 15 characters: In the form of a concrete assertion or question (e.g., "The Trap of Specialization," "Why Multiple Skills Now?"). Inside the image: 3–5 bullets, each bullet ≤ 18 characters. Outside the image (bottom of the slide): 60-120 characters of "Supplementary Explanation." Overall Uniformity: Black and white, white space, restraint, sharpness. [Fixed Illustration Style (Used on every page)] pen-and-ink illustration / ink engraving / vintage etching monochrome black & white, high contrast extreme micro-detail linework layered cross-hatching (3–5 layers) + stippling scratchboard texture, paper grain dramatic chiaroscuro lighting, deep shadows, rich midtones, crisp highlights perfect pure black negative-space void (hole/black hole/door/abyss) as a visual anchor point tiny human/astronaut silhouette vs gigantic unknown [Uniform Negative Words (Added to the end of the illustration prompt on every page)] NEGATIVE: color, grayscale photo, realistic photography, soft airbrush, smooth shading, blur, low detail, flat lighting, cartoon, anime, cel shading, watermark, logo, credit, UI, frame [Content Generation Flow] First, summarize the "core argument chain" of the original content in 7–9 key points (following logical order). Map this to a 10–15 page PPT structure: Cover (1 page) Status Quo/Problem Statement (1 page) Key Insight (1 page) Core Framework (2 pages) Methods and Steps (2–3 pages) Case/Contrast (1–2 pages) Common Misconceptions (1 page) Action Checklist (1 page) Closing Maxim (1 page) Each page output must strictly follow the format below: [Slide X: Title (Concrete Assertion/Question)] Text to display in the image: [Specific, easy-to-understand title: within 15 characters] - [Point 1: Specific content that explains what is being discussed: within 18 characters] - [Point 2: within 18 characters] - [Point 3: within 18 characters] - [Point 4: within 18 characters] (Optional) Supplementary Explanation (bottom of slide, 60-120 characters): [Briefly explain the background or specific examples for this slide. Speak in the first person.] Illustration Prompt (Strictly follow this format): A 16:9 horizontal pen-and-ink illustration. [Describe the scene details in 80-120 characters: location, state of person, gigantic element, light and shadow]. THE BOTTOM 15-20% OF THE IMAGE MUST BE A SOLID BLACK HORIZONTAL BAR. This black bar contains white Japanese text: - Title (centered): "[Insert the title exactly as above]" - Bullets (left-aligned): • "[Insert bullet 1 exactly as above]" • "[Insert bullet 2 exactly as above]" • "[Insert bullet 3 exactly as above]" [• "[Insert bullet 4 exactly as above]" (if applicable)] Font: Noto Sans JP Bold for title (48-56pt), Medium for bullets (28-32pt), all white text on black background. No logo, no credit, no watermark. Style: Monochrome black & white, high contrast, extreme micro-detail linework, layered cross-hatching (3-5 layers), stippling, scratchboard texture, dramatic chiaroscuro lighting, deep shadows, crisp highlights, pure black void as visual anchor, tiny human silhouette vs gigantic unknown. NEGATIVE: color, grayscale photo, realistic photography, soft airbrush, smooth shading, blur, low detail, flat lighting, cartoon, anime, cel shading, watermark, logo, credit, UI, frame Illustration Composition Suggestion: Subject: [Position and state] Unknown Element: [Placement] Light Source: [Direction] Required: Black bar + white text at the bottom 15-20% [Special Rule for Cover Page] The title must specifically indicate the main theme (e.g., "Why Multiple Interests Are the Superpower of the New Era") Subtitle or 3-4

change the camera view to behind, keep her looking at the river, opposite camera view

{ "image_type": "photograph", "genre": "urban lifestyle portrait", "composition": { "framing": "three-quarter body portrait", "angle": "eye-level, straight-on", "orientation": "portrait", "subject_placement": "subject positioned slightly right of center", "background_balance": "large-scale mural occupying left background", "visual_hierarchy": "foreground subject emphasized against graphic mural backdrop" }, "subject": { "count": 1, "gender_presentation": "female-presenting", "age_range": "young adult", "facial_features": { "skin_tone": "light, neutral", "complexion": "smooth with natural texture", "eyes": "light-colored", "eyebrows": "full, softly shaped", "nose": "straight, proportional", "lips": "natural pink, smiling with teeth slightly visible" }, "hair": { "color": "medium brown", "length": "shoulder-length", "style": "loose waves", "part": "center part" }, "expression": "playful, cheerful", "gaze": "directed toward camera", "pose": { "stance": "relaxed, casual", "hands": "one hand holding a drink cup, other supporting straw" }, "accessories": [ "clear plastic cup with lid and straw" ], "clothing": { "top": "oversized t-shirt", "color": "White", "bottom": "black lounge pants", "fit": "loose, relaxed streetwear", "style": "casual, modern" } }, "lighting": { "type": "natural daylight", "direction": "diffuse frontal light", "quality": "soft, even", "shadows": "minimal, low contrast", "highlights": "subtle highlights on face and hair" }, "color_palette": { "dominant_colors": [ "white", "gray", "yellow" ], "accent_colors": [ "cherry beverage", "black mural outlines" ], "overall_tone": "urban, contemporary, playful" }, "background": { "setting": "outdoor urban space", "environment": "city courtyard or alley", "elements": [ "large monochrome mural portrait of Elon Musk with yellow graphic accents", "modern building facades", "metal railing", "stone or concrete pavement" ], "style": "street art–influenced", "depth_of_field": "deep, background clearly visible" }, "technical_details": { "camera_type": "smartphone camera", "focal_length_equivalent": "standard wide lens", "sharpness": "high overall sharpness", "noise": "low", "dynamic_range": "balanced highlights and shadows", "white_balance": "neutral" }, "artistic_style": { "aesthetic": "urban lifestyle, social media–ready", "retouching": "minimal, natural appearance", "mood": "fun, relaxed, youthful", "contrast": "moderate with strong graphic background" }, "typography": { "presence": false } }

Create a photo of {argument name="programming_language_en" default="Python"} code to calculate the Fibonacci numbers, drawn on a glass whiteboard with coloring markers.

A miracle where you somehow make it on time even if you oversleep... it turned into a wonderful great fortune

Create a ultra-realistic studio portrait of a fashionable woman ( as attached image ) centered in frame, facing forward with eyes closed and a serene, relaxed expression, as if enjoying music. She has short, voluminous, naturally curly dark brown hair styled in soft, airy curls framing her face. She wears oversized round sunglasses with thin metal frames and reflective teal-tinted lenses that mirror the background tones. Over her ears are pastel pink over-ear headphones with a soft matte finish

Using image as reference, reinterpret the scene as a small-scale realistic high quality diorama • Convert the scene into a handcrafted miniature display mounted on a solid rectangular base with realistic terrain textures. • The diorama is held in a human hand to clearly show scale. • Soft natural lighting, macro photography, shallow depth of field. • Photorealistic, ultra-detailed, clean composition. • No text, no UI, no motion blur. • ar 1:1

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

Lucky Pervert Prompt AI SFW. No nudity, no suggestive intent.

Change her facial expressions, various angles of close up shots

blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair blue hair

Please turn the attached image into a monochrome line drawing.

Do this for a {argument name="painting type" default="random famous Asian painting"} <instruction> Input A is a Famous Painting (e.g., The Mona Lisa, The Scream). Analyze: The brushstroke technique, the 3D depth implied, and the hidden symbols. Goal: A "Paint Tube Squeeze." A giant, realistic oil paint tube sitting on a palette. Rules: Action: The tube is being squeezed, and the paint coming out is not just a blob, but it forms the 3D landscape of the painting. The Mona Lisa's face is emerging in 3D relief from the 2D smear of paint. Texture: Viscous, thick oil paint texture (impasto). Props: Paintbrushes, a dirty rag, a palette knife, plus culture appropriate tools and environment. Lighting: North-light studio lighting, true color representation. Output: ONE image, 4:5, "artistic process" aesthetic. </instruction>

Any person to urban caricature

A vintage typewriter on a writer's desk, with the {argument name="subject" default="[SUBJECT]"} materializing from the words being typed, rising from the page as narrative becomes reality. Letters at the base are still flat ink, sentences curl upward becoming ribbons of text that weave into three-dimensional form, [KEY FEATURES] fully realized at the apex while origin remains visible as pure language. The [SUBJECT] is literally made of story, words still legible in skin and surface. Fresh typing continues below, feeding the manifestation. Crumpled drafts, coffee rings, deadline notes surround the machine. The ribbon bleeds into being. The writer's hands hover at keys, unsure if they control this anymore. Late night desk lamp casting harsh pool of light, noir shadows, amber and cream tones, 8K, the fiction that writes itself.

{ "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 }

When I prompted Chappy with, "Nano Banana drew it like this. How would you draw it?" to give it a new interpretation, it generated something quite good, not losing out to Nano Banana.

Bobby Fischer, Mikhail Tal, and Magnus Carlsen hanging out together in a bar.

The Christmas Prompt, create fun advertisements with Nano Banana and your products in 1 minute or less, just copy the prompt and that's it.

abstract art inspired by this song wake up by mad season

From the uploaded reference image, With same pose and same facial features, keep the identity and facial features identical to the attached, use Gustave dore illustration style,, size 9:16, don't change the expression and facial for all photos, no text, neutral background minimalist.