Back 中文 CC Prompt Galaxy
{ "generation_request": { "meta_data": { "tool": "Nano Banana 2", "task_type": "tokyo_ramen_bar_giant_bowl_cl… - AI prompt reference from CC Prompt Galaxy

Playful girl close-up at colorful Tokyo ramen bar AI Image Prompt

Prompt

Use the reference woman exactly. Place her inside a colorful Tokyo ramen bar. The image should feel playful, candid, close-up, and delicious, with the ramen bowl exaggerated in the foreground for depth. She has dark hair in two playful braided pigtails or soft twin braids with loose strands, small red ribbon ties or tiny sakura clips, fresh dewy skin, rosy blush, soft eyeliner, glossy pink lips, wearing a cute casual Tokyo food-date outfit: fitted white baby tee or soft pastel top with light cardigan, playful but stylish, small hoop earrings, delicate rings, glossy manicure. She leans toward a giant ramen bowl close to the camera, smiling or eyes closed while holding chopsticks, with realistic chopstick grip, natural fingers. The environment is a colorful Tokyo ramen bar interior with paper lanterns, menu posters, warm lights, cozy counter seating. Background: vibrant walls and lanterns softly blurred, no readable text. Lighting: direct flash mixed with warm pink-orange restaurant lighting. Mood: playful, delicious, colorful, candid, youthful Tokyo food nightlife. Camera: 24mm wide food-lifestyle lens, slightly low close-up angle with ramen bowl dominating foreground, close portrait with oversized ramen foreground depth, sharp on ramen and face, slight wide-angle depth, moderate depth of field with warm bokeh. Negative prompt: messy ramen, fake noodles, deformed chopsticks, bad hands, different woman, identity drift, readable. Additional settings: aspect ratio 4:5 portrait, photoreal flash food lifestyle editorial, ultra crisp, subtle flash film grain, warm red pink lantern yellow color grade.

AI Image Content Analysis

Content: Subject: reference woman; Setting: colorful Tokyo ramen bar; Style: playful, candid, close-up, delicious; Composition: ramen bowl exaggerated in foreground for depth; Details: hair (braided pigtails/twin braids with accessories), makeup (dewy, rosy blush, glossy pink lips), outfit (white tee + cardigan), action (leaning forward, holding chopsticks); Environment: paper lanterns, menu posters, warm lights; Lighting: direct flash mixed with warm pink-orange restaurant light; Lens: 24mm wide low-angle close-up; Aspect: 4:5 portrait; Negative: avoid messy, deformed, identity drift.

Pros: ① Specific visual details (hairstyle, makeup, outfit, pose) for accurate generation; ② Clear lens and lighting instructions (24mm wide, flash mixed with warm light) giving controllable atmosphere.

Cons: ① Heavy reliance on reference image of the woman, risk of inconsistency without it; ② Prompt is lengthy with some redundant cues (e.g., 'playful' repeated).

Reference image: Explicit reference-image dependency

Author
Özge Döner
Type
Image
Aspect ratio
9:16
Size
670 × 1200
Added
2026-06-20

Source materials are collected from publicly accessible web pages. Contact us if a rights issue needs review. Copyright & Privacy