Oryginalny dokument
GPT Image 2 · en
A full-body fashion portrait full of emotion, the protagonist is {argument name="subject" default="young women"} Standing in a narrow city alley or tunnel covered in thick, colorful graffiti, shooting at night, employing a realistic style with dramatic, low-key lighting and flash photography. She leans casually against a wall, one hand touching a pair of large black headphones, the other hand tucked into an oversized {argument name="hoodie color" default="Mustard Yellow"} Inside the front pocket of the hoodie. The hoodie was long enough to be worn as a hooded dress, with a simple black smiley face printed on the chest and a white drawstring. She carried a black backpack, revealing two shoulder straps, and wore white mid-calf socks and chunky black and white low-top sneakers. Her legs were bare, her posture relaxed, one knee slightly bent, one foot stepping forward. Her shoulder-length hair was slightly messy, and the color was {argument name="hair color" default="Deep gold"} The shot employs a vertical composition, taken from head to toe, with the subject positioned slightly to the left of the frame. The background is a rough spray-painted wall, primarily in shades of blue-green, yellow, pink, and black, interspersed with paint drips, graffiti signatures, and abstract cartoon graffiti shapes, creating a raw street art atmosphere. The ground is dark, worn, and reflects paint splatters. High contrast, deep shadows, and realistic skin and fabric textures are used to achieve an editorial-grade street photography style and an underground urban atmosphere. Clothing and body details are sharply focused, while facial details are softened, creating a cinematic, nocturnal atmosphere.Jak używać
- Skopiuj cały oryginalny prompt wraz z parametrami.
- Dostosuj temat, tekst i kompozycję do swoich potrzeb.
- Użyj zgodnego narzędzia zewnętrznego; sprawdź warunki dostępu i wynik.
Przed rozpoczęciem
- Sprawdź, czy potrzebny jest obraz referencyjny. Zgodność nie potwierdza modelu użytego do przykładu.
- Sprawdź nazwy, liczby i napisy; wyniki zależą od wersji modelu.
