Nano Banana Prompt

What it does

The Nano Banana Prompt skill helps you craft highly detailed and effective prompts for large language models, particularly when generating images. It specializes in creating prompts that achieve photorealistic rendering, maintain consistent facial features across transformations (identity preservation), handle complex compositions with multiple subjects, and incorporate precise technical specifications like camera settings and lighting setups. The skill provides structured approaches using both text-based and JSON prompt formats to maximize control over the output.

When to use it

• Generating photorealistic images: When you need highly detailed and realistic visuals.
• Maintaining facial consistency: When transforming an image while ensuring the person's face remains recognizable.
• Creating complex scenes: For prompts involving multiple subjects, layered effects, or specific era aesthetics (like Y2K).
• Requiring technical precision: When you need to control camera settings, lighting, and other photographic elements.

Key capabilities

• Photorealistic rendering: Generates prompts for realistic textures, lighting, and materials.
• Identity preservation: Maintains facial features across image transformations.
• Complex composition handling: Supports multiple subjects and detailed environments.
• Technical precision control: Allows specification of camera specs, lighting setups, and era aesthetics.
• Text-based prompt generation: Provides a structured text format for simpler prompts.
• JSON prompt generation: Enables precise control over complex scenes through JSON formatting.
• Hybrid Prompting: Combines narrative descriptions with technical specifications.

Example prompts

• "A professional, high-resolution profile photo, maintaining exact facial features of the uploaded image. Shot from chest up with ample headroom, looking directly at camera. Smart casual blazer in charcoal gray. Solid neutral studio background (#562226). Bright airy lighting with catchlights in eyes. 85mm f/1.8 lens, shallow depth of field, crisp focus on eyes, soft bokeh."
• "Create a scene with multiple subjects: a cyberpunk hacker and a futuristic robot bartender. The hacker is wearing neon-lit clothing; the robot has intricate mechanical details. Use JSON to specify element placement and lighting conditions."
• "Keep the facial features of the person in the uploaded image exactly consistent. Dress them in a professional navy blue business suit with..."

Tips & gotchas

• Specificity is key: Detailed prompts yield significantly better results than brief ones.
• Use technical language: Incorporate photography and cinematography terminology for greater precision.
• JSON Structure Guide: Refer to the JSON Structure Guide for templates when constructing complex, structured prompts.