Nano Banana Pro
Prompts

Prompts updated daily

Prompts

1
BY@Studio Veco|日本一ダサい画像を生成する人
Dec 22, 2025

AI Agent Development 'Swamp' Diagram Prompt

AI Agent Development 'Swamp' Diagram Prompt

A detailed JSON-based prompt for Nano Banana Pro to generate a 'Swamp' diagram (a popular internet meme format) illustrating the circular nature of getting stuck in AI Agent development. The prompt defines the diagram's structure, style (simple, cute editorial), layout (straight intro track leading into a clockwise loop), and specific nodes with characters, visuals, and dialogue/thought terms.

Prompt
diagram: title: "The Cycle of the Generative AI Agent Development Swamp" style: character: "simple_editorial_cute" tone: "light_like_original" line: "soft_round" shading: "flat_minimal" palette: "muted_editorial" background: "light_beige_or_white" rule: first_character_only: "Only the first person is different" others_same_character: "All others are the same person" anxiety_requires_tech_terms: true dialogue_tone: "Maintain the short, light phrasing of the original diagram" layout: intro_track: "The upper section is a straight line (left to right), then drops down to join the loop" loop_track: "Arranged as a loop (ring), with arrows curving clockwise along the circumference" nodes: # ===== Upper Section: Straight Introduction ===== - id: A zone: "intro" position: "upper_left" actor: "Different person (Senior Engineer)" visual: "Pointing at a laptop" item: "AI Agent Demo Screen" says: "It'll make you happy." arrow_to: { id: B, shape: "straight", direction: "right" } - id: B zone: "intro" position: "upper_center" actor: "Protagonist (Same person)" visual: "Waving lightly" says: "Even a simple agent..." arrow_to: { id: C, shape: "straight", direction: "right" } - id: C zone: "intro" position: "upper_right" actor: "Protagonist (Same person)" visual: "Executing sample code" item: "LangChain / CrewAI Sample" arrow_to: { id: D, shape: "straight", direction: "down" } # ===== D: Awakening Point ===== - id: D zone: "connector" position: "right_outer_before_loop" actor: "Protagonist (Same person)" visual: face: "Eyes wide open (cute)" effect: "Small flash of inspiration line" posture: "Leaning forward" state: "Awakening" says: "Agents, this is insane..." micro_text: "(Wakes up here)" arrow_to: id: E shape: "gentle_curve" direction: "down_into_ring" # ===== Loop Start (Must rotate from here) ===== - id: E zone: "loop" position: "loop_right_upper" actor: "Protagonist (Same person)" visual: "Holding head in hands (cute)" state: "Anxiety/Irritation Begins" says: "Irritated" thought_terms: - "Prompt Design" - "Tool Selection" - "Memory Design" thought_text: "It's not working as intended..." arrow_to: { id: F, shape: "curved_along_ring", direction: "clockwise" } - id: F zone: "loop" position: "loop_right_lower" actor: "Protagonist (Same person)" visual: "Surrounded by code and logs" state: "Irritation Settles In" says: "In a state of irritation" callout: "Loop! Runaway! Hallucination!" thought_terms: - "RAG" - "Function Calling" - "Tool-Use" arrow_to: { id: G, shape: "curved_along_ring", direction: "clockwise" } - id: G zone: "loop" position: "loop_bottom" actor: "Protagonist (Same person)" visual: "Covered in sticky notes and diagrams" says: "The body gradually develops tolerance, and usage increases." items: - "Agent Architecture Diagram" - "Role Assignment Memo" - "State Transition Flow" arrow_to: { id: H, shape: "curved_along_ring", direction: "clockwise" } - id: H zone: "loop" position: "loop_left_lower" actor: "Protagonist (Same person)" visual: "Works well, small fist pump" state: "Temporary Satisfaction" says: "Desire is temporarily satisfied" arrow_to: { id: I, shape: "curved_along_ring", direction: "clockwise" } - id: I zone: "loop" position: "loop_left_upper" actor: "Protagonist (Same person)" visual: "Thinking again" state: "Obsession/Thought Occupation" says: "Thinking about the agent

Try These AI Skills Instead

Discover featured tools that can help you generate amazing content.

YouMind Style Background Image

Generate a YouMind brand style abstract image for background use. Font Guidelines: Use <Libre Baskerville> for English titles and <Source Sans> for Chinese titles.

YouMind Style Background Image

Infographic Maker

Say goodbye to the hassle of manually creating charts. Simply provide your structured data, and Infographic Maker can generate high-quality PNG infographics with a single click. It features 6 built-in chart types (timeline, flowchart, leaderboard, scale chart, comparison chart, funnel chart) and 5 meticulously crafted visual styles (Business Blue, Creative Color, Dark Tech, Elegant Warm, Minimalist Black and White), easily covering all scenarios from annual reports to social media. Supporting Instagram Stories (9:16), Feed (4:5), and Square (1:1) sizes, it lets your data speak for itself.

Infographic Maker

Data Visualization

Generate visualizations based on user-provided data that conform to the Storytelling with Data (SWD) principle. Triggering conditions: This skill must be used when a user provides data and requests "draw a chart," "generate a chart," "visualize," "make a graph," or "show me this data," or uploads CSV/Excel/spreadsheet data and wants to see a graphical representation. Even if the user only says "analyze this data" and the data is suitable for visualization, this skill should still be used to generate a chart.

Data Visualization

Every Classic-Modern Conflict Cover

The article's core ideas are transformed into a visual impact. The collision of classical engraving and modern symbols creates the Every.to-style cover, characterized by dark emphasis, high contrast, wordless composition, and a strong sense of artistry.

Every Classic-Modern Conflict Cover

Romantic rendering of portrait images

Transform ordinary portrait photos into a 3D cartoon style depicting a tranquil sunset under cherry blossom trees. Supports single or multiple photos (multiple photos will be merged), outputting 4K high-definition images using the Nano Banana 2 model, presenting a serene atmosphere with backlit silhouettes.

Romantic rendering of portrait images

glance

A cover generator designed for high click-through rates. Based on article content analysis and hook strategies, it identifies authentic brand identities and generates covers that stand out in the news feed. Core principles: grab attention in 3 seconds, prioritize authentic brands, and drive clicks through emotional resonance. It judges the optimal combination of text and visuals from the perspective of top cover designers.

glance
View All Skills

Common Questions

Nano Banana Pro is Google's latest multimodal AI model featuring multimodal understanding (text, images, and video), high-quality generation from photorealistic to artistic styles, fast iteration with quick edits and variations, diverse styles from pixel art to oil paintings, precise control over composition and lighting, and complex multi-object, multi-character scene rendering.
They are curated mainly from public Twitter/𝕏 sources. If you are the author and wish to opt out, please contact us for immediate removal.
Simply copy the prompt and use it in YouMind with the 'Nano Banana Pro' image generation model according to the description. We are working on a tighter integration for one-click usage in the future.
It helps you consolidate your content creation and learning best practices into YouMind Shortcuts. This enables one-click generation based on your materials—like turning a YouTube video into a blog post or extracting quotes from an article.
Check out our blog post Nano Banana Pro Hands-On: 10 Mind-Blowing Real-World Cases for more curated Nano Banana Pro examples.

Ready to create with
Nano Banana?

Experience Nano Banana Pro's Powerful Capabilities
LET YOUR IMAGINATION SOAR

Start Generating