Case Media
Case Notes
This page keeps the media, full prompt, and original source together so you can inspect the result first and decide whether the prompt is worth copying, saving, or comparing.
Case Insights
To make this page easier to search, cite, and reuse later, the case is also broken down into practical guidance about usage, visual cues, and prompt structure.
Best Fit Scenarios
- Use this as a character design benchmark when you need a fast style baseline before rewriting your own prompt.
- It is especially helpful if your target overlaps with Portrait, Fashion, Poster and you want to judge the image result before tuning wording.
- Keep it as a control sample when you compare nearby prompt variants one variable at a time.
Visual Signals To Notice
- The clearest style signals here are Portrait, Fashion, Poster, so those should usually stay in your first rewrite.
- Look at silhouette, costume language, mood styling, and whether the character reads clearly at a glance.
- This case keeps one primary output, so the first image should be treated as the main visual reference.
How The Prompt Is Structured
- The prompt reads as a long, highly specified prompt, which is useful when you want to judge how much specificity this direction needs.
- Its keyword cluster is centered on Portrait, Fashion, Poster, so you can usually keep that cluster while swapping subject, camera, layout, or copy details.
- A practical rewrite path is: keep the outcome, keep the strongest style cues, then replace only the subject and environment blocks.
Good Follow-up Questions
- What changes first if you keep Portrait, Fashion, Poster but switch the subject matter?
- Which part of the result comes from section-level structure (Character Design) versus tag-level style cues?
- Which related cases in the same section give you a cleaner or more extreme variation of the same direction?
Full Prompt
Vertical 3:4, ultra-realistic street photography style Use my uploaded portrait photo as the only identity reference. Preserve only my real facial features, face shape, hairstyle, hair color, skin tone, body proportions, and overall personal appearance. Do not copy the face, identity, or body of the reference image. The reference image should only be used for the scene, composition, pose, outfit style, lighting, color grading, and atmosphere Create a realistic portrait of one young woman sitting in front of an urban street newsstand or magazine kiosk. The background should include a metallic-framed glass display filled with magazines, newspapers, posters, and small booklets. The environment should feel like a real city street corner, not a studio set The woman sits on a metal bench, ledge, or step in front of the kiosk. Her body leans slightly forward. One hand gently supports her cheek, while the other hand rests naturally on her knee or leg. Her pose is quiet, relaxed, slightly distant, and natural. Her eyes look near the camera in a subtle, unforced way, like a candid street portrait Outfit: a simple light cream or off-white sleeveless camisole, thin-strap top, or soft knit tank top, paired with loose black wide-leg pants. The styling should feel clean, minimal, youthful, understated, and realistic. Do not make the outfit overly glamorous or overly sexualized Lighting and mood: cool-toned urban daylight, slightly overcast or late-afternoon atmosphere. A cool white fluorescent tube light glows inside the kiosk. The metal and glass surfaces should have realistic reflections. The overall color grading is slightly desaturated, with cool gray, green, silver, and muted street tones Composition: the woman is placed in the center or slightly lower center of the frame. The kiosk glass display fills the background. Blurred trees, sidewalk, and city street elements appear on the left side. The image should feel like a real phone photo or realistic street-camera portrait, with natural depth of field, authentic skin texture, subtle pores, real shadows, natural fabric folds, slight grain, and documentary realism No text, no watermark, no logo, no subtitle, no “AI generated” label Negative Prompt: watermark, text, logo, subtitle, AI-generated label, signature, extra people, duplicate person, wrong identity, copied face, pasted face, face swap look, plastic skin, over-smoothed skin, doll-like face, anime style, CGI, 3D render, unrealistic body proportions, distorted hands, extra fingers, broken fingers, unnatural arms, unnatural pose, overexposed face, heavy beauty filter, glossy commercial lighting, studio background, luxury fashion advertisement, exaggerated pose, overly sexualized outfit, low resolution, blurry face, deformed eyes, unnatural expression, fake magazine text, readable large text, messy composition, harsh flash, unrealistic reflections
