Nano Banana Pro
Prompts

Prompts updated daily

Prompts

1
BY@John
Feb 2, 2026

Advanced JSON Prompt for Wong Kar-wai Style Portrait with Strict Face Restoration

Advanced JSON Prompt for Wong Kar-wai Style Portrait with Strict Face Restoration

An extremely complex JSON prompt designed to generate a portrait in the moody, cyan-green Wong Kar-wai aesthetic, featuring two subjects on a motorcycle. Crucially, the prompt includes detailed instructions for 'CRITICAL FACE RESTORATION' for both a male (Reference Image 1) and a female (Reference Image 2) subject, requiring 100% identity preservation of specific facial features (shape, eyes, nose, hair, etc.) while ignoring their original clothing. This is a highly technical prompt focused on identity preservation and specific cinematic styling.

Prompt
{ "prompt": "Wong Kar-wai moody color palette dominated by heavy cyan-green tones (95–98% green/teal diffusion), Rembrandt chiaroscuro lighting, intense film grain, high ISO noise, low-res DV camcorder aesthetic, strong motion blur, double-exposure tunnel trails. Voyeuristic tight shot with heavy foreground occlusion, mirror reflections, frame-in-frame feel. Ultra-wide 18–24mm lens, extreme close-up (faces only 2–4 cm from lens), wildly exaggerated perspective — heads dramatically larger than distant elements. Long dark road tunnel background filled with massive blurred linear light streaks (mostly vivid green + trace pale yellow), heavy long-exposure smear.\n\nCRITICAL FACE RESTORATION - MALE (Reference Image 1):\n28-year-old male with EXACT facial features from reference image 1:\n- Face MUST be 100% identical to reference image 1\n- Face shape: [exact shape from ref img 1]\n- Eyes: [exact eye shape, size, eyelid type, spacing, color from ref img 1]\n- Eyebrows: [exact shape, thickness, arch from ref img 1]\n- Nose: [exact bridge height, tip shape, nostril width from ref img 1]\n- Mouth: [exact lip shape, thickness, width from ref img 1]\n- Jawline: [exact jaw shape, chin shape from ref img 1]\n- Skin tone: [exact color/undertone from ref img 1]\n- Hair: [exact hairstyle, color, texture, length from ref img 1]\n- Facial hair: [exact stubble/beard pattern from ref img 1]\n- Distinctive features: [moles, scars, unique marks from ref img 1]\n- ZERO deviation from reference image 1 allowed\n- Smooth youthful skin matching reference texture\n- Hong Kong-style celebrity aesthetic\n- Intensely staring forward while actively riding and controlling motorcycle\n- NO clothing/outfit details from reference image 1 - ignore reference clothing entirely\n\nCRITICAL FACE RESTORATION - FEMALE (Reference Image 2):\nWoman with EXACT facial features from reference image 2:\n- Face MUST be 100% identical to reference image 2\n- Face shape: [exact shape from ref img 2]\n- Eyes: [exact eye shape, size, eyelid type, spacing, color from ref img 2]\n- Eyebrows: [exact shape, thickness, arch from ref img 2]\n- Nose: [exact bridge height, tip shape, nostril width from ref img 2]\n- Mouth: [exact lip shape, thickness, width from ref img 2]\n- Jawline: [exact jaw shape, chin shape from ref img 2]\n- Skin tone: [exact color/undertone from ref img 2]\n- Hair: [exact hairstyle, color, texture, length from ref img 2]\n- Makeup: [exact makeup style from ref img 2 if any]\n- Distinctive features: [moles, beauty marks, unique marks from ref img 2]\n- ZERO deviation from reference image 2 allowed\n- Seated directly behind male on motorcycle rear seat\n- Arms tightly wrapped around his waist in close embrace\n- Face pressed intimately against his shoulder/back\n- NO clothing/outfit details from reference image 2 - ignore reference clothing entirely\n\nCLOTHING & STYLING (ORIGINAL PROMPT - NOT FROM REFERENCES):\n- Male: Casual contemporary "

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