Woman at Vending Machine in Tokyo Alley AI Image Prompt
Create a photorealistic candid street snapshot in a narrow Tokyo entertainment-district back alley, viewed from behind. The central subject is {argument name="character name" default="a young woman"} standing slightly right of center in front of two bright Japanese drink vending machines, choosing a beverage. She has {argument name="hair color" default="pale pink hair"} tied in a low ponytail with a white scrunchie, seen from the back, wearing an oversized light blue button-up shirt, a blue plaid pleated skirt, and a brown leather shoulder bag decorated with small colorful plush keychains; include a small purple plush toy tucked near the bag strap. The vending machines fill the right side of the frame, glowing cool white and blue, with rows of colorful bottles and cans visible behind glass, coin slots, buttons, product labels, and payment panels; add urban stickers, posters, graffiti marks, and partial black-and-white street signage on the wall beside them. On the left side, show an old narrow restaurant storefront with Japanese signs, warm interior lights, menu boards, wood and concrete textures, and a utility pole covered in stickers. Include exactly 5 visible pedestrians besides the main subject: 2 young women walking away on the left, 1 woman in dark pants walking down the center of the alley, and 2 smaller distant pedestrians near the vanishing point. Use a natural everyday mood, overcast daylight, muted colors, soft depth of field, realistic lens perspective, street-level eye height, 16:9 horizontal composition, no posed expression because the main subject is facing away, no watermark, no extra readable headline text.
Content: Subject (woman from behind, with variable parameters) + Scene (back alley, vending machines, restaurant, pedestrians) + Style (photorealistic candid) + Composition (16:9, subject right-of-center) + Lighting (overcast soft light) + Color (muted) + Material (realistic) + Lens (realistic perspective, shallow DoF, eye-level)
Pros: Very detailed, clear scene layering; variable parameters offer flexibility
Cons: Many elements may be hard to generate precisely at once; crowd placement is overly specific
Reference image: No obvious reference-image dependency
Source materials are collected from publicly accessible web pages. Contact us if a rights issue needs review. Copyright & Privacy
