Astorie Logo

Normal and depth map generation prompts for Nano Banana Pro

Normal and depth map generation prompts for Nano Banana Pro — output 1
Normal and depth map generation prompts for Nano Banana Pro — output 1

Generated output: Normal and depth map generation prompts for Nano Banana Pro — output 1

Two English prompts for Nano Banana Pro to generate a tangent-space normal map and a physically plausible depth map from an input artwork image, suitable for 3D-style viewing via WebGL or Three.js.

Prompt

1,116 charactersOpen Astorie studio ↗
Generate a surface normal map from the input artwork image.

Output one RGB image where each pixel encodes the surface normal direction in standard tangent-space format:
• R = X direction
• G = Y direction
• B = Z direction

Requirements:
• Maintain the same resolution and aspect ratio as the input image.
• Normal directions must follow the local geometry implied by brush strokes, shading, and contours.
• Do NOT add new artistic elements or repaint the scene.
• Only infer plausible micro-geometry and surface orientation.
• Ensure smooth, consistent normal transitions without noise.

Generate a depth map from the input artwork image.

Output a single grayscale depth map where:
• White = near to the viewer
• Black = far from the viewer

Requirements:
• Maintain the same resolution and aspect ratio as the input image.
• Depth must be smooth, continuous, and physically plausible.
• Infer only geometric depth that could reasonably exist in the original artwork.
• Do NOT add new objects or details.
• Do NOT stylize, repaint, or reinterpret the scene.
• Avoid texture noise; focus solely on depth structure.
From sourceView source ↗

About

The source requires reference images. Confirm input files before use.

More to explore

Cozy Tech Bedroom Portrait Generation Prompt — output

Cozy Tech Bedroom Portrait (JSON Format)

Melisa♡Nano Banana Pro
{
  "meta": {
    "title": "Cozy Tech Bedroom Portrait",
    "version": "1.0",
    "intent": "Photorealistic Social Media/Lifestyle"
  },
  "generation_params": {
    "aspect_ratio": "4:5",
    "width": 1024,
    "height": 1280,
    "seed": -1,
    "steps": 25,
    "cfg_scale": 7.0
  },
  "prompt_components": {
    "subject": {
      "description": "Girl from reference, matching face exactly",
      "hair": "{argument name=\"hair color and style\" default=\"Wet silver grey hair\"}",
      "makeup": "Natural soft-glam makeup",
      "expression": "Subtle smile"
    },
    "apparel": {
      "clothing": "{argument name=\"clothing\" default=\"Oversized white t-shirt\"}",
      "accessories": "None"
    },
    "pose_and_action": {
      "body_position": "Sits cross-legged on a bed",
      "interaction": "Laptop in front of her",
      "vibe": "Relaxed cozy pose"
    },
    "environment": {
      "setting": "Nighttime bedroom",
      "background_elements": "Dark curtains",
      "atmosphere": "Modern cozy-tech vibe"
    },
    "technical_specs": {
      "lighting": "Dim ambient lighting, soft harsh flash on face",
      "color_grading": "Muted warm tones",
      "camera_effects": "Gentle film grain",
      "render_quality": "Ultra-realistic, realistic skin texture, clean complexion, crisp detailed rendering"
    }
  },
  "full_concatenated_prompt": "Ultra-realistic nighttime bedroom photo of the same girl from the reference, matching her face exactly, with wet silver grey hair and natural soft-glam makeup. She sits cross-legged on a bed with a laptop in front of her, wearing an oversized white t-shirt. Relaxed cozy pose, subtle smile. Dark curtains, dim ambient lighting, soft harsh flash on her face, gentle film grain, muted warm tones. Modern cozy-tech vibe, realistic skin texture, clean complexion, crisp detailed rendering.",
  "negative_prompt": "different face, deformed limbs, messy background, overexposed flash, incorrect laptop text, distortion"
}
Try this prompt ↗

Find your next direction

ASTORIE CANVAS

Take the idea further.

Bring your prompts, references and results together in one creative space.

Open your canvas ↗