AI Image Prompts · 绘画提示词库

Using this prompt will dramatically increase the sense of luxury in the thumbnail.

layering:
  order:
    - text_layer
    - character_layer
    - background_layer
  strict: true

subject:
  description: >
    Preserve the subject exactly as in the reference image, keeping all facial features,
    colors, hairstyle, clothing, and proportions. No redesign or reinterpretation.
  framing: >
    Bust-up composition (head to upper torso), making the subject appear large and prominent.
  integrity: full_identity_preservation
  detail_level: ultra_high_resolution
  micro_details: preserve_skin_texture_hair_edges_fabric_details

composition:
  aspect_ratio: "16:9"
  layout: >
    Subject positioned on one side; headline text on the opposite side.
  emphasis: >
    Strong presence on the character's upper body and expression.

action:
  description: >
    Minimal motion enhancement. Maintain the reference pose while adding subtle dramatic energy.

location:
  description: >
    Generate a simple, abstract background inferred from the tone of the reference image.
    No specific elements required; allow the model to interpret color and atmosphere freely.
    Background must NOT contain any characters, silhouettes, faces, bodies,
    or blurred forms derived from the subject.
  background_feel: clean_and_minimal
  allowed_elements: pure_color_gradients_light_abstract_shapes_only
  prohibit_subject_reuse_in_background: true

style:
  visual_style: >
    High-impact reveal-splash aesthetic with strong contrast between character and headline.
  text_effects: >
    Metallic, high-energy lettering with pronounced depth and perspective. No glow effects.
  character_rendering: >
    Extremely high-resolution rendering with sharp facial details, clean hair definition,
    precise edges, and crisp texture fidelity.
  background_style_rules: >
    Background must be purely non-figurative. No silhouettes, no blurred shapes,
    and no reused subject elements.
  ink_splash_rules: >
    Ink splash must be pure black only. No other colors, tinting, blending, or variation.

camera_lighting:
  camera_angle: from_reference
  lighting: >
    Enhance with dramatic key lighting and subtle rim highlights to emphasize the reveal.
  clarity: maximum_definition

colors:
  palette: >
    Background colors inferred from the reference image.
    Character name in metallic silver; announcement text in saturated yellow.
  mood: dramatic, heroic, high_energy

text:
  character_name: "{argument name="character name" default="Character Name"}"
  announcement_fixed: "{argument name="announcement" default="Entering the Battle!!"}"
  placement: opposite_side_of_character
  perspective: >
    Pronounced perspective: front surface larger, back tapered with visible extrusion.
  character_name_style: >
    Metallic silver, b

A stunning young woman with long wavy grey hair sits on a snow-covered ferry seat during a heavy snowfall, leaning her head on her arm. She wears a thick grey knitted sweater and a black puffer vest, with snowflakes resting on her hair and clothes. The background shows an empty ferry deck, icy railings, and a blurred winter cityscape across the water. The mood is cold, cinematic, and serene with soft natural lighting and a muted color palette.

A hyper-real 16K documentary shot capturing the exact moment the Sun flickers—turning off for 0.2 seconds. Show real Earth daylight collapsing into instant, impossible darkness. Streetlights half-ignite in mid-boot, car headlights flare weakly, every shadow in the world disappears at the same exact millisecond, leaving a terrifying flat black nothing. In the next heartbeat, daylight detonates back on—shadows snap violently back into existence like razor-sharp cutouts. Birds freeze mid-flight as if gravity paused; cars halt as if inertia hesitated. The far horizon glows a faint, residual red, like an afterimage burned onto the sky. Use natural global lighting physics, atmospheric scattering, documentary realism, handheld news-camera vibration, micro-grain, zero CGI softness, ultra-sharp lensing, real-world color science, and scientific accuracy. Convey global panic but captured with the calm, unfiltered eye of a live news broadcast. Hyper-real, 16K, macro-cinematic documentary detail.

Horizontal split-screen cinematic wide shot of {argument name="city" default="Tokyo city"} seamlessly blending two eras: {argument name="era 1" default="1920s"} on the left and {argument name="era 2" default="present day"} on the right, merging organically in the center with transitional materials and interactions between people from both times.,
  "subject": "Tokyo city split between 1920s and present day with people interacting across eras",
  "environment": "Urban Tokyo streetscape transitioning from wooden machiya shops, tiled roofs, narrow alleys, rickshaws, vintage trams and paper lanterns on the left to glass-and-steel skyscrapers, neon-lit storefronts, elevated train lines, LED billboards, sleek cafes, bicycles, taxis and compact cars on the right; wet reflective pavement and blended center where gates, tracks and lighting morph into modern equivalents",
  "style": "photorealistic, cinematic, ultra-detailed, historically accurate period detail on left and crisp contemporary detail on right",
  "lighting": "mixed cinematic lighting: soft warm sepia fill on the 1920s left with subtle film-grain texture, cool neon backlight and high-contrast illumination on the present-day right, volumetric city fog and atmospheric particles across the scene, balanced color grading to preserve both eras",
  "camera": {
    "angle": "eye-level wide-angle",
    "distance": "wide shot (cinematic 4:3 composition)",
    "depth_of_field": "dynamic depth of field (selective focus across planes)",
    "focus": "primary focus on the midground center where era interactions occur, with layered focus into foreground and background details"
  },
  "composition": {
    "framing": "horizontal split-screen blended composition, cinematic wide 4:3 framing",
    "subject_placement": "left half dominated by 1920s elements, right half by modern elements, central seam blended organically with key human interactions placed near center rule-of-thirds points",
    "foreground": "wet pavement reflections, close pedestrians from both eras, rickshaw wheel and modern bicycle tire, scattered period props newspapers and modern items smartphones",
    "background": "left: narrow alleys, vintage trams, tiled roofs and paper signs; right: elevated train lines, skyscrapers, LED billboards and neon storefronts; distant atmospheric fog and city lights unifying the skyline",
    "negative_space": "subtle open sky and upper building massing to avoid clutter while maintaining cinematic breadth"
  },
  "mood": "cinematic, nostalgic on the left, vivid and energetic on the right, overall sense of curiosity and surprise from human interactions, narrative and time-travel intrigue",
  "color_palette": [
    "sepia brown",
    "warm amber",
    "cool cyan",
    "neon magenta",
    "neutral concrete grays"
  ],
  "technical": {
    "render_type": "photorealistic photo",
    "post_processing": []
  }

Cinematic storytelling scene of {argument name="characters" default="characters"} in {argument name="setting" default="setting"}. Wide establishing shot + emotional mid-shot + intense detail close-up. Moody lighting, film-grain texture, dramatic contrast, narrative-driven framing, Hollywood-grade depth and atmosphere.

● Generation Theme
{argument name="generation theme" default="Icon material set for YouTube videos"}

● Content
{argument name="content" default="Create icons for YouTube production, editing, posting, and analysis in a unified design. Examples: Actions: Play button, high rating, comments, share, notification bell; Editing: Cut, timeline, telop, BGM, sound effects; Filming equipment: Camera, microphone, light, PC, smartphone, headset; Operation: Upload, analysis, save, playlist, list, arrow"}

● Production Conditions
・Unified ratio, line width, color scheme, and world view
・High visibility
・No text required
・Background: Solid white color
・Resolution: "2K"
・Aspect Ratio: "16:9"

● Design Image
→ Insert the design image below here 💡

【Negative prompt】
Real, photo texture, three-dimensional, 3D, overly complex details, metal texture, dark shadows, horror, overly dark colors

-------------------

● Design Image ① (Soft and Fluffy)
Rounded shapes, soft color scheme, thin black lines, pastel colors, friendly atmosphere, hand-drawn illustration style

-------------------

● Design Image ② (YouTube Simple Flat Style)
Thick lines, emphasis on Red×White×Black, sharp corners, emphasized lines, priority on visibility, modern UI icon

-------------------

● Design Image ③ (Simple)
Minimal, thin lines, refined spacing, centered on achromatic colors, icon font style, elegant and calm design

-------------------

● Design Image ④ (Game Streaming/Streamer)
Fluorescent accent colors (neon blue/purple/red), SF feel, Sharp edges, HUD UI style, cyber and edgy design

-------------------

● Design Image ⑤ (Colorful Pop/KIDS Education)
Thick, rounded silhouette, bright colorful scheme (red, yellow, green, blue, pink), picture book style, soft and fun atmosphere, simple and recognizable icons, educational design that is cute but not too childish.

-------------------

● Design Image ⑥ (Explanation/History/Retro)
Calm retro color scheme (brown, dark green, deep navy, sepia), novel/bulletin board/analytical atmosphere, thin lines, slightly heavy icon feel, old map/document/archive feel, mysterious tone with a unified world view.

-------------------

● Design Image ⑦ (Flashy/Dynamic)
Thick lines, strong contrast, flashy colors (red, yellow, black), energetic and dynamic impression, Japanese manga-style emphasis (exclamation marks, speed lines, emphasized text style), powerful pop design that grabs the viewer's attention.

Let's play with Nano Banana Pro 
[Improved Super Robot Wars Battle Production Prompt]

{argument name="character name" default="Marieshe Fold"}
Special Move Name: "{argument name="special move name" default="Friday Crash"}"
Catchphrase: "{argument name="catchphrase" default="Friday is not a holiday"}"

Overlay this with insane roast scribble, red ink, doodles, remarks, comments.

Make a json of a tier list (S-F scale) for: {argument name="category" default="[*insert-here*]"}

Now generate image with the classically seen style/color scheme and representative thumbnail images for each list item

You are a **Horror Concept Artist and YouTube Thumbnail Specialist**.
Deeply analyze the content of the input text provided at the end, and generate a **high-click-through-rate horror-themed thumbnail image** that simultaneously incites fear and curiosity in viewers.

In doing so, introduce the character from the attached reference image to match the **dark and unsettling world view**, positioning them as a **"Witness who has touched the forbidden."** Maintain character consistency while naturally blending them in with expressions distorted by fear or tense poses.

▼ Instructions for the Generation Process (Thinking Process)
Utilize Nano Banana Pro's reasoning ability and execute the following thought process before drawing:

1.  **[Step 1: Concept Extraction]**: Extract the **Uncanny Valley** created by the contrast between the "silly name Nano Banana" and the "logical, super-performance AI" from the input text. Find elements where cuteness becomes grotesque.
2.  **[Step 2: Visual Translation]**: To visualize the "Thinking Mode," adopt a depiction where the space around the character is encroached upon by digital noise or glowing neural circuits. Grotesquely reinterpret the "banana" motif as decay or mechanical fusion.
3.  **[Step 3: Screen Composition]**: Design a "Contrasting Composition" to enhance visibility as a YouTube thumbnail, placing the character (fearful face) on the right, the threat (symbol of distorted AI) on the left, and large text at the bottom center.

▼ Design and Style Specifications
* **Composition/Layout**: Wide-angle lens (24mm), low angle view to emphasize the character's helplessness and the AI's immensity. The background is dark, with sharp spotlights hitting the subject.
* **Taste**: Photorealistic Cyber-Horror. Dark, humid texture and neon contrast, similar to the movies 'Alien' or 'Blade Runner.'
* **Text**: Place **"The True Identity of Nano Banana"** in a bold Mincho or grunge font in the center or top of the image. Make the text glow red (Glow effect).
* **Character**: Draw the reference character in the style of a "grungy hooded explorer," specifying an expression of screaming or freezing while looking at "something" in the background.

A lone human silhouette walking forward as the world around them breaks all physical laws — a city bending and twisting like melted steel, gravity collapsing sideways, buildings splitting open into glowing red cracks of energy, shards of glass floating in slow motion, time frozen mid-air. The sky is a storm of black clouds tearing apart into neon red voids. Surreal physics, impossible geometry, reality warping into spirals. Ultra-cinematic, photorealistic, 4K detail. Dark futuristic aesthetic, high contrast red-black lighting, dramatic atmosphere, deep shadows. Emphasize intensity, rebellion, and rule-breaking energy.

Camera + Style Parameters:

{
  "style": "{argument name="style" default="ultra cinematic surrealism"}",
  "resolution": "{argument name="resolution" default="4K"}",
  "ratio": "{argument name="ratio" default="16:9"}",
  "camera": {
    "lens": "{argument name="lens" default="35mm wide"}",
    "depth_of_field": "{argument name="depth of field" default="deep focus"}",
    "motion": "{argument name="motion" default="slight forward push"}"
  },
  "lighting": {
    "type": "{argument name="lighting type" default="red-black high contrast"}",
    "glow": "{argument name="glow effect" default="cracks emitting red neon energy"}",
    "shadows": "{argument name="shadows" default="heavy and dramatic"}"
  },
  "environment_details": {
    "city_style": "{argument name="city style" default="dark futuristic dystopia"}",
    "effects": [
      "floating debris",
      "time slices",
      "gravity distortions",
      "energy fissures"
    ],
    "weather": "{argument name="weather" default="storm clouds ripping open with neon red light"}"
  }
}