GPT Image Prompt
VISUAL ATTACK:
Background: Warm off-white background covers 68%, flat and clean, with oversized matte-black letterforms cutting across the left and center background.
Color blocks: Warm off-white 68%, matte black 22%, cool gray 6%, signal red 4%.
Accent: Signal red under 4%, used only on tiny issue marks, micro labels, and one small underline.
Subject scale: Full-body subject, 92% image height, placed center-right.
Hero hook: The long black flared-pants silhouette and the coffee-cup-in-hand read first; face reads second; the slim white turtleneck torso reads third.
Typography: Giant condensed background type occupies the left 32% and partially overlaps behind the torso; one thin vertical title spine runs down the far right edge; micro editorial text stays near the waist and lower-left corner.
Layout grammar: L03 Giant Background Type + L12 Vertical Title Spine; negative space stays upper-left and lower-left; eye path goes giant type → face → white turtleneck torso → coffee cup → flared pant line.
Contrast: Hard graphic contrast.
Surface: Glossy campaign print with subtle magazine grain.
Text role: Layout structure + branding.
PROMPT:
Create a high-impact typography-led fashion campaign poster using the uploaded woman as the core visual reference. Keep her as a beautiful adult Asian woman with long wavy black hair, soft bangs, calm direct gaze, and an elegant but approachable fashion presence. Preserve the core styling hook: fitted white turtleneck long-sleeve top, black high-waisted flared pants, slim black belt, small black shoulder bag, black pointed shoes, and a takeaway coffee cup in one hand. Keep the pose fashion-clean: one hand lightly touching her hair, legs crossed in a long elegant line, body slightly angled, full-body visible.
This must feel like a true Typography-Led Campaign, not a plain portrait. Use layout grammar L03 Giant Background Type combined with L12 Vertical Title Spine. The background is warm off-white covering about 68% of the poster, with huge matte-black condensed letterforms filling roughly the left 32% and partly slipping behind the subject. Add a narrow vertical title strip on the far right edge. Use short readable title logic only, such as “MONO SHIFT” or similarly clean campaign wording, and keep all secondary text minimal and controlled. Add a few tiny editorial issue marks and micro labels only near the waist and lower-left zone; no dense paragraphs, no random gibberish.
The subject should occupy about 92% of image height and stand center-right, with the strongest one-second read being the black flared-pants silhouette against the light ground. The white top must create a clean contrast anchor. Use color coverage: warm off-white 68%, matte black 22%, cool gray 6%, signal red 4%. Red is a strict accent only for tiny marks and a subtle underline. Focal path: giant type → face → torso → coffee cup → pant flare. Keep the cylindrical minimalist studio architecture reduced into a clean neutral campaign space, not a realistic room. Surface should feel like glossy coated fashion print with slight magazine grain, refined edges, strong hierarchy, crisp silhouette, polished but not generic, highly saveable.
NEGATIVE PROMPT:
generic fashion photo, boring realistic portrait, stock photo look, default poster template, weak typography, random text everywhere, unreadable gibberish paragraphs, muddy beige palette, low contrast, centered flat composition, no hierarchy, weak silhouette, no giant type, oversized cluttered labels, cheap social-media graphic, messy background, over-detailed room, cinematic realism drift, bad anatomy, distorted hands, broken fingers, warped coffee cup, deformed shoes, face distortion, over-retouched skin, plastic skin, species drift away from typography-led campaign
How to use: Copy and paste this prompt into ChatGPT, Gemini, Nano Banana, or your favorite AI image tool. If it mentions LoRA, reference image, uploaded photo, or identity reference, upload your own photo first. No reference photo? Replace the character with a clear age, gender, and nationality, such as “25-year-old Japanese woman” or “30-year-old American man”.
Nanobanana Prompt
How to use: Copy and paste this prompt into ChatGPT, Gemini, Nano Banana, or your favorite AI image tool. If it mentions LoRA, reference image, uploaded photo, or identity reference, upload your own photo first. No reference photo? Replace the character with a clear age, gender, and nationality, such as “25-year-old Japanese woman” or “30-year-old American man”.