YouTube thumbnail prompts

metadata:
title: "Nano Banana Pro Design Course Eyecatch - Resort Workcation Style"
model_context: "Luxury Resort Advertisement mixed with Digital Nomad Anime aesthetics"

image_structure:
composition_type: "Scenic Wide Shot + Integrated Typography + Character Overlay"
visual_flow: "Background Scenery -> Huge Text -> Character Details"

layers:
layer_background:
shape: "Full screen background."
content: "Photoreal, Breathtaking tropical beach resort at golden hour (sunset/sunrise)."
details:
elements: "Turquoise ocean, white sandy beach, palm trees swaying, luxury hotel buildings in the distance."
atmosphere: "Relaxing, luxurious, open, and inspiring."
lighting: "Warm golden sunlight mixed with tropical blue shadows."

layer_typography_integrated:
location: "Center to Left side, integrated into the sky and horizon."
elements:
- type: "Background Big Text"
text: "{argument name="large background text" default="Nano Banana Pro"}"
style: "Massive, semi-transparent sans-serif font standing behind the hotel/trees or blending with the clouds. White or Cyan color."

- type: "Overlay Script Text"
text: "{argument name="overlay script text" default="Creative Life"}"
style: "Elegant, red or dark pink handwritten script font overlaying the big text. Adds a luxury touch."

- type: "Bottom Banner Text"
text: "{argument name="bottom banner text" default="Let's become a traveling designer"}"
style: "Clean sans-serif text in a solid bar at the bottom or floating with a shadow."

layer_character_foreground:
location: "Right side or Bottom-Right."
content: "Japanese Kawaii Anime Girl enjoying workcation."
style: "2D Cel-shaded anime art, vibrant and cute."
details:
subject: "A cute anime girl in resort fashion."
appearance:
hair: "Bright color (like orange or blonde) swaying in the sea breeze."
clothing: "Tropical sundress, straw hat, sunglasses on head."
props: "Holding a high-tech tablet or laptop, smiling confidently."
pose: "Relaxed but productive pose, maybe sitting on a deck chair or standing on the beach."

layer_graphic_overlay:
location: "Bottom Left corner."
shape: "Abstract wave or curve shape (similar to reference)."
color: "Translucent Lime Green or Teal gradient."
purpose: "Adds a modern graphic design element to frame the text."

style_and_tone:
art_style: "Travel Magazine Cover Aesthetic"
color_palette:
primary: "Turquoise, Golden Orange, White"
secondary: "Lime Green (Accent), Pink (Script text)"
quality_tags:
- "Best quality"
- "Scenery focus"
- "Cinematic lighting"
- "Detailed water"
- "Anime key visual"

Create a breathtaking, ultra-premium anime cinematic artwork set in a dark fantasy world, designed to look like a frame from the most expensive anime ever produced. A {argument name="character" default="calm, impossibly charismatic male warrior stands alone on the edge of a massive ruined temple overlooking a futuristic ancient city at night"}. He has sharp expressive eyes, detailed black hair moving naturally in the wind, an elegant dark combat coat with intricate silver detailing, subtle battle damage, and an effortless, intimidating posture. He is not attacking or shouting. He simply stands completely still, looking slightly downward with an emotionless, confident expression. His presence alone dominates the entire scene. Around him is an {argument name="aura effect" default="enormous aura field—deep atmospheric energy flowing naturally through the environment like invisible pressure made visible"}. Thin luminous particles, drifting embers, fragments of dust and rain curve around his body. The ground beneath his feet shows subtle cracks from the sheer pressure of his presence. His coat and hair move dramatically in the energy-filled wind. Behind him, enormous storm clouds spiral across the sky, illuminated by distant lightning. A gigantic moon breaks through the clouds, creating a powerful silhouette around his figure. Far below, thousands of tiny city lights create immense depth and scale. The aura should feel beautiful, intimidating and otherworldly, not like a generic glowing outline. Use layered translucent energy, atmospheric distortion, subtle light refraction, floating particles and faint wave-like pressure around the character. Keep the character's face and body sharply defined while the environment reacts to his presence. Composition: low-angle hero shot, character positioned slightly off-center, massive negative space above him, dramatic depth, foreground particles, distant city below, enormous sky, cinematic perspective. Visual style: elite modern anime production, extraordinarily detailed linework, painterly backgrounds, realistic lighting, physically believable shadows, cinematic color grading, realistic atmospheric perspective, highly detailed eyes, hair strands and fabric, subtle skin texture, volumetric moonlight, high contrast, razor-sharp focal subject, breathtaking environmental detail. Blend stylized anime character design with realistic cinematic rendering, so the image feels like a premium anime still rather than a generic illustration. The character should radiate the ultimate “aura farming” energy: silent confidence, overwhelming presence, effortless dominance, mysterious power, elegance and danger. No text, no logos, no watermark, no goofy expression, no exaggerated screaming, no giant muscles, no generic superhero costume, no messy composition, no excessive neon, no blurry face, no distorted anatomy, no extra fingers, no deformed hands, no cheap CGI appearance. Aspect ratio: 16:9. Ultra-detailed, cine

A screenshot of the 2026 Koshien high school baseball finals broadcast. High school baseball broadcast, with the score "{argument name="score" default="Bottom of the 8th, Chiben Wakayama 2-2 Kenadai Takasaki"}" in the corner, 2 outs, bases loaded, and inning display. Features the transparent overlays characteristic of NHK terrestrial broadcasting.

{
  "request_id": "portrait_neon_urban_001",
  "configuration": {
    "model": "v6. 0_or_latest",
    "output_settings": {
      "dimensions": {
        "width": 1080,
        "height": 1920,
        "aspect_ratio": "9:16",
        "target_resolution": "64K DSLR"
      }
    }
  },
  "scene_composition": {
    "subject": {
      "entity": "Young woman",
      "pose": "Standing confidently",
      "action": "Extending index finger forward toward camera lens",
      "interaction": "Dynamic gesture / POV interaction",
      "wardrobe": {
        "outerwear": "{argument name="outerwear color" default="dark crimson red"} striped baseball-style shirt",
        "undergarment": "Light inner shirt",
        "bottoms": "Cargo pants",
        "accessories": [
          "Necklace",
          "Crossbody bag"
        ]
      }
    },
    "environment": {
      "location": "Urban street",
      "time_of_day": "Night",
      "ambience": "Neon-lit",
      "background_elements": [
        "Colorful city lights",
        "Blurred passersby"
      ]
    },
    "cinematography": {
      "camera": {
        "perspective": "Wide-angle",
        "depth_of_field": "Soft bokeh",
        "motion": "Slight motion blur"
      },
      "lighting": {
        "style": "Cinematic",
        "primary_sources": ["cyber punk street lights", "City glow"]
      },
      "ui_overlay": {
        "enabled": true,
        "aesthetic": "Smartphone video recording",
        "on_screen_elements": [
          "REC 00:00:00",
          "8K/60fps",
          "Frame brackets",
          "VIDEO indicator",
          "CINEMATIC indicator"
        ]
      }
    }
  },
  "technical_rendering": {
    "style": "Hyper-realistic",
    "engines": [
      "Octane Render",
      "Unreal Engine 5"
    ]
  },
  "negative_prompt": {
    "stylistic_exclusions": [
      "cartoon",
      "illustration",
      "anime"
    ],
    "quality_exclusions": [
      "low quality",
      "pixelated",
      "blurry"
    ],
    "anatomical_exclusions": [
      "bad anatomy",
      "deformed hands",
      "extra fingers",
      "missing limbs",
      "bad proportions"
    ],
    "branding_exclusions": [
      "watermark (except for requested UI overlays)"
    ]
  }
}

Also, restore my house to its bare shell state before renovation, and gradually renovate it into a Christmas-themed house step-by-step.

Here, Nano Banana Pro needs to generate at least 5 intermediate process images so that the first and last frames have that video transition effect.

metadata:
model_context: "Corporate Tech, High-Energy Business Youtube Thumbnail mixed with Anime Art"

image_structure:
composition_type: "Diagonal Split Layout (Arrowhead Shape)"
visual_flow: "Left Text (Problem/Solution) -> Right Visual (Result/Character)"
layers:
layer_background_left:
shape: "Geometric polygon covering left 60% of screen, with a sharp arrow-point extending into the right side"
color: "Matte Black (#1A1A1A)"
texture: "Subtle carbon fiber or mesh pattern to add tech depth"
layer_typography:

location: "Centered within the left black area"
alignment: "Left-aligned or Centered"
elements:
- type: "Headline (Main)"
text: "{argument name="main headline" default="Design to Earn\nwith AI Side Jobs"}"
style: "Extremely bold, heavy Gothic font (Impact style). White text."
highlight: "Apply Bright Yellow (#FFD700) color to the word '稼ぐ' (Earn) and 'AI'"
- type: "Sub-Headline (Detail)"
text: "{argument name="sub headline" default="Complete Guide to Nano Banana Pro"}"
style: "Smaller white sans-serif text, clean and readable"
- type: "Body Text (Explanation)"
text: "{argument name="explanation text" default="From beginner to professional quality.\nCourse aiming for monetization via the shortest route."}"
style: "Small, thin grey or white text block, justified layout"
layer_cta_button:
shape: "Rounded Pill Shape"
color: "Bright Yellow (#FFD700)"

text: "{argument name="CTA text" default="Apply Now ▶"}"
text_color: "Black"
location: "Bottom left, below the text block"
style: "Flat design with slight drop shadow"
layer_visual_right:
shape: "Fills the remaining right side (behind the arrow overlap)"
content: "Japanese Kawaii Anime Girl illustration"

style: "2D Cel-shaded anime art, high detail, vibrant colors"
details:
subject: "A cute anime girl with a futuristic / cyber-fashion look"
appearance:
hair: "Pastel pink and blue gradient bob cut, with cyber hair clips"
eyes: "Large sparkling anime eyes, confident smile"
clothing: "Stylish tech-wear hoodie with yellow accents to match the background theme"
pose: "Dynamic pose, pointing finger towards the text on the left or giving a thumbs up"
background_context: "Simple light grey or white background with abstract pop patterns (dots/stars) to make the character stand out"
style_and_tone:
art_style: "Modern Corporate Tech Design mixed with Japanese Anime aesthetics"
color_palette:

primary: "Black, Yellow"
secondary: "Pastel Pink/Blue (Character), White"

A 2x2 grid of ancient currency that has morphed into architectural dioramas.

[Top Left: Egypt - A gold coin where the pyramid is a cutaway revealing a {argument name="Random Tomb Interior" default="Random Tomb Interior"} with tiny mummies]

[Top Right: Rome - A silver Denarius where the Colosseum rises up, containing a {argument name="Random Gladiator Fight" default="Random Gladiator Fight"} with moving figures]

[Bottom Left: Aztec - A stone disk coin where the temple steps open to reveal a {argument name="Random Jungle Overgrowth" default="Random Jungle Overgrowth"} taking over]

[Bottom Right: China - A bronze coin with a square hole, featuring the Great Wall winding out of the coin into a {argument name="Random Mountain Landscape" default="Random Mountain Landscape"}]

Archaeological photography, dusty textures, sun-drenched lighting, distinct cultural styles, sharp focus.

{
  "request_id": "portrait_neon_urban_001",
  "configuration": {
    "model": "v6.0_or_latest",
    "output_settings": {
      "dimensions": {
        "width": 1080,
        "height": 1920,
        "aspect_ratio": "9:16",
        "target_resolution": "64K DSLR"
      }
    }
  },
  "scene_composition": {
    "subject": {
      "entity": "Young woman",
      "pose": "Standing confidently",
      "action": "Extending index finger forward toward camera lens",
      "interaction": "Dynamic gesture / POV interaction",
      "wardrobe": {
        "outerwear": "White striped baseball-style shirt",
        "undergarment": "Light inner shirt",
        "bottoms": "Cargo pants",
        "accessories": [
          "Necklace",
          "Crossbody bag"
        ]
      }
    },
    "environment": {
      "location": "Urban street",
      "time_of_day": "Night",
      "ambience": "Neon-lit",
      "background_elements": [
        "Colorful city lights",
        "Blurred passersby"
      ]
    },
    "cinematography": {
      "camera": {
        "perspective": "Wide-angle",
        "depth_of_field": "Soft bokeh",
        "motion": "Slight motion blur"
      },
      "lighting": {
        "style": "Cinematic",
        "primary_sources": ["Neon street lights", "City glow"]
      },
      "ui_overlay": {
        "enabled": true,
        "aesthetic": "Smartphone video recording",
        "on_screen_elements": [
          "REC 00:00:00",
          "8K/60fps",
          "Frame brackets",
          "VIDEO indicator",
          "CINEMATIC indicator"
        ]
      }
    }
  },
  "technical_rendering": {
    "style": "Hyper-realistic",
    "engines": [
      "Octane Render",
      "Unreal Engine 5"
    ]
  },
  "negative_prompt": {
    "stylistic_exclusions": [
      "cartoon",
      "illustration",
      "anime"
    ],
    "quality_exclusions": [
      "low quality",
      "pixelated",
      "blurry"
    ],
    "anatomical_exclusions": [
      "bad anatomy",
      "deformed hands",
      "extra fingers",
      "missing limbs",
      "bad proportions"
    ],
    "branding_exclusions": [
      "watermark (except for requested UI overlays)"
    ]
  }
}

A miniature diorama showing tiny {argument name="PEOPLE / CHARACTERS" default="PEOPLE / CHARACTERS"} struggling with an oversized {argument name="EVERYDAY OBJECT" default="EVERYDAY OBJECT"}. Exaggerated scale contrast, expressive poses, cinematic lighting. Ultra-detailed props, handcrafted realism, macro lens perspective.

Split-screen YouTube thumbnail composition. LEFT SIDE (60%): JD Vance's face, professional warm lighting, determined confident expression with slight smirk, slight low angle shot looking up, high contrast and saturated colors, dark blurred background, heroic and resolute mood. RIGHT SIDE (40%): Shattered fractured glass effect overlaying darkened desaturated images of MAGA supporters and political figures pulling in different directions, visible crack lines and fragmentation throughout, chaotic and divided composition, dark grays and muted reds, broken and unstable visual. TOP OF ENTIRE THUMBNAIL: Bold yellow text with thick black outline reading "{argument name="text" default="JD VANCE DESTROYS THE PLOT"}", text spans across both sides at top third.

{
  "prompt": "A 64K DSLR resolution portrait of a young man with short dark curly hair and a well-groomed beard, standing confidently in a bright neon-lit urban street at night. He is wearing a white striped baseball-style shirt, a light inner shirt, cargo pants, a necklace, and a crossbody bag. He is extending his index finger forward towards the camera lens in a dynamic gesture. The image features a smartphone video recording aesthetic with visible on-screen UI overlays: 'REC 00:00:00', '8K/60fps', frame brackets, and mode indicators like 'VIDEO' and 'CINEMATIC'. The background features colorful city lights and blurred passersby with a soft bokeh effect. Cinematic lighting, slight motion blur, wide-angle perspective. Octane render, Unreal Engine 5 style.",
  "negative_prompt": "cartoon, illustration, anime, low quality, pixelated, blurry, bad anatomy, deformed hands, extra fingers, missing limbs, bad proportions, watermark (except for requested UI overlays)",
  "aspect_ratio": "9:16",
  "width": 1080,
  "height": 1920,
  "model_version": "v6.0_or_latest"
}

A hand holding a smartphone, with an autumn park featuring fallen leaves and a green bench in the background. The smartphone screen displays a vivid photo of the **{argument name="subject" default="theme character"}**. The background landscape inside the phone screen is perfectly aligned with the real, blurred background behind the phone, creating an illusion of transparency. White handwritten text annotations and arrows are drawn on the screen, pointing to the features of the **{argument name="subject feature" default="subject"}**. Soft natural light, photorealistic, 4k resolution, high detail, creative social media photography style. 3D pop-up effect: the upper body emerges from the screen, while the lower body remains within the user interface. The image of the **{argument name="subject" default="theme character"}** is as shown, retaining facial and external features without any changes.

# ===== USER CONTROLS =====
aspect_ratio: "{argument name="aspect ratio" default="3:1"}"          # examples: 3:1, 21:6, 16:9, 9:19.5, 2:1 ... (set any)
title_text: "{argument name="title text" default="<<YOUR_TEXT>>"}"
title_style_preset: "{argument name="logo style preset" default="cool"}"   # cool, cute, cool_cute, luxury, pop, cyber, minimal, retro, kawaii
face_zoom: "{argument name="face zoom" default="off"}"             # off, on
logo_position: "{argument name="logo position" default="right"}"       # up, down, left, right

subject: >
  Create a wide banner using the provided reference image content.
  The primary face must be centered, and a title logo (derived from title_text + title_style_preset)
  must be placed clearly in the composition.

composition: >
  Use the aspect ratio defined in USER CONTROLS (aspect_ratio).
  Keep important elements comfortably inside the frame with inner padding:
  - Keep the face and the title logo at least 15% away from the left/right edges.
  - Keep the face and the title logo at least 16% away from the top/bottom edges.
  Background may extend to the edges.

action: >
  Place the reference image content with maximum fidelity.
  Auto-crop/scale/reposition to fit the banner with no stretching.
  Detect the primary face (if multiple faces, pick the largest/most prominent).
  Center the primary

A YouTube thumbnail where this man is {argument name="theme_en" default="introducing Nano Banana Pro"}. Style: {argument name="style_en" default="for businesspeople"}. Font: {argument name="font_en" default="dynamic, glossy, italic"}. Target: {argument name="target_en" default="for Japanese viewers"}. Text: {argument name="text_en" default="In-depth guide to Google’s new AI ‘Nano Banana Pro’"}.

A dreamlike, movie-quality augmented reality visual where numerous hovering Spotify player interface cards orbit the central figure (the person shown) in a complete 3D spatial composition, with each music player card strategically placed at varying distances, some prominently positioned in front and partially covering the subject, while others float behind and alongside them, utilizing the authentic Apple Music UI/Spotify UI elements playback progress indicators and featuring songs by {argument name="artist name" default="Artist Name"}; all cards display smooth rounded edges with subtle angular perspective shifts, presenting a translucent, frosted-glass aesthetic that radiates a gentle diffused border luminescence with measured cinematic light bloom interacting organically with the ambient lighting of the scene; the composition showcases a cool-to-neutral color palette with rich yet preserved shadow detail, strategic bursts of color from album artwork, medium-high contrast levels with gradual highlight transitions, delicate focal depth variation where nearer cards maintain crisp detail while farther ones receive gentle blur treatment, and understated motion-enhancing accents, all while keeping the subject photorealistic, centrally positioned, and authentically integrated into their physical surroundings.

Using the person from this icon, create a flashy, glitzy image like a thumbnail for a so-called “suspicious information product” in the {argument name="genre_en" default="SEO or AI"} field.

2x2 grid, 16:9, do this for 4 important {argument name="subject" default="Asian cities"}: Generate a photoreal miniature pop-up book diorama for {argument name="subject" default="Asian cities"}.Rules:- infer SUBJECT_DNA automatically- use BASE_DOCUMENT as the physical foundation- the subject must rise from the page as a paper-engineered 3D world- include inferred landmarks, architecture, terrain, infrastructure, cultural motifs, and small scale cues- show folded platforms, stairs, slots, hinges, support struts, and hidden paper mechanics- integrate the subject name or symbolic typography as raised paper letters or structural forms- the base page should contain an inferred map, diagram, blueprint, or printed context relevant to {argument name="subject" default="Asian cities"}- everything must feel crafted from paper, cardstock, ink, miniature model materials, and precise pop-up engineering- no hard-coded city, landmark, tower, temple, map, color, or text unless supplied

{
  "generation_request": {
    "subject_reference": {
      "Gender": "Female", A Beautiful Woman in her 20s.
      "facial_preservation": "High fidelity, exact features, no stylization, no alteration to identity"
    },
    "prompts": {
      "positive_prompt": "High-resolution aerial action photography of [Reference Woman] paragliding. Low-angle wide-angle selfie shot captured via a selfie stick held in her left hand. She is suspended in a professional paragliding harness with legs freely dangling, wearing a black bikini and simple flip-flops. Her right hand grips the paragliding control handle. The background is an expansive, vibrant tropical coastline with deep turquoise ocean and clear blue sky. Bright natural daylight, sharp focus, hyper-realistic skin texture, cinematic composition, dynamic motion, true-to-life proportions.",
      "negative_prompt": "CG, 3d render, anime, cartoon, painting, drawing, illustration, altered face, distorted features, bad anatomy, deformed hands, missing fingers, helmet, sunglasses, wetsuit, sneakers, cloudy, dark lighting, blurry, noise, grain, low resolution"
    },
    "scene_details": {
      "camera_angle": "Low perspective, wide-angle, looking up from selfie stick",
      "lighting": "Bright natural daylight, hard sunlight",
      "attire": [
        "Black bikini",
        "Simple flip-flops"
      ],
      "pose_constraints": {
        "left_hand": "Holding selfie stick pointed toward self",
        "right_hand": "Holding paragliding control handle",
        "legs": "Dangling freely"
      }
    },
    "technical_settings": {
      "aspect_ratio": "9:16",
      "style": "Ultra-realistic, raw photography"
    }
  }
}

2x2 grid, 16:9, do this for 4 famous movies: TYPOGRAPHIC_EMERGENCE SELECT visual_output FROM latent_graphic_systems WHERE subject = {argument name="movie subject" default="[CENTRAL_IMAGE]"} AND mark_substrate = 'continuous running prose, legible at close range' AND type_density_map = infer(VALUE_STRUCTURE FROM SUBJECT_SILHOUETTE) AND line_flow = infer(TEXT_PATH FROM SUBJECT_CONTOUR) AND typeface_logic = {argument name="typography style" default="infer(PERIOD_APPROPRIATE_FACE FROM AUTHOR, PUBLICATION_ERA)"} AND color_scheme = {argument name="color scheme" default="'ink on aged paper, single value, no illustration marks whatsoever'"} AND drawing_rule = 'every mark in the image is a letterform; tonal value is produced ONLY by leading, tracking, and type size; no rules, no fills, no drawn lines' ORDER BY emergence_at_distance DESC, legibility_at_close_range DESC, value_range_via_typography DESC, no_non_letterform_marks DESC LIMIT 1;

Please create a YouTube thumbnail using this character.
- Use only the upper body, with a cheerful pose and expression.
- Include large text that says “{argument name="title_text_en" default="雑談"}” and add the furigana “{argument name="furigana_en" default="ざつだん"}”.
- Give it a pop feel, but make the background simple and composed of stripes.

# ===== USER CONTROLS =====
title_text: "{argument name="display string" default="<<YOUR_TEXT>>"}"
title_style_preset: "{argument name="logo design preset" default="cool"}"  # cool, cute, cool_cute, luxury, pop, cyber, minimal, retro, kawaii
face_zoom: "{argument name="zoom on/off" default="off"}"            # off, on

subject: >
  Create a 3:1 wide banner using the provided reference image content.
  The primary face must be centered inside an invisible safe zone (not drawn),
  and a title logo (derived from title_text + title_style_preset) must be placed inside the same safe zone.

composition: >
  Aspect ratio 3:1.
  Invisible safe zone (DO NOT draw it):
  - Left margin: 15% of width
  - Right margin: 15% of width
  - Top margin: 16% of height
  - Bottom margin: 16% of height
  Keep the entire face AND the entire title logo fully inside this safe zone.
  Background may extend to the edges.

action: >
  Place the reference image content with maximum fidelity.
  Auto-crop/scale/reposition to fit a 3:1 banner with no stretching.
  Detect the primary face (if multiple faces, pick the largest/most prominent).
  Center the primary face within the safe zone both horizontally and vertically.
  Never crop off the face/eyes; keep the full face comfortably inside the safe zone (not near edges).

  Face zoom behavior:
  - If face_zoom is OFF: keep the original framing as much as possible while still centering the face in the safe zone.
  - If face_zoom is ON: zoom/crop to a bust-up portrait centered on the face
    (head and shoulders visible; include upper chest; do not crop the top of the head or chin; keep facial features prominent).

  Create negative space inside the safe zone for the title logo by adjusting crop/reposition/out

# ===== USER CONTROLS =====
title_text: "{argument name="display string" default="<<YOUR_TEXT>>"}"
title_style_preset: "{argument name="logo design preset" default="cool"}"  # cool, cute, cool_cute, luxury, pop, cyber, minimal, retro, kawaii
face_zoom: "{argument name="zoom on/off" default="off"}"            # off, on

subject: >
  Create a 21:6 wide banner using the provided reference image content.
  The primary face must be centered inside an invisible safe zone (not drawn),
  and a title logo (derived from title_text + title_style_preset) must be placed inside the same safe zone.

composition: >
  Aspect ratio 21:6.
  Invisible safe zone (DO NOT draw it):
  - Left margin: 15% of width
  - Right margin: 15% of width
  - Top margin: 16% of height
  - Bottom margin: 16% of height
  Keep the entire face AND the entire title logo fully inside this safe zone.
  Background may extend to the edges.

action: >
  Place the reference image content with maximum fidelity.
  Auto-crop/scale/reposition to fit a 21:6 banner with no stretching.
  Detect the primary face (if multiple faces, pick the largest/most prominent).
  Center the primary face within the safe zone both horizontally and vertically.
  Never crop off the face/eyes; keep the full face comfortably inside the safe zone (not near edges).

  Face zoom behavior:
  - If face_zoom is OFF: keep the original framing as much as possible while still centering the face in the safe zone.
  - If face_zoom is ON: zoom/crop to a bust-up portrait centered on the face
    (head and shoulders visible; include upper chest; do no

9 shots, same character, same vibe.

Read the motif depicted in the attached image, generate multi-angle shots, and create four scenes divided into a 2x2 grid.

[Action 1] The senior colleague (senpai) is looking at books on a shelf. The photographer presses a button on a remote control in their hand, and a distinctive electronic sound/chime rings. [Dialogue 1] The senpai is surprised, immediately turns to the camera, and playfully says, "Stop it." [Action 2] The photographer rings the electronic sound again. [Action 3] The senpai looks down shyly, squats momentarily, then stands up, laughing and covering their face with their hands. [Text Overlay] "{argument name="text overlay 1" default="Tried pressing the senpai's switch while they were shopping at the bookstore"}" "{argument name="text overlay 2" default="#This feeling is too cute www"}" "{argument name="text overlay 3" default="#Definitely inviting me www"}"