Ai Image Prompts

Do this for {argument name="City/Year A vs. City/Year B" default="New York 1700 vs New York 2025"}

<instructions>
Input Variable: [City/Year A vs. City/Year B] (e.g., New York 1900 vs. New York 2025)

System Instruction:
Generate a photorealistic, isometric macro render of a split-era urban diorama. The goal is Historical and Municipal Accuracy, avoiding sci-fi tropes or idealization.

1. Temporal Forensic Analysis:
Analyze the Dates:
 Strictly adhere to the architectural technologies available in Year A versus Year B.
The Left Block (The Past): Construct the Left side using the dominant vernacular of the era.
For 1900: Beaux-Arts stone, brick tenements, water towers, external fire escapes, and cobblestone/early asphalt.
The Right Block (The Present/Future): Construct the Right side using current urban realities, not futuristic fantasies.
For 2025: Prioritize "Super-Slender" Pencil Towers (Billionaire's Row style), Glass Curtain Walls mixed with preserved older facades, and "Hudson Yards" style angled steel.
  Crucial Detail: If the year is modern (2020+), you MUST include Urban Clutter: Green construction plywood barriers, sidewalk scaffolding (sheds), steam vents, and delivery trucks.

2. The Container (The Cross-Section):
The Base: Two suspended chunks of city infrastructure, revealing the "Underground" layer on the side profile.
Left Underground: Brick sewers and early subway tunnels.
Right Underground: Concrete conduit banks, fiber optic lines, and modern subway tiles.
The Divider: A jagged timeline fracture. No glowing sci-fi energy. The divide is a stark cut in the asphalt.

3. The Composition (The Density):
Left Street Life: Period-accurate transport (Horse-drawn carriages mixed with early Model T Fords or Trolleys). Pedestrians in dark coats/hats.
Right Street Life: Municipal Realism. Yellow Taxis, Amazon delivery vans, Uber cars, and bike lanes with cyclists. The street level should feel congested and chaotic.
Vegetation: Left has Elm trees (if applicable); Right has manicured "Corporate Plaza" planters and rooftop gardens.

4. Accurate Lighting Simulation (No "Neon Filters"):
Left Lighting: Carbon-Arc and Gaslight. The light should be dim, patchy, and warm (2400K), casting long shadows.
 Right Lighting: Mixed Municipal Lighting. A chaotic mix of warm sodium streetlights (orange), harsh white LED construction lights (6000K), and internal office lighting (neutral). Do not use "Cyberpunk Blue" or "Purple" unless it is a specific billboard.
Atmosphere: The Left is hazy from coal smoke. The Right has a clearer, sharper air quality but with light pollution.

5. Visual Syntax:
Camera: Isometric Orthographic projection, 45-degree angle.
Render Style: Photorealistic Architectural Visualization (ArchViz), 8k, V-Ray Render. Focus on texture fidelity (rust, wet pavement, grime) rather than bloom effects.

Output: 1:1 Aspect Ratio, Extreme Detail, Historically Authentic.

Transform the burger into a clean exploded-view composition.
The burger is separated into exactly five layers, floating vertically with even spacing:

Brioche bun

Beef patty

Melted cheese

Fresh lettuce

Ripe tomato

Each layer remains photorealistic and aligned, maintaining the original proportions from the hero shot.

Add minimal, clean annotations with thin lines and clear typography, describing benefits:

Brioche bun — {argument name="bun benefit" default="soft texture, lightly toasted finish"}

Beef patty — juicy, rich flavor, perfectly seared

Melted cheese — creamy melt, enhances savoriness

Fresh lettuce — crisp bite, freshness balance

Ripe tomato — natural sweetness, juicy contrast

Background remains the same, slightly darkened to ensure maximum annotation readability.
Lighting stays consistent with the first image for visual continuity.
Commercial, technical, clean, easy to understand at a glance.

[Role]
You are a professional graphic designer. Create a YouTube thumbnail.

[Composition Instructions]
- Split-screen composition, dividing the screen into left and right halves.
- Left side: A Japanese woman with a surprised expression (photorealistic style). Background is a dark office.
- Right side: A vibrant yellow background. Place the text “{argument name="text" default="AI Revolution"}” in bold Gothic font in the center.
- Ensure sufficient negative space around the text to maximize visibility.

[Style]
A scene from an animated movie, cyberpunk

[Camera and Composition Settings]
- Lens: Use a wide-angle lens (24mm equivalent) to emphasize perspective.
- Angle: Extreme low angle (worm's-eye view). The character is viewed looking up from just above the ground.
- Placement: Place the character's left hand directly in front of the camera to exaggerate the sense of distance.
- Background: High-rise buildings sharply converge toward a vanishing point.

[Role]
You are a manual creator. Create {argument name="subject" default="how to make Okonomiyaki"}.

[Format]
Flat design infographic, 16:9

[Layout Instructions]
- A “3-step” process diagram flowing from left to right.
- Step 1 (Left): Magnifying glass icon (Investigation).
- Step 2 (Center): Gear icon (Processing).
- Step 3 (Right): Light bulb icon (Solution).
- Connect each element with arrows and align them at equal intervals.
- Background is white, icons are unified in blue and orange key colors.

An ultra-wide, surreal, 9:16 overhead flat lay photograph. A group of 4 [{argument name="characters" default="characters"}] are seated around a square table, one person on each side. The camera is pulled back significantly to create a large amount of negative space (empty floor area) around the people and the table, ensuring a clean, minimalist composition.

The scene is [{argument name="scene" default="scene"}]: [Characters] are wearing their classic costumes, and their interaction is as follows: [DESCRIBE ACTION OF EACH PERSON]

The table is a custom physical prop, designed to look like a WeChat Moments post: with solid white bands only on the top and bottom edges (no white borders on the left and right sides).
- The top white band features a personal profile picture, with a [{argument name="LOGO DESCRIPTION" default="a cool poker avatar or real photo"}], the username “[USERNAME]” is drawn on the right, followed by the posting time text (e.g., “1 hour ago” or “Just now”), and the “...” more options icon on the far right.
- The bottom white band features a right-pointing arrow “Comment” icon (with a bubble shape) and a “Like” icon (WeChat's characteristic thumbs-up icon, which can be designed as gray unliked or red liked) on the right side, separated by a vertical line; the far left or middle can be left blank or include a small location icon (if location is tagged).

The center of the table is painted [EXACT CENTER COLOR & HEX CODE], and the objects on the table are [FOOD/OBJECTS DESCRIPTION].
Important: All objects and hands interacting with them are strictly confined to this central [COLOR] painted area. Nothing should extend onto the white bands or beyond the table boundaries. The floor background is [FLOOR COLOR, e.g., minimalist clean solid color] to create visual separation. Professional studio lighting with distinct cast shadows. 8K, sharp focus.

create a sketch of a hand-drawn drawing with lines on notebook paper, doodles, and arrows identifying each item of clothing

You are a professional persona designer. Based on the following information, please design a detailed persona.

**Target Audience:** {argument name="target audience" default="Women in their 30s, living in the city center, working at an IT company"}
**Objective:** {argument name="objective" default="Developing a marketing strategy for a new beauty serum"}

**Elements to include in the persona:**
1. Basic information (Name, Age, Occupation, Residence, Family structure)
2. Personality and Values
3. Lifestyle (Daily routine, Hobbies, Information sources)
4. Challenges and Needs (Beauty concerns, Desired solutions)
5. Goals and Motivation
6. Purchasing behavior (Points of emphasis, Budget range, Purchase channels)
7. Touchpoints with the service/product (Usage scenarios, Expected effects)

**Output format:**
- Use appropriate headings for an easily readable structure.
- Include specific descriptions that could be used for a persona image.

You are an expert in infographics. Read the article or report provided by the user and automatically generate a visually clear and attractive infographic that summarizes its content. Specifically, please create it considering the following elements:

### Objective
To visualize the main message, key data, process, or structure of the article or report so that it can be understood at a glance.

### Style and Tone
*   **Style**: A hand-drawn or minimal and sophisticated diagram style, similar to Napkin AI.
*   **Tone**: Professional yet approachable and visually appealing.

### Components
1.  **Title**: An attractive title that concisely represents the article's theme.
2.  **Key Points**: 3 to 5 of the most important points extracted from the entire article.
3.  **Diagrams**: Graphs, flowcharts, icons, or conceptual diagrams to represent the key points or processes.
4.  **Data**: If there are specific numbers or statistical data in the article, display them in an emphasized manner.
5.  **Conclusion/Action**: A summary of the article or the next action expected from the reader.

### Output Format
Based on the content of the provided article, output the overall image of the infographic, integrating the above components, as detailed instructions. Describe the diagram ideas, layout suggestions, and the image of the colors and fonts to be used specifically.

### Article/Report
{argument name="Content of the Article or Report" default="[Paste the full text of the article or report here]"}

Analyze: Determine the scientist responsible, the specific era, and the visual diagrams associated with the theory. Goal: A Macro Diorama on a Laboratory Bench. A messy, highly detailed flat-lay of a historical workspace that serves as a giant landscape for a living miniature version of the scientist. Centerpiece: An open, antique notebook lying flat. The pages must be visible and filled with specific handwritten equations and diagrams relevant to the Input Theory. Sitting directly on top of these open pages is a tiny, hyper-realistic figurine of the scientist sitting at a proportionally tiny wooden desk, working on the very notes beneath him. Surroundings: The environment is cluttered with giant-scale period-accurate objects that relate to the scientist's work. This includes a newspaper from the era acting as a backdrop, a giant coffee mug leaving stains, and massive scientific tools relevant to the theory (such as compasses, lenses, or pocket watches) scattered like terrain. Perspective: Slightly angled 45-degree macro shot looking down at the notebook. Texture: Wood grain, scratched metal, paper texture, dust particles. Lighting: Warm, late-night library lamp lighting creating a spotlight on the tiny scientist and deep shadows behind the giant props. Output: one image, 4:5 aspect ratio, photorealistic historical macro photography.

Input A: {argument name="concept" default="calculus"}
Input A is a technology that traveled historical trade routes (papermaking, gunpowder, astronomy, silk production, algebra, etc.).
Analyze: origin civilization, the journey route, cultural adaptations at each stop, timeline of spread.
Goal: Miniature Silk Road/trade route caravan scene showing technology being transported and transformed.
Rules:
- Base: 3D topographic map showing actual historical route (mountains, deserts, seas)
- Caravan: 8-12 miniature merchant/scholar figurines progressing along route with pack animals
- Each stop: micro-diorama of how that civilization adapted the technology
  * Origin point: technology in pure form with inventor culture's aesthetic
  * Midpoint stops: hybrid versions showing cultural fusion
  * Destination: fully transformed/adapted version
- Include: the technology itself transforming—paper becoming different textures, numbers changing symbol systems, etc.
- Obstacles: miniature barriers that were overcome (mountain passes, hostile territories, language barriers shown as scroll fragments in different scripts)
- Time markers: seasons/years labeled along route
- Materials: actual sand/terrain materials, tiny textiles from different cultures, brass caravans
- Lighting: journey from dawn (origin) to dusk (destination) across the scene
Output: ONE image, 21:9 ultra-wide to capture full journey, epic historical adventure photography

Single large horizontal blueprint sheet, 16:9 aspect ratio, showing the complete evolutionary journey of **{argument name="invention name" default="[INVENTION]"}** from its first concept to its modern form, presented as a technical blueprint coming to life.
Authentic aged blueprint paper with white technical lines on deep blue background, subtle coffee stained edges and worn paper texture. Forced perspective across the page from left to right.
Left side shows the original patent era design of **{argument name="invention name" default="[INVENTION]"}** as a pure flat 2D technical line drawing, precise drafting style, no depth. Inventor figure on the far left also drawn fully in 2D blueprint line art.
Gradual transformation across 7 to 9 clearly separated stages moving rightward: Stage 1 pure technical line drawing. Stage 2 blueprint lines beginning to lift off the page with a paper craft effect. Stage 3 partial miniature model emerging from the blueprint. Stage 4 fully formed 3D miniature model, unpainted. Stage 5 painted miniature with realistic materials. Final stage shows a photo realistic tiny working version of **{argument name="invention name" default="[INVENTION]"}**.
The inventor figure evolves in parallel from flat 2D drawing on the left into a fully 3D miniature figurine on the right, matching the same transformation stages.
Each stage labeled with technical annotations, measurement markings, arrows, and small evolution dates in blueprint drafting style typography.
Drafting tools including compass, protractor, mechanical pencil, ruler, and T square interacting with the flat blueprint areas, while the 3D sections break free from the page.
Lighting transitions from cool LED blueprint table backlight on the left to realistic practical lighting on the right, emphasizing depth and realism.
Ultra detailed technical illustration meets practical effects, high realism, clean composition, museum quality concept visualization.

Create a beautiful visual comparison chart that matches these 10 eras/ages of human civilization with Taylor Swift’s 10 Eras Tour albums. For each pairing, explain and show why the aesthetic and mood match. The 10 Ages: Stone Age, Bronze Age, Iron Age, Classical Antiquity, Medieval, Renaissance, Age of Exploration, Industrial Revolution, Space Age, Digital Age

Exploded view of the same taco, presented as a clean, commercial recipe-style breakdown.
Exactly five ingredients, matching the first image, separated and arranged vertically from top to bottom, evenly spaced and perfectly aligned.

Ingredient order (top → bottom):

Fresh tomato salsa — 40 g

Shredded cheddar cheese — 30 g

Grilled chicken pieces — 80 g

Crisp lettuce — 25 g

Soft wheat taco tortilla — 60 g (bottom base)

Add clear infographic-style annotations for each ingredient.
Each annotation includes the ingredient name and its exact weight in grams, written exactly as listed above.

Annotation design guidelines:
– Clean sans-serif font, medium weight
– Text placed inside minimal frames or boxes
– Thin, precise connector lines pointing directly to each ingredient
– High readability, no overlap, no decorative excess
– Structured vertical layout, like a modern recipe card

Background is light, neutral, and optimized for text clarity and visual cleanliness.
Overall style is minimal, instructional, and commercial, suitable for marketing, explainer visuals, and product breakdowns.