Original document
GPT Image 2 · en
Create a high-end streetwear fashion advertising poster inspired by modern Asian clothing advertisements. A full-body portrait of a stylish young male model standing confidently, ankles crossed, hands in his jacket pockets, head slightly tilted back and to the side, expression calm and deep. He has medium-length, curly, tousled hair with a soft texture. He has a slim, athletic build. The clothing includes one {argument name="jacket style" default="Dark olive green hooded cotton jacket"} He wore his shirt open, layered over a clean white crewneck sweatshirt with a small brand logo on the chest, paired with loose-fitting black cargo pants and simple white sneakers. The style was simple, youthful, and modern. (Background: [Insert background here]){argument name="background color" default="Vibrant electric blue"} Seamless studio backdrop with subtle gradient lighting, soft halo stripes, and glossy floor reflections. The lighting utilizes soft studio lighting with delicate shadows and a sophisticated commercial feel. Graphic poster layout with a large, bold, compressed sans-serif font.{argument name="brand name" default="JEANSWEST"} "Stretch the background behind the model vertically to a light gray-white. Add large text 'JW26' in the lower right corner. The composition should convey the quality of a high-end, trendy, simple, commercial, youthful, and modern fashion advertisement. The focus should be clear, the fabric texture hyper-realistic, with cinematic lighting, balanced white space, smooth brand design, high resolution, and a vertical poster proportion."How to use
- Copy the complete original prompt, including any parameters.
- Replace the subject, text and composition with your own requirements.
- Use a compatible external tool; check its current access conditions and review the result.
Before you start
- Check whether a reference image is required. A compatible model label does not mean this example was generated with that model.
- Keep names, figures and visible text accurate; results can vary between model versions.
