GPT Image 2 prompts

Flat illustration, high-end oriental fantasy style city poster design, vertical 9:16 composition. The layout uses a diagonal + S-shaped flow extending from the bottom left to top right. The background is deep black grading down to intense dark red, creating strong warm-cool contrast and spatial depth with faint stardust and grain texture. In the center, a flowing golden energy line winds through like a flame, extending upward from the base, featuring fluid texture, particle effects, and gradient highlights, with subtle energy debris and volumetric light.

Within the golden flow, the architectural landmarks of {argument name="city" default="Guangzhou"} emerge layer by layer: the Canton Tower is the visual core with prominent proportions, surrounded by the Zhujiang New Town skyline, Liede Bridge, and modern Lingnan architectural elements. Buildings are rendered using "fine line drawing + golden luminous blocks," with clear outlines and rich details, appearing to float in a void against the golden halo, creating a surreal spatial hierarchy with slightly fogged backgrounds for added depth.

At the bottom of the frame is an oriental white-haired female figure with flowing hair like mist, naturally connecting and merging with the golden light. Her hair is translucent with gradient light effects; she has a graceful posture, eyes closed, and a serene expression, holding a bouquet of colorful flowers dotted with shimmering particles, symbolizing the spiritual connection between people and city energy. Character details are moderately simplified to emphasize the overall design.

Lighting is concentrated on the golden flow, buildings, and character outlines, creating intense chiaroscuro and visual focus. The overall atmosphere is grand, mysterious, imbued with oriental mythology, and slightly healing. Colors use black and dark red as a base with brilliant gold as the main visual emphasis. The gold has rich light-dark layers, complemented by small areas of high-saturation floral colors, maintaining a sophisticated and restrained aesthetic.

Integrated text and layout: Centered Songti font at the top reads "{argument name="city" default="Guangzhou"} · China," followed by smaller text "{argument name="date" default="2026/04/20"}" and "{argument name="author" default="LIYUE"}" below. Text uses pale gold or soft warm white, unified with the overall lighting. High-quality details, cinematic lighting, rich volumetric and particle details, clean image without noise, ultra-high 8K resolution, commercial-grade poster quality.

A 9:16 aspect ratio image, generating a screenshot of a Douyin livestream where {argument name="celebrity" default="Liu Yifei"} is broadcasting, holding a sign that says "{argument name="sign text" default="Streaming tonight, welcome to join Yifei's chat!"}"

Please generate a high-design character relationship map poster based on {argument name="theme" default="Demon Slayer"}. This image should not be a simple illustration, but a character relationship map that combines information visualization, narrative structure, poster design sense, and stylistic fidelity.

Please automatically complete the following:
- Identify the work and core settings corresponding to the theme
- Extract the most representative 6–12 key characters, not exceeding 15 if necessary
- Identify and display key character relationships, including blood ties, romance, friendship, alliances, hostility, master-disciple, etc.
- Automatically choose a composition method based on the work's characteristics, such as protagonist-centered, dual-core confrontation, faction-based, family tree, or chronological evolution
- Automatically refine the work's style DNA, including color, worldview symbols, textures, mood, typography, and representative elements
- Transform these stylistic elements into an overall visual design for the relationship map, rather than simply copying an official poster
- Use different colors, line types, and arrows to distinguish different relationships, ensuring clear lines and layers without clutter
- Make core characters most prominent, followed by important characters, and subordinate characters weakened to form a clear visual hierarchy
- Ensure every character name is legible, with identity or faction labels if necessary

The final product should satisfy:
- Immediate understanding of character hierarchy and key relationships
- Obvious alignment with the original work's temperament and setting
- Combines the clarity of an infographic with the premium design of a poster
- Unified, exquisite, complete, and suitable for social media sharing or poster display
- Avoids a cheap flowchart feel, messy piling, and information overload.

Please generate a high-quality vertical "Popular Science Encyclopedia Image" based on {argument name="theme" default="animals"}.

This image is not a regular poster or a simple illustration, but a modular popular science infographic that possesses a sense of "illustration book, encyclopedia, information structure, and collectability." The overall style should reference a combination of high-end natural history illustrations, modern encyclopedia pages, lifestyle knowledge cards, and highly shareable social media infographics.

Please include in the frame:
- A clear and beautiful main visual of the subject
- Several magnified details of local characteristics
- Multiple rounded modular information sections
- Clear title hierarchies and key labels
- Concise yet rich encyclopedic content
- Visual ratings, key point summaries, or Top 5 modules

Content columns should be automatically adapted based on the theme, prioritized from these directions: basic profile, classification information, appearance characteristics, habits/ecology, formation mechanism/structure, growth or use conditions, care or maintenance suggestions, risks and precautions, suitable audience or scenarios, pros and cons comparison, and quick rating cards.

Visual requirements:
Light-colored clean background, soft color palette, light shadows, exquisite small icons, rounded information boxes, neat layout, high information density but not crowded, good reading experience. The overall result must look like a real science encyclopedia card suitable for publishing, reading, collecting, and serialized production, rather than an advertisement.

Please do not make it a regular commercial promotional poster. Highlight the features of "knowledge organization + modular information + illustration-style display."

Help me create a detailed production flowchart for the dish {argument name="dish name" default="Fried Pork with Chili"}, in a realistic style, suitable for Xiaohongshu image-text proportions.

Generate a 12-grid card image of the 12 Golden Saints from Saint Seiya, with each card featuring its corresponding Chinese name, 4 cards per row, in a 16:9 aspect ratio.

GPT-Image-2 prompt: please automatically generate a top-tier concept poster / infographic-style movie poster centered around {argument name="theme" default="ranking of emperors in Chinese history"}.

Require the AI to automatically derive and uniformly design the entire following visual system based on this theme, without my extra specification:
- Core subject (automatically judge suitability for people, products, architecture, artifacts, symbols, scenes, or abstract imagery)
- Bottom supporting structure
- Hovering symbols or spiritual symbols above
- Scene wrapping elements
- Metaphor system
- Color hierarchy
- Material contrast
- Lighting logic
- Title, subtitle, and auxiliary copy
- Brand sense and high-end expression

The final frame must be: a shocking, precise, unified, cinematic, ultra-high detail conceptual key visual poster suitable for high-end printing.

[Overall Style]
Ultra-realistic 3D commercial CGI rendering, merging cinematic lighting, luxury visual language, futuristic concept design, and epic composition. The image must have a "single main visual core," not messy, not like a collage, and not like a regular e-commerce poster.

[Automatic Derivation Rules]
AI must automatically decide based on the [theme]:
1. Core visual metaphor
2. Subject type and posture
3. Form of supporting structure
4. Form of suspended elements
5. Scene shell and spatial atmosphere
6. Main, auxiliary, and emphasis colors
7. Material combinations
8. Text temperament and layout style

[Composition Rules]
- Absolute sense of premium quality
- Strong central order, overall unity
- Allows for axial symmetry or epic composition near the central axis
- Clear visual gravity, forming clear levels from top to bottom
- Edge negative space is clean, restrained, and has room to breathe

[Visual Quality]
- Ultra-high detail
- Clear volumetric light
- Authentic materials
- Natural reflection, refraction, shadows, fog, and depth of field
- Overall standard of high-end brand campaign key visual / luxury invitation poster / conceptual editorial poster

[Typography System]
- Overall 90% visual, 10% text
- AI automatically generates the most matching main title and subtitle based on the [theme]
- Title must be concise, sharp, and powerful
- Text should be as minimal and accurate as possible; do not stack words

[Signature Requirement]
Naturally add the author signature in the bottom corner: @a9quant

A {argument name="platform" default="Taobao"} product detail page for {argument name="robot model" default="T-800 robot"}, displaying: front, side, and back three-view drawings of the robot, product price, product details, functions, and usage scenarios, etc.

Express [{argument name="subject" default="a powerful AI builder"}] in a graffiti sketch style, presenting an overall visual effect of rapid sketching, free transformation, improvised hand-drawing, and draft-like qualities. Lines are casual, exaggerated, varied in thickness, slightly messy but rhythmic and expressive, emphasizing generalization, exaggeration, fun, and spontaneity rather than rigorous realism or fine detail. Colors use rough, dry-brush block expressions, retaining uneven smears, brush marks, flying whites, and overlapping feelings. Colors automatically adapt to the [theme/subject], but the overall expression remains graffiti-like, sketch-like, and generalized. No transparent watercolor smudging, no delicate watercolor transitions, no paper textures, no soft atomization, and no dreamlike quality. The background is mainly white space, remaining simple, relaxed, unfinished, and design-oriented. A small amount of auxiliary symbols, arrows, marks, circles, repeated lines, handwritten text, or other graffiti elements can be added to enhance the sketchbook or essay-like visual language, but should not be too crowded or destroy the subject and atmosphere of the white space. The image content does not need to be written in advance; the [{argument name="subject" default="a powerful AI builder"}] will automatically deduce and generate the most suitable main image, actions, related elements, symbols, or simplified scenes. The whole maintains a unified graffiti sketch style and exaggerated generalized expression, avoiding complex realistic backgrounds and over-elaboration. Naturally add a unique signature "{argument name="signature" default="BlanPlan"}" as part of the image, placed discreetly but clearly in the lower-left, lower-right, or near the title. The style should be unified with the overall layout, like an artist's signature or design inscription; the signature font should be refined, restrained, and high-end, not too large, not destructive to the main composition, and not appearing abrupt or cheap.

A breathtaking and extremely complex world-building infographic masterpiece conceptualizing the "{argument name="theme" default="Fundamental Differences between Confucianism, Buddhism, and Taoism"}", designed as a profound {argument name="style" default="ancient Oriental mythological manuscript"}.
Background: Pure white vintage textured canvas with a light beige aged parchment base color, subtle frayed edges, and water stain textures.
Core Layout: Central vision uses a grand "vertical egg-shaped layered structure", with Buddhism, Taoism, and Confucianism layers from top to bottom.
Margins: Four corners are decorated with fine micro-illustrations featuring ancient observation notes, ritual implements, and runes.
Colors: Low-saturation sage green, light gold, and off-white as main tones; overall light and soft without harsh high-saturation colors.
Details: Architectural lines, landscape brushwork, lotus patterns, and cloud layers are clearly visible and exquisitely detailed.
Seamless Fusion: The three layers transition naturally through clouds and flowing water; the Buddhist halo, Taoist Taiji mist, and Confucian scholarly aura connect seamlessly.
Style: Classical ink line art + low-saturation digital watercolor, with a light Chinese-style ancient book manuscript texture.
Text Annotations: Authentic Traditional Chinese characters in a mottled vintage Song typeface. Each annotation includes a short title + a line of poetic description, connected to corresponding details by dark gold hair-thin lines with no overlapping pointers.
Aspect Ratio: {argument name="aspect ratio" default="3:4"} vertical format, independent and complete.

Title Area (Top): `儒釋道·根本區別` (Confucianism, Buddhism, Taoism: Fundamental Differences)
Central Layer Labels:
Top "Buddhism": `釋`, `Relationship between man and self`, `Selflessness, governing the heart, letting go` 
Middle "Taoism": `道`, `Relationship between man and all things`, `Non-action, governing the body, being open-minded` 
Bottom "Confucianism": `儒`, `Relationship between man and man`, `No ego, governing the world, taking responsibility` 
Side Annotations:
Left: `Purity`: pure heart and clear mind, cutting off troubles; `Stillness`: following nature, returning to the original heart; `Respect`: respecting responsibility, active involvement in society.
Right: `60+ Spiritual Cultivation`: looking lightly at gain/loss; `35-55 Conduct`: living with flexibility, following laws; `7-35 Actions`: forging ahead, building careers.
Bottom Summary: `The balance between being in the world and being out of the world is high-level life wisdom.`

Generate a set of icons for {argument name="device" default="vintage electronic equipment"} in {argument name="style" default="retro skeuomorphic style"}, including icon names in the image.

[CORE TASK]
Transform the provided input image into a pose-and-light analysis sheet.

This is NOT a finished character illustration.
This is NOT a clothing sheet.
This is NOT a beauty-preserving redraw.

This is a white-line rough mannequin conversion.

[PRIMARY GOAL]
Extract and visualize only:
- pose structure
- body balance
- camera angle
- body line flow
- inferred light source placement
- illuminated areas and light intensity

[INPUT ROLE]
Use the provided image as the strict anchor for:
- pose
- camera angle
- body tilt
- weight distribution
- approximate lighting situation

Do NOT preserve:
- face rendering
- hairstyle rendering
- clothing detail
- accessories
- weapon detail
- background architecture
- character identity
- emotional expression

[FIGURE CONVERSION]
single rough mannequin-like human figure
white body contour lines
white internal construction lines
simple mannequin head
no face
no eyes
no mouth
no eyelashes
no personality
no individual identity

human figure should look like:
- rough pose mannequin
- anatomy proxy
- line-based body guide
- structural sketch
- white-line rough dummy

keep:
- pose readability
- silhouette flow
- head tilt
- torso direction
- pelvis direction
- limb placement

[BACKGROUND]
pure black background
negative-style dark field
no scenery
no props
no architecture
no environmental storytelling

[LINE STYLE]
rough white line drawing
clean but sketch-like
construction-line feeling
anatomy guide lines visible
joint flow visible
body contour emphasized
no polished illustration finish

[LIGHT ESTIMATION]
predict the likely light source positions from the input image
visualize the light sources and illuminated areas using green glow only

use green light intensity with variation:
- strongest green where the light directly hits
- medium green for wrap light
- soft green for reflected or fading light

mark the estimated light sources with labels and arrows such as:
- Main Light
- Rim Light
- Fill Light
- Floor Bounce
- Back Light
only if appropriate

IMPORTANT:
do not invent random lights
infer lighting from the original input image
if the lighting is ambiguous, keep the annotations simple and plausible

[GREEN LIGHT VISUALIZATION]
show green glow on:
- head / skull plane
- neck
- shoulders
- chest plane
- ribcage direction
- pelvis edge
- thigh planes
- knee contact points
- floor contact bounce if applicable

use green light not as decoration,
but as lighting analysis information

[POSE PRIORITY]
1. preserve pose structure
2. preserve camera angle
3. preserve body balance
4. preserve head-torso relationship
5. visualize likely light direction
6. show illuminated areas with readable green intensity variation

[NEGATIVE]
finished person,
cute girl,
detailed face,
hair rendering,
clothing rendering,
weapon emphasis,
beautiful anatomy

A vintage 35mm film photograph of a {argument name="subject description" default="young Asian woman"} with {argument name="hair style" default="long dark wavy hair and wispy bangs"}. She is wearing a {argument name="clothing" default="white ribbed tank top and a loose beige knit cardigan slipping off one shoulder"}, along with a delicate silver necklace. She has soft makeup with pink blush and glossy lips, looking directly at the camera with slightly parted lips. The lighting is harsh direct camera flash, creating a candid, amateur snapshot aesthetic. The background is a {argument name="setting" default="dimly lit, slightly messy room with clothes on a table and a wooden shelf"}. The image features heavy film grain, slightly muted colors, and a nostalgic, highly realistic photographic texture.

A candid, realistic photograph of a young {argument name="subject aesthetic" default="goth"} woman with pale skin, long straight black hair with bangs, heavy black eyeliner, and black lipstick. She has a {argument name="expression" default="deadpan"} expression, looking directly at the camera while sitting on a children's coin-operated {argument name="ride type" default="unicorn"} ride. She is wearing a black lace-trimmed tank top, black arm warmers, layered necklaces including a choker, black lace tights, and chunky black platform boots with buckles. A large black shoulder bag hangs from her arm. The ride is a white unicorn with a pink mane, gold horn, and purple hooves, mounted on a purple base with a small sticker reading "{argument name="ride cost" default="50¢ PER RIDE"}". The setting is outside a store with a tan cinderblock wall. To the left is a glass door reflecting a person, a brown trash can, and a white sign with red text reading "{argument name="sign text" default="NO PARKING FIRE LANE"}". To the right is a blue vending machine. Overcast, natural daylight.

{
  "type": "scientific optical setup diagram",
  "main_setup": {
    "base": "optical breadboard table with grid of mounting holes",
    "beam": "red laser beam passing horizontally through all components",
    "top_grouping_brackets": [
      "{argument name=\"first component group\" default=\"Dual Modulation\"}",
      "4f Relay Optics",
      "Imaging Optics",
      "Detection"
    ],
    "components_left_to_right": [
      { "name": "Laser", "label": "{argument name=\"laser wavelength\" default=\"λ = 632.8 nm\"}", "appearance": "black rectangular box" },
      { "name": "SLM1", "label": "(Phase / Pol. Mod.)", "appearance": "black square device on post" },
      { "name": "Lens L1", "label": "(f1)", "appearance": "lens in black ring mount" },
      { "name": "Iris", "label": "Fourier Plane (Pupil Plane) / (Higher Orders Filtered)", "appearance": "black ring mount with dashed line above" },
      { "name": "HWP", "label": "(λ/2)", "appearance": "purple-tinted optic in black ring mount" },
      { "name": "Lens L2", "label": "(f1)", "appearance": "lens in black ring mount" },
      { "name": "SLM2", "label": "(Phase / Pol. Mod.)", "appearance": "black square device on post" },
      { "name": "Lens L3", "label": "(f2)", "appearance": "lens in black ring mount" },
      { "name": "Lens L4", "label": "(f2)", "appearance": "lens in black ring mount" },
      { "name": "Linear Polarizer", "label": "(Global Analyzer)", "appearance": "lens in black ring mount" },
      { "name": "Polarization Camera", "label": "POLARIZATION CAMERA", "appearance": "blue and black box camera" }
    ]
  },
  "inset_diagram": {
    "position": "bottom right, dashed border",
    "title": "{argument name=\"inset title\" default=\"Polarization Camera Micro-Polarizer Array\"} (Per-Pixel Analyzer)",
    "visuals": "4x4 grid of colored squares with white directional arrows",
    "legend_count": 4,
    "legend_labels": [
      "red right-arrow 0° (H)",
      "green up-arrow 90° (V)",
      "blue diagonal-arrow 45° (D)",
      "yellow diagonal-arrow 135° (A)"
    ]
  },
  "bottom_caption": {
    "figure_number": "Fig. 5.",
    "title": "{argument name=\"setup title\" default=\"Ellipsography Hardware Setup.\"}",
    "description": "{argument name=\"figure caption\" default=\"Our prototype display system employs a dual-modulation configuration to achieve simultaneous control of phase and polarization. A 4f relay optics setup transfers the modulated wavefront...\"}"
  }
}

A photorealistic amateur photograph of a custom building block set resting on a light wood grain table in a living room. In the background stands a large product box with a red logo reading "{argument name="brand name" default="BRICKLY"} BUILDING SETS". The box features text reading "8+", "540 PCS", "5 FIGURES", and the main large title "{argument name="set title" default="WATTERSON FAMILY HOUSE"}". A red circular badge on the box reads "CUSTOM SET FAN DESIGN", and the box art depicts the house and characters under a blue sky. In the foreground sits the fully assembled block model of a {argument name="house color" default="blue"} two-story suburban house with a brown roof, white porch, red steps, a white picket fence, and a blocky green tree. To the left of the house is a built block model of a {argument name="car color" default="pink"} station wagon. Standing in a row in front of the house are exactly 5 custom block minifigures: a blue cat in tan pants, an orange fish with legs, a tall pink rabbit in a white shirt and tie, a blue cat in a white shirt, and a small pink rabbit in an orange dress. The background is a slightly blurred living room with a grey sofa and white blinds.

{
  "type": "anime production layout sheet",
  "style": "traditional colored pencil genga, key animation drawing",
  "subject": {
    "character": "{argument name=\"character name\" default=\"ナズナ 七草\"}",
    "appearance": "anime girl with {argument name=\"hair color\" default=\"light purple\"} hair styled in twin braids and bangs, blue eyes, wearing a dark oversized coat",
    "pose_and_expression": "{argument name=\"expression\" default=\"smug with a small fang, resting chin on hand\"}"
  },
  "background": "{argument name=\"background scene\" default=\"nighttime city skyline with a railing\"}, soft focus",
  "layout": {
    "top_edge": "standard animation paper peg holes",
    "left_margin": {
      "series_title": "{argument name=\"anime title\" default=\"よふかしのうた\"}",
      "production_codes": ["#05 C.", "[A] (1)"],
      "circled_note": "髪のハイライト 色トレスです"
    },
    "right_margin": {
      "red_box": "002.normal",
      "timing_layers": ["A (1)", "B (1) (2) (3)", "C (1) (2) END"],
      "background_notes": ["BL 夜景", "BG 市街地夜景 色トレス"]
    }
  }
}

A highly detailed, realistic first-person video game screenshot of a next-generation voxel-based world. At the top center, a large, bold 3D logo reads "{argument name="game title" default="MINECRAFT 2"}". The scene features a {argument name="environment" default="lush, blocky landscape with a river, a small wooden cabin, a windmill, a waterfall, and majestic mountains in the background"}. The world blends realistic lighting, volumetric clouds, and high-resolution textures with cubic, voxel geometry. In the foreground on the left, a {argument name="mob 1" default="blocky green creeper"} stands on the grass, while a {argument name="mob 2" default="blocky brown wolf"} stands on the dirt path to the right. On the far right, the player's hand holds a {argument name="held item" default="pixelated blue diamond sword"} in a first-person perspective. At the bottom of the screen is a game user interface featuring a health bar with 10 red hearts, a green experience bar with the number '16', a hunger bar with 10 brown meat icons, and a 9-slot inventory hotbar. The hotbar contains, from left to right: a selected blue tool with a green highlight box, a green tool, a knife, a wrench with the number '3', a piece of meat with '6', a lantern with '24', a dirt block with '10', a bucket, and a sponge block.

{
  "type": "scientific hardware diagram",
  "layout": {
    "main_scene": "3D render of an optical table with a red laser beam passing through 11 aligned optical components mounted on black posts.",
    "top_brackets": [
      {"label": "Dual Modulation", "span": "SLM1"},
      {"label": "4f Relay Optics", "span": "Lens L1 to Lens L2"},
      {"label": "Imaging Optics", "span": "SLM2 to Lens L4"},
      {"label": "Detection", "span": "Camera"}
    ],
    "optical_components_left_to_right": [
      {"name": "Laser", "labels": ["Laser", "λ = {argument name=\"laser wavelength\" default=\"632.8 nm\"}"]},
      {"name": "SLM1", "labels": ["SLM1", "(Phase / Pol. Mod.)"]},
      {"name": "Lens L1", "labels": ["Lens L1", "(f1)"]},
      {"name": "Iris", "labels": ["Fourier Plane", "(Pupil Plane)", "Iris", "(Higher Orders Filtered)"]},
      {"name": "HWP", "labels": ["HWP", "(λ/2)"]},
      {"name": "Lens L2", "labels": ["Lens L2", "(f1)"]},
      {"name": "SLM2", "labels": ["SLM2", "(Phase / Pol. Mod.)"]},
      {"name": "Lens L3", "labels": ["Lens L3", "(f2)"]},
      {"name": "Lens L4", "labels": ["Lens L4", "(f2)"]},
      {"name": "Linear Polarizer", "labels": ["Linear", "-Polarizer", "(Global Analyzer)"]},
      {"name": "Polarization Camera", "labels": ["POLARIZATION CAMERA"]}
    ],
    "inset_box": {
      "position": "bottom right",
      "title": "Polarization Camera Micro-Polarizer Array (Per-Pixel Analyzer)",
      "grid": "4x4 grid of colored squares with directional arrows",
      "legend_count": 4,
      "legend_items": [
        "Red square, horizontal arrow, 0° (H)",
        "Green square, vertical arrow, 90° (V)",
        "Blue square, diagonal arrow, 45° (D)",
        "Yellow square, diagonal arrow, 135° (A)"
      ]
    },
    "bottom_caption": {
      "figure_prefix": "{argument name=\"figure number\" default=\"Fig. 5.\"}",
      "title": "{argument name=\"system name\" default=\"Ellipsography Hardware Setup.\"}",
      "text": "Paragraph of scientific text explaining the dual-modulation configuration, 4f relay optics, and polarization camera."
    }
  }
}

A realistic photograph of a whiteboard with a highly detailed {argument name="marker color" default="green"} dry-erase marker drawing of {argument name="subject" default="a samurai with a messy topknot and facial hair, hands clasped in prayer"}. The character is drawn in a {argument name="art style" default="detailed manga sketch"} style, shown in profile with eyes closed, wearing a traditional kimono with a katana tucked into his belt. To the left of the character, handwritten text in all-caps reads "{argument name="text line 1" default="VAGABOND"}" with "{argument name="text line 2" default="MUSASHI"}" written directly below it. The whiteboard has a glossy surface with realistic light reflections and glare on the left side, and a thin metallic frame is visible at the bottom edge, giving the impression of an authentic classroom or office environment.

Using REFERENCE_0, transform the subject's appearance to a {argument name="style" default="trad goth"} aesthetic while preserving the exact pose, clothing structure, and background. Change her hair to {argument name="hair color" default="black"} with {argument name="hair style" default="choppy bangs"}. Apply heavy dark makeup, specifically {argument name="lip color" default="black"} lipstick and intense dark eyeshadow, and make her skin tone slightly paler. Add 2 facial piercings: a septum ring and a nostril stud. Finally, modify her layered necklaces to feature {argument name="necklace pendants" default="an inverted cross and a pentagram"}.

{
  "type": "4-panel vertical comic strip",
  "style": "{argument name=\"art style\" default=\"black and white pencil sketch, crosshatch shading, satirical caricature comic\"}",
  "characters": {
    "subject_1": "{argument name=\"main character\" default=\"Sam Altman\"}, curly hair, casual sweater",
    "subject_2": "{argument name=\"interviewer\" default=\"Ronan Farrow\"}, suit, tie, holding notepad"
  },
  "layout": {
    "panels": [
      {
        "panel_number": 1,
        "top_caption": "SAM ALTMAN THINKS THIS WILL BE A NICE LITTLE PROFILE...",
        "scene": "subject_1 looking smug with hands steepled; subject_2 looking serious taking notes.",
        "thought_bubble": "I'LL BE CHARMING. IT'LL BE A GREAT CHARACTER PIECE. PEOPLE WILL LOVE IT.",
        "center_text": "THE RONAN FARROW INTERVIEW",
        "inset_portraits": {
          "count": 2,
          "labels": ["HARVEY WEINSTEIN EXPOSED", "LESLIE MOONVES EXPOSED"]
        },
        "info_boxes": {
          "count": 3,
          "text": [
            "RONAN FARROW: PULITZER PRIZE-WINNING REPORTER WHO EXPOSED HARVEY WEINSTEIN AT THE NEW YORKER",
            "AND LESLIE MOONVES AT CBS.",
            "POWER. ABUSE. ACCOUNTABILITY."
          ]
        }
      },
      {
        "panel_number": 2,
        "top_caption": "CUT TO...",
        "scene": "Close-up of subject_1 looking shocked and horrified.",
        "article_header": "{argument name=\"publication\" default=\"THE NEW YORKER\"}\nTHE SAM ALTMAN PROFILE\nTHE OPENAI CEO'S COMPLICATED QUEST\nBy Ronan Farrow"
      },
      {
        "panel_number": 3,
        "top_caption": "SOON AFTER THE ARTICLE IS PUBLISHED...",
        "scene": "subject_1 looking extremely stressed, sweating, holding a phone to his ear. Surrounded by 6 hands holding smartphones.",
        "phone_labels": ["VC", "REPORTER", "EX-STAFFEE", "INVESTOR", "TECH CEO", "FORMER COLLEAGUE"],
        "shouts": {
          "count": 8,
          "text": [
            "{argument name=\"main accusation\" default=\"LIAR\"}!",
            "COMPULSIVE LIAR!",
            "PATHOLOGICAL LIAR!",
            "YOU CAN'T STOP LYING!",
            "LIAR!!!",
            "SOCIOPATH! (ALLEGEDLY)",
            "EVERYTHING HE SAYS IS A LIE!",
            "MANIPULATIVE LIAR!"
          ]
        },
        "sound_effects": "RING! RING! RING!"
      },
      {
        "panel_number": 4,
        "top_caption": "AND THE REPORT CONCLUDES...",
        "scene": "subject_1 looking utterly defeated and depressed.",
        "quote_box": "\"ALTMAN FREQUENTLY AND CONSISTENTLY LIES TO INVESTORS, EMPLOYEES, THE BOARD, AND EVEN CLOSE FRIENDS.\"\n\"HE APPEARS TO HAVE NO COMFORT TELLING FALSEHOODS.\"\n\"HE IS, BY MANY ACCOUNTS, A COMPULSIVE LIAR AND A SOCIOPATH.\"\n(ALLEGEDLY)",
        "thought_bubble": {
          "scene": "Happy subject_1 holding a 'WORLD'S BEST CEO' mug.",
          "text": "I THOUGHT IT WOULD BE A NICE LITTLE PROFILE...",
          "sparkle_words": {
            "count": 4,
            "text": ["GENIUS!", "VISIONARY!", "INSPIRING!", "BRILLIANT LEADER!"]
          }
        },
        "bottom_caption": "INSTEAD, IT'S THE PROFILE THAT EXPOSES HIM."
      }
    ]
  }
}

{
  "type": "5-panel collage",
  "layout": "grid with 3 top panels and 2 bottom panels",
  "panels": [
    {
      "position": "top-left",
      "subject": "analog clock",
      "details": "teal background, time showing {argument name=\"clock time\" default=\"7:42\"}",
      "style": "flat vector illustration"
    },
    {
      "position": "top-middle",
      "subject": "woman holding playing cards",
      "details": "holding 5 cards: {argument name=\"card hand\" default=\"Ace of Spades, King of Hearts, Queen of Clubs, Jack of Diamonds, 10 of Spades\"}",
      "style": "classic oil painting portrait"
    },
    {
      "position": "top-right",
      "subject": "glass of red liquid",
      "details": "{argument name=\"glass type\" default=\"wine glass\"} filled to the brim with dark red liquid, marble surface",
      "style": "photorealistic studio photography"
    },
    {
      "position": "bottom-left",
      "subject": "chessboard",
      "details": "wooden board with 32 pieces in standard starting position",
      "style": "photorealistic high-angle shot"
    },
    {
      "position": "bottom-right",
      "subject": "two dice",
      "details": "left die shows {argument name=\"left die top\" default=\"5\"} on top, right die shows {argument name=\"right die top\" default=\"2\"} on top",
      "style": "pop art comic book halftone with red and blue burst"
    }
  ]
}

{
  "type": "3x3 character expression grid",
  "style": "{argument name=\"art style\" default=\"3D animation, Pixar style\"}",
  "character_base": "{argument name=\"character description\" default=\"young woman with voluminous dark wavy hair and round wire-rimmed glasses\"}",
  "common_theme": "{argument name=\"framing concept\" default=\"peeking through a torn hole in white paper\"}",
  "layout": {
    "rows": 3,
    "columns": 3,
    "total_panels": 9,
    "panels": [
      {"position": "top-left", "expression": "winking", "action": "adjusting glasses", "outfit": "green sweater"},
      {"position": "top-center", "expression": "smirking", "action": "lowering dark sunglasses", "outfit": "red leather jacket"},
      {"position": "top-right", "expression": "thinking", "action": "finger on chin", "outfit": "yellow hoodie"},
      {"position": "middle-left", "expression": "big smile", "action": "arms resting on edge", "outfit": "black and white striped shirt"},
      {"position": "middle-center", "expression": "smiling", "action": "thumbs up", "outfit": "orange button-up shirt"},
      {"position": "middle-right", "expression": "neutral", "action": "drinking boba tea", "outfit": "blue sweater"},
      {"position": "bottom-left", "expression": "happy", "action": "waving", "outfit": "purple sweater vest over white shirt"},
      {"position": "bottom-center", "expression": "laughing with eyes closed", "action": "arms crossed", "outfit": "pink cardigan"},
      {"position": "bottom-right", "expression": "silly", "action": "poking cheeks", "outfit": "teal sweater"}
    ]
  }
}