Clean Ink Zen Memory

Delivery and mode selection

• Produce one standalone 3:4 vertical poster per source image. Never combine photos.
• Offer two modes when the user has not already chosen:
  1. Split comparison — contemplative real photography above, clean ink reconstruction below.
  2. Full canvas — the whole poster becomes a clean ink memory study.
• Use one mode for all uploaded photos unless the user maps modes per image.
• Read only the selected guide: split-comparison.md or full-canvas.md.
• Return a ready-to-use prompt only when explicitly requested; otherwise use the available image generation or editing capability.

Shared visual rules

Use the source as the only content reference. Preserve subject identity and count, pose, proportions, direction, defining structure, occlusion, and core spatial relationships. Select the strongest visual anchor and remove only nonessential clutter.

Build the image with saturated pure-black liquid ink shapes for the core, a few economical variable ink lines, and controlled small round ink dots for intermediate values and edge recession. Every dot must be crisp and intentionally placed. Marks may occur only within the subject and its necessary extension; all untouched paper must remain bright, even, and pristine.

The visual sequence is solid ink form to controlled stipple to clean paper white. Never imitate charcoal, graphite, powder, rubbing, dirty paper, ink splash, broad wash, random specks, gray fog, or digital pixelation.

Tiny editorial text is optional only when the user wants it. Lock a truthful 1–6-word English observation before rendering; never copy reference wording or invent a place, date, or relationship.

Avoid

Charcoal or pencil texture, dusty shading, smudges, stains, aged paper spots, random ink debris, full-canvas grain, dry brush, ink splash, uniform dot screens, mosaic or pixel effects, photo halftone filters, blur, transparent fades, large titles, signatures, logos, QR codes, garbled text, and watermarks.