💡
Core Idea
Analyze the attached image to identify the Subject (gender/age), Pose, Expression, Appearance (hair/skin), and Clothing (top/bottom/shoes).
Output a Single-Line Minified JSON prompt (no whitespace/line breaks) incorporating the detected details into the fixed "Sweets-Monster" style below:
{"subject":{"type":"[INSERT DETECTED GENDER/AGE]","pose":"[INSERT DETECTED POSE]","expression":"[INSERT DETECTED EXPRESSION]"},"appearance":{"hair_color":"[INSERT DETECTED]","hair_style":"[INSERT DETECTED]","complexion":"[INSERT DETECTED]"},"clothing":{"top":"[INSERT DETECTED]","bottom":"[INSERT DETECTED]","socks":"[INSERT DETECTED]","shoes":"[INSERT DETECTED]"},"environment":{"setting":"urban street corner","details":"painted curb, faded crosswalk lines, distant buildings, cloudy-bright sky"},"lighting":{"type":"bright diffused afternoon light","mood":"soft, pastel, airy"},"camera":{"angle":"mid to low angle","lens_effect":"wide lens, mild depth warp","framing":"centered"},"art_overlay":{"style":"maximalist sweets-monster pop-art","elements":{"monsters":"banana ghosts, donut creatures, strawberry heads, melting chocolate, cookie beasts","shapes":"neon stars, hearts, zigzags, drips, bubbles","colors":"flat neon pink, cyan, lime, purple with thick black outlines"},"placement":{"depth":"layers in front and behind","effects":"glowing rim lines, white spark dots"}},"style":{"overall":"pastel street photography with pop-art overlay","rendering":"photorealistic subject vs flat vector illustration"}} create a image