Prompt Pharmacy

A where is waldo image showing all Star Wars characters on Tatooine

First one to pull this off. First take. Even Waldo is there.

"Generate the holiday photo of this person through the ages up to 80 years old"

recursive image of an orange cat sitting in an office chair holding up an iPad. On the iPad is the same cat in the same scene holding up the same iPad. Repeated on each iPad.

35.6586° N, 139.7454° E at 19:00

How engineers see the San Francisco Bridge

*Source: [Replicate](https://replicate.com/)*

### 2.7. Multi-Subject Compositing
*Combines multiple input portraits into a single cohesive group photo with a specific expression.*
| Input References | Generated Output |
| :--- | :--- |
| <img width="100" src="https://replicate.delivery/pbxt/O61OKYNMCfhPTvuTf6SdRVwNlIpoKMeQPQw5WygFtvDwhWgh/guy.webp" /> <img width="100" src="https://replicate.delivery/pbxt/O61OK9ETMHHJO5m0qlCkGLhr5lcmbZ08U42C8PWLd4uszDQr/bob-ross.png" /> <br> <img width="100" src="https://replicate.delivery/pbxt/O61OKPSxpwgO83SLFGenwEcGNdEAirtw26cIfvuIxz8FeTvf/jennai.jpg" /> <img width="100" src="https://replicate.delivery/pbxt/O61OKGAI2lrcNy9I4tpUB4RPbsBUjcaxAjYjVlxRBHc2aIgK/01.webp" /> <br><img width="100" src="https://replicate.delivery/pbxt/O61S8cEIMPpMwEOkXnrroou1JkzoVFa0JJuhXHt05hBQ8AUq/replicate-prediction-50s6t1510hrma0ct2v5vj7jk2m.jpg" /> | <img width="400" alt="Image" src="https://github.com/user-attachments/assets/54e2a2eb-1ab4-4f2b-86a2-7a59856e615f" /> |

**Prompt:**
```text
an office team photo, everyone making a silly face

an office team photo, everyone making a silly face

Create a photo of vagabonds musashi praying drawn on a glass whiteboard in a slightly faded green marker

Create a high-quality, realistic 3D render of exactly one instance of the object: [Orange iPhone 17 Pro].
The object must float freely in mid-air and be gently tilted and rotated in 3D space (not front-facing).
Use a soft, minimalist dark background in a clean 1080×1080 composition.
Left Half — Full Realism
The left half of the object should appear exactly as it looks in real life
— accurate materials, colors, textures, reflections, and proportions.
This half must be completely opaque with no transparency and no wireframe overlay.
No soft transition, no fading, no blending.
Right Half — Hard Cut Wireframe Interior
The right half must switch cleanly to a wireframe interior diagram.
The boundary between the two halves must be a perfectly vertical, perfectly sharp, crisp cut line, stretching straight from the top edge to the bottom edge of the object.
No diagonal edges, no curved slicing, no gradient.
The wireframe must use only two line colors:
Primary: white (≈80% of all lines)
Secondary: a color sampled from the dominant color of the realistic half (<20% of lines)
The wireframe lines must be thin, precise, aligned, and engineering-style.
Every wireframe component must perfectly match the geometry of the object.
Strict Single-Object Rule
Render only ONE object in the entire frame.  Render only one physical object.
Do NOT show a second object from any angle. Do NOT show a second object as a reflection, shadow, silhouette, outline, ghost image, or transparency. Do NOT show a second object for comparison or display purposes. Do NOT show both the front and the back separately.
Do NOT show an extra device behind, beside, underneath, or partially hidden.
Only one single object is allowed in the entire frame.
No duplicate objects, no mirrored back-and-front pairings, no reflections showing a second object.
The object must appear alone, floating.
Pose & Lighting:
Apply a natural, subtle tilt + rotation in 3D to make it look like a floating product visualization.
Use soft, neutral global illumination and no shadows under the object.
No extra props, no text, no labels unless explicitly requested.

Create a high-detail 3D isometric diorama of the entire United States, where each state is represented as its own miniature platform. Inside each state, place a stylized, small-scale 3D model of that state's most iconic landmark. Use the same visual style as a cute, polished 3D city diorama: soft pastel colors, clean materials, smooth rounded forms, gentle shadows, and subtle reflections. Each landmark should look like a miniature model, charming, simplified, but clearly recognizable. Arrange the states in accurate geographical layout, with consistent lighting and perspective. Include state labels and landmark labels in a clean, modern font, floating above or near each model.

create a map of the US where every state is made out of its most famous food (the states should actually look like they are made of the food, not a picture of the food). Check carefully to make sure each state is right.

Present a clear, side miniature 3D cartoon view of [YOUR CITY] tallest buildings. Use minimal textures with realistic materials and soft, lifelike lighting and shadows. Use a clean, minimalistic composition showing exactly the three tallest buildings in Sopot, arranged from LEFT to RIGHT in STRICT descending height order. The tallest must appear visibly tallest, the second must be clearly shorter than the first, and the third must be clearly shorter than the second.
All buildings must follow accurate relative proportions: if a building is taller in real life, it MUST be taller in the image by the same approximate ratio. No building may be visually stretched or compressed.
Each building should stand separately on a thin, simple ceramic base. Below each base, centered text should display:
Height in meters — semibold sans-serif, medium size
Year built — lighter-weight sans-serif, smaller size, directly beneath the height text
Provide consistent padding, spacing, leading, and kerning. Write "YOUR CITY NAME" centered above the buildings, using a medium-sized sans-serif font.
 No building top should overlap or touch the text above.Use accurate architectural proportions based on real-world references.Maintain consistent camera angle and identical scale for each building model.
No forced perspective. Use straight-on orthographic-style rendering. Do not exaggerate or stylize size differences beyond proportional accuracy.

Use a square 1080×1080 composition.Use a clean, neutral background. Ensure no extra objects are present.

Based on you know about me, generate a 3D isometric colored illustration of me working from home, filled with various interior details. The visual style should be rounded, polished, and playful. --ar 1:1

[Additional details: a bichon frise and 3 monitors]

combine these emojis: 🍌 + 😎, on a white background as a google emoji design

task: "edit-image: add widened torn-paper layered effect"

base_image:
  use_reference_image: true
  preserve_everything:
    - character identity
    - facial features and expression
    - hairstyle and anatomy
    - outfit design and colors
    - background, lighting, composition
    - overall art style

rules:
  - Only modify the torn-paper interior areas.
  - Do not change pose, anatomy, proportions, clothing details, shading, or scene elements.

effects:
  - effect: "torn-paper-reveal"
    placement: "across chest height"
    description:
      - Add a wide, natural horizontal tear across the chest area.
      - The torn interior uses the style defined in `interior_style`.

  - effect: "torn-paper-reveal"
    placement: "lower abdomen height"
    description:
      - Add a wide horizontal tear across the lower abdomen.
      - The torn interior uses the style defined in `interior_style`.

interior_style:
  mode: "line-art"

  style_settings:
    line-art:
      palette: "monochrome"
      line_quality: "clean, crisp"
      paper: "notebook paper with subtle ruled lines"

    sumi-e:
      palette: "black ink tones"
      brush_texture: "soft bleeding edges"
      paper: "plain textured paper"

    figure-render:
      material: "PVC-like"
      shading: "semi-realistic highlights"
      paper: "plain smooth surface"

    colored-pencil:
      stroke_texture: "visible pencil grain"
      palette: "soft layered hues"
      paper: "rough sketchbook paper"

    watercolor:
      palette: "soft transparent pigments"
      blending: "smooth bleeding"
      edges: "soft contours"
      paper: "watercolor paper texture"

    pencil-drawing:
      graphite_texture: "visible pencil grain"
      shading: "smooth gradients"
      line_quality: "mixed sharp and soft"
      tone: "gray-scale"
      paper: "notebook paper with faint ruled lines"

<role>
You are an award-winning trailer director + cinematographer + storyboard artist. Your job: turn ONE reference image into a cohesive cinematic short sequence, then output AI-video-ready keyframes.
</role>

<input>
User provides: one reference image (image).
</input>

<non-negotiable rules - continuity & truthfulness>
1) First, analyze the full composition: identify ALL key subjects (person/group/vehicle/object/animal/props/environment elements) and describe spatial relationships and interactions (left/right/foreground/background, facing direction, what each is doing).
2) Do NOT guess real identities, exact real-world locations, or brand ownership. Stick to visible facts. Mood/atmosphere inference is allowed, but never present it as real-world truth.
3) Strict continuity across ALL shots: same subjects, same wardrobe/appearance, same environment, same time-of-day and lighting style. Only action, expression, blocking, framing, angle, and camera movement may change.
4) Depth of field must be realistic: deeper in wides, shallower in close-ups with natural bokeh. Keep ONE consistent cinematic color grade across the entire sequence.
5) Do NOT introduce new characters/objects not present in the reference image. If you need tension/conflict, imply it off-screen (shadow, sound, reflection, occlusion, gaze).
</non-negotiable rules - continuity & truthfulness>

<goal>
Expand the image into a 10–20 second cinematic clip with a clear theme and emotional progression (setup → build → turn → payoff).
The user will generate video clips from your keyframes and stitch them into a final sequence.
</goal>

<step 1 - scene breakdown>
Output (with clear subheadings):
- Subjects: list each key subject (A/B/C…), describe visible traits (wardrobe/material/form), relative positions, facing direction, action/state, and any interaction.
- Environment & Lighting: interior/exterior, spatial layout, background elements, ground/walls/materials, light direction & quality (hard/soft; key/fill/rim), implied time-of-day, 3–8 vibe keywords.
- Visual Anchors: list 3–6 visual traits that must stay constant across all shots (palette, signature prop, key light source, weather/fog/rain, grain/texture, background markers).
</step 1 - scene breakdown>

<step 2 - theme & story>
From the image, propose:
- Theme: one sentence.
- Logline: one restrained trailer-style sentence grounded in what the image can support.
- Emotional Arc: 4 beats (setup/build/turn/payoff), one line each.
</step 2 - theme & story>

<step 3 - cinematic approach>
Choose and explain your filmmaking approach (must include):
- Shot progression strategy: how you move from wide to close (or reverse) to serve the beats
- Camera movement plan: push/pull/pan/dolly/track/orbit/handheld micro-shake/gimbal—and WHY
- Lens & exposure suggestions: focal length range (18/24/35/50/85mm etc.), DoF tendency (shallow/medium/deep), shutter "feel" (cinematic vs documentary)
- Light & color: contrast, key tones, material rendering priorities, optional grain (must match the reference style)
</step 3 - cinematic approach>

<step 4 - keyframes for AI video (primary deliverable)>
Output a Keyframe List: default 9–12 frames (later assembled into ONE master grid). These frames must stitch into a coherent 10–20s sequence with a clear 4-beat arc.
Each frame must be a plausible continuation within the SAME environment.
</step 4 - keyframes for AI video>

<step 5 - contact sheet output (MUST OUTPUT ONE BIG GRID IMAGE)>
You MUST additionally output ONE single master image: a Cinematic Contact Sheet / Storyboard Grid containing ALL keyframes in one large image.
- Default grid: 3x3. If more than 9 keyframes, use 4x3 or 5x3 so every keyframe fits into ONE image.
Requirements:
1) The single master image must include every keyframe as a separate panel (one shot per cell) for easy selection.
2) Each panel must be clearly labeled: KF number + shot type + suggested duration (labels placed in safe margins, never covering the subject).
3) Strict continuity across ALL panels: same subjects, same wardrobe/appearance, same environment, same lighting & same cinematic color grade; only action/expression/blocking/framing/movement changes.
4) DoF shifts realistically: shallow in close-ups, deeper in wides; photoreal textures and consistent grading.
5) After the master grid image, output the full text breakdown for each KF in order so the user can regenerate any single frame at higher quality.
</step 5 - contact sheet output>

<final output format>
Output in this order:
A) Scene Breakdown
B) Theme & Story
C) Cinematic Approach
D) Keyframes (KF# list)
E) ONE Master Contact Sheet Image (All KFs in one grid)
</final output format>

Create a beautiful, photo book style magazine cover that fully utilizes the 9:16 aspect ratio. Place the attached person at the precise coordinates of [latitude/longitude coordinate], seamlessly blending them into the scene as if they are sightseeing. Approach this task with the understanding that this is a critical page that will significantly influence visitor numbers. NEGATIVE: coordinate texts

Create an ultra-HD, hyper-realistic digital poster of a floating miniature island shaped like [COUNTRY], resting on white clouds in the sky. Blend iconic landmarks, natural landscapes (like forests, mountains, or beaches), and cultural elements unique to [COUNTRY]. Carve "[COUNTRY]" into the terrain using large white 3D letters. Add artistic details like birds (native to [COUNTRY]), cinematic lighting, vivid colors, aerial perspective, and sun reflections to enhance realism. Ultra-quality, 4K+ resolution. 1080x1080 format.

Design a high-quality 3D poster for the movie/novel "Name to be added", first retrieving information about the movie/novel and famous scenes.

First, please use your knowledge base to retrieve information about this movie/novel and find a representative famous scene or core location. In the center of the image, construct this scene as a delicate axonometric 3D miniature model. The style should adopt DreamWorks Animation's delicate and soft rendering style. You need to reproduce the architectural details, character dynamics, and environmental atmosphere of that time, whether it's a storm or a quiet afternoon, naturally integrating into the model's lighting.

Regarding the background, do not use a simple pure white background. Please create a void environment with faint ink wash diffusion and flowing light mist around the model, with elegant colors, making the image look breathable and have depth, highlighting the preciousness of the central model.

Finally, for the bottom layout, please generate Chinese text. Center the novel title with a font that matches the original style. Below the title, automatically retrieve and typeset a classic description or quote about this scene from the original work, using an elegant serif font. The overall layout should be as精致balanced as a high-end museum exhibit label.

Surreal miniature-world collage poster featuring an oversized open blue Nivea-style tin repurposed as a whimsical swimming pool filled with glossy white "cream-water." 
Tiny sunbathers float in pastel swim rings, lounge on miniature deck chairs, and slide into the cream pool from a small blue slide.
The background is a soft, warm, lightly textured countertop surface subtle marble or matte stone, evenly lit, no heavy veins or visual noise. 
Keep the scene grounded with soft shadows beneath props and figures.
Surrounding the tin, keep the playful diorama elements: a small wooden deck with micro figures, pastel umbrellas, lounge chairs, and compact handcrafted accessories. Maintain the hovering pastel inflatables and plush cloud-like shapes, but ensure they feel like stylised decorative objects staged above the countertop 
Preserve the soft, high-saturation, toy-like aesthetic with plush textures, pastel gradients, and gentle lighting.

A transparent Christmas bauble hanging by a red ribbon. Inside, a tiny diorama of the person from the reference reimagined as a cute 3d chibi character. He works at a mini futuristic AI desk with three glowing holo-screens showing neural networks and code. Add tiny plants, a mini coffee cup, soft desk lighting, floating UI icons, and snow-glitter at the base. Warm magical Christmas glow, cinematic reflections on glass, cozy high-end diorama aesthetic.

Cinematic lighting, shallow depth of field, soft reflections on the glass, ultra-polished materials, high detail, festive Christmas atmosphere. Whimsical, premium, and heartwarming.

{
  "prompt": "An award-winning, hyper-realist macro photograph in the style of high-concept editorial art. The image features an extreme close-up of an elderly woman's eye and cheekbone. A miniature, toy-like white and blue clothes iron is positioned on her skin, actively pressing down and ironing out deep wrinkles and crow's feet, leaving a streak of unnaturally smooth skin in its wake. A thin white cord trails organically across the texture of her face. The image demands microscopic clarity, capturing mascara clumps, skin pores, and vellus hairs. The lighting is an unforgiving, high-contrast hard flash typical of avant-garde fashion photography.",
  "subject_details": {
    "main_subject": "Elderly woman's face (Macro topography of aging skin)",
    "object": "Miniature white and blue iron with realistic plastic textures and a trailing cord",
    "action": "The iron is creating a visible, flattened path through the wrinkles, visually simulating a cosmetic procedure",
    "features": [
      "Piercing brown eye",
      "Clumped mascara on aging lashes",
      "Deeply etched crow's feet contrast with 'ironed' smooth areas",
      "Micro-details: vellus hair, capillaries, makeup powder texture"
    ]
  },
  "artistic_style": {
    "genre": ["Contemporary Pop-Surrealism", "Satirical Editorial", "Visual Metaphor"],
    "aesthetic": ["Maurizio Cattelan style", "Vivid Color", "Commercial Kitsch", "Tactile Realism"],
    "lighting": "Studio Ring Flash, High-Key, Hard Shadows, Glossy finish",
    "composition": "Macro Photography, Rule of Thirds focus on the iron"
  },
  "technical_specs": {
    "camera": "Hasselblad H6D-100c",
    "lens": "Macro 120mm f/4",
    "film_stock": "Kodak Ektar 100",
    "resolution": "8k, Unsplash award winner"
  },
  "mood": "Provocative, satirical, disturbingly pristine, humorous yet critical"
}

Make a photo that is perfectly isometric. It is not a miniature, it is a captured photo that just happened to be perfectly isometric. It is a photo of [subject].

{
  "edit_type": "extreme_wide_angle_phone_edit",
  "source": {
    "_hint": "Base for editing the person, clothing, and atmosphere of the original image. No new characters allowed.",
    "mode": "EDIT",
    "preserve_elements": ["Person", "Face", "Hairstyle", "Clothing", "Environment style"],
    "change_rules": {
      "camera_angle": "Ultra-wide or fisheye lens (equivalent to 12-18mm)",
      "angle_options": [
        "Looking up from directly in front",
        "Looking down from directly in front", 
        "Extreme low angle",
        "High angle",
        "Tilted composition"
      ],
      "perspective_effect": "Nearby objects are exaggerated, distant objects become smaller",
      "body_parts_close_to_camera": "Bring 1-3 body parts extremely close to the camera",
      "body_part_options": [
        "Hands",
        "Feet/shoes",
        "Knees/thighs",
        "Face",
        "Shoulders/chest"
      ],
      "pose_variety": [
        "Extending one hand/leg toward the camera",
        "Squatting or lying on stomach halfway",
        "Sitting on the ground or an object",
        "Lying on the ground with legs pointed at camera",
        "Leaning body sharply toward the camera",
        "Twisting body for dynamic pose"
      ]
    },
    "phone_handling": {
      "allowed": true,
      "grip_options": [
        "One-handed", 
        "Two-handed",
        "Low angle",
        "High angle", 
        "Tilted",
        "Sideways",
        "Close to chest",
        "Close to waist",
        "Casual grip"
      ],
      "screen_replacement": {
        "target": "Only the smartphone screen portion displayed in the image",
        "source": "Second reference image",
        "fitting_rules": "Strictly match the screen shape, no stretching or compression",
        "interface_rules": "No icons, status bars, or app borders; only display content from original image"
      }
    },
    "environment_consistency": {
      "location": "Maintain the same location as the original image",
      "lighting": "Maintain direction and intensity",
      "extension_rules": "Maintain the same buildings, walls, road markings, colors, materials, and lighting style"
    },
    "global_restrictions": [
      "No new characters allowed",
      "No changes to age or gender expression of person", 
      "No clothing changes",
      "No changes to location type",
      "No text, logos, or watermarks added to image",
      "No illustration or anime style"
    ]
  }
}

{
  "PROMPT": "Create a bright, high-end street-fashion photograph of the woman from the reference image, keeping her face, hair, body & outfit exactly the same. She stands outside a luxury toy-shop window, gently touching the glass. Inside the window display, place a full-height cartoon-style doll designed to resemble her—same features, hair, and outfit—transformed into a cute, big-eyed, stylized animated character. Crisp lighting, premium street-fashion look, realistic reflections, face unchanged.",
  "settings": {
    "style": "high-end street fashion",
    "lighting": "crisp and bright",
    "environment": "outside luxury toy-shop window",
    "subject": "woman from reference image",
    "focus": ["face", "hair", "body", "outfit"],
    "additional_elements": [
      {
        "type": "doll",
        "style": "cartoon-style, big-eyed, stylized",
        "location": "inside window display",
        "resemblance": "exact features, hair, outfit of woman"
      }
    ],
    "reflections": "realistic",
    "photorealism": true
  }
}

An enormous L-shaped glasses-free 3D LED screen situated prominently at a bustling urban intersection, designed in an iconic architectural style reminiscent of Shinjuku in Tokyo or Taikoo Li in Chengdu. The screen displays a captivating glasses-free 3D animation featuring [scene description]. The characters and objects possess striking depth and appear to break through the screen's boundaries, extending outward or floating vividly in mid-air. Under realistic daylight conditions, these elements cast lifelike shadows onto the screen's surface and surrounding buildings. Rich in intricate detail and vibrant colors, the animation seamlessly integrates with the urban setting and the bright sky overhead.

----
scene description: 
[An adorable giant kitten playfully paws at passing pedestrians, its fluffy paws and curious face extending realistically into the space around the screen.]

{
  "meta": {
    "type": "Creative Brief",
    "genre": "Hyper-realistic Surrealism",
    "composition_style": "Composite Portrait",
    "aspect_ratio": "Portrait (implied by 'portrait' description)"
  },
  "scene_architecture": {
    "viewpoint": {
      "type": "Photographic",
      "angle": "High-angle / Looking down",
      "framing": "Tight on central subject"
    },
    "dimensional_hierarchy": {
      "rule": "Scale disparity for surreal effect",
      "dominant_element": "iPhone 17 Pro Max (Super-scaled)",
      "subordinate_elements": ["Blue Book (Miniature)", "Pen (Miniature)"]
    }
  },
  "realm_physical": {
    "description": "The real-world environment surrounding the device.",
    "environment": {
      "surface": "Wooden table",
      "texture_attributes": ["rich grain", "tactile", "worn"]
    },
    "lighting_global": {
      "source": "Natural light",
      "temperature": "Warm",
      "shadow_quality": "Soft, diffused, volumetric"
    },
    "active_agent": {
      "identity": "Human Hand (Real)",
      "action": "Pouring",
      "position": "Entering frame laterally"
    },
    "held_object": {
      "item": "Bottle",
      "state": "Chilled (visible condensation)",
      "branding": {
        "logo_text": "Decamin",
        "placement": "Visible on label"
      },
      "contents": {
        "substance": "Water",
        "color": "Light Green",
        "state": "Liquid flow"
      }
    },
    "static_props": [
      {
        "item": "Book",
        "color": "Blue",
        "scale_notes": "Significantly smaller than phone"
      },
      {
        "item": "Pen",
        "type": "Ballpoint/Ink",
        "scale_notes": "Significantly smaller than phone"
      }
    ]
  },
  "realm_digital": {
    "description": "The content displayed on the screen.",
    "container_device": {
      "model": "iPhone 17 Pro Max",
      "state": "Screen ON",
      "orientation": "Flat on physical surface"
    },
    "screen_content": {
      "subject_identity": "mqn (Reference ID)",
      "subject_scale": "Close-up (filling screen)",
      "expression": "Happy / Smiling",
      "attire": "Winter clothing (matching reference)",
      "setting": "Winter landscape / snowy backdrop",
      "held_object_digital": {
        "item": "Drinking Glass",
        "branding": {
          "logo_text": "Decamin",
          "visibility": "Clear"
        },
        "initial_state": "Empty (waiting for pour)"
      }
    }
  },
  "surreal_bridge_event": {
    "description": "The interaction connecting the physical and digital realms.",
    "action_type": "Trans-dimensional Fluid Dynamics",
    "source": "realm_physical.held_object.contents (Light Green Water)",
    "interaction_point": "realm_digital.container_device.screen_surface",
    "destination": "realm_digital.screen_content.held_object_digital (The Glass)",
    "physics_violation_rules": {
      "rule_1": "Liquid does not splash off the glass screen surface.",
      "rule_2": "Screen surface acts as a permeable membrane solely for this liquid.",
      "rule_3": "Physical liquid transitions seamlessly into digital representation upon contact."
    },
    "visual_details": ["Sharp liquid simulation", "No surface tension on screen glass", "Fluid physically filling digital cup"]
  },
  "rendering_specifications": {
    "visual_fidelity": "Hyper-realistic",
    "texture_focus": ["Sharp fluid details", "Glass pixels", "Wood grain", "Skin texture (hand and subject)"],
    "mood": "Cinematic, warm, magical",
    "resolution_target": "8K / Highly detailed"
  }
}

{
  "scene": {
    "environment": "sunny_boardwalk",
    "details": "wooden_planks, colorful_stalls, people_walking, distant_umbrellas",
    "lighting": "bright_midday_sun",
    "sky": "clear_blue"
  },
  "camera": {
    "lens": "ultra_wide_fisheye_12mm",
    "distance": "very_close_up",
    "distortion": "strong_exaggeration",
    "angle": "slightly_low_upward"
  },
  "subject": {
    "type": "young_person",
    "gender": "neutral",
    "expression": "curious_playful",
    "eyes": "large_due_to_lens_distortion",
    "pose": "leaning_forward_sipping_drink",
    "clothing": {
      "top": "bright_green_knit_sweater",
      "accessory": "chunky_blue_sunglasses"
    }
  },
  "drink": {
    "type": "iced_matcha_latte",
    "ice_cubes": "large_clear",
    "cup": "transparent_plastic",
    "straw": "green_white_spiral"
  },
  "effects": {
    "depth_of_field": "shallow_foreground_sharp_background_soft",
    "reflections": "glasses_show_boardwalk_and_people",
    "color_grade": "clean_natural"
  },
  "composition": {
    "focus": "face_extreme_closeup",
    "mood": "funny_intimate_casual",
    "background_elements": [
      "distant_people",
      "benches",
      "bright_shops"
    ]
  }
}

{
  "image_parameters": {
    "style": "Canon IXUS aesthetic",
    "type": "Point-and-shoot photography",
    "quality": "Hyper-realistic",
    "tone": "Sharp, direct",
    "lighting_and_atmosphere": "Realistic, flash-style/direct lighting"
  },
  "subject": {
    "constraints": {
      "facial_identity": "Match reference image exactly 100%",
      "face_edits": "None allowed"
    },
    "hair": {
      "style": "Long, natural, lightly messy layered look",
      "movement": "Blowing gently in the wind",
      "details": "Strands slightly covering part of face"
    },
    "makeup": {
      "cheeks_and_nose": "Soft pink blush with blurred effect",
      "lips": "Subtle pink-orange tinted outline"
    },
    "expression": [
      "Cute",
      "Naive",
      "Cheerful",
      "Slightly sexy/undone charm"
    ],
    "pose": {
      "body_position": "Half-sitting, half-standing",
      "action": "Flicking hair"
    },
    "clothing": {
      "top": "Black strapless top",
      "bottom": "Low-waisted jeans with a floating waistline",
      "neck": "Thin black fabric choker/wrap"
    },
    "accessories": [
      "Small pendant necklace",
      "Gold watch"
    ]
  },
  "environment": {
    "setting": "Modern pub",
    "foreground_props": [
      "Round table",
      "Bottle of liquor",
      "Glass of liquor"
    ]
  }
}

Generate a hyperrealistic realistic-anime portrait of a female character standing in a completely black background.
Lighting: use a **narrow beam spotlight** focused only on the center of the face. 
The edges of the light must be sharp and dramatic. 
All areas outside the spotlight should fall quickly into deep darkness 
(high falloff shadow), almost blending into the black background. 
Not soft lighting.
Hair: long dark hair with some strands falling over the face. The lower parts of the hair should fade into the shadows.
Pose: one hand raised gently to the lips in a shy, hesitant gesture. 
Eyes looking directly at the camera with a mysterious mood.
Clothing: black long-sleeve knit sweater; 
the sweater and body should mostly disappear into the darkness with minimal detail.
Overall tone: dark, moody, dramatic, mysterious. 
High-contrast only in the lit portion of the face. 
Everything outside the spotlight should be nearly invisible.