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, Illustration, Character 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, Illustration, Character, 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 2 media outputs, which makes it easier to check whether the style remains stable across multiple results.
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, Illustration, Character, 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, Illustration, Character 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
Use the uploaded portrait only as the identity reference. Accurately preserve the person’s real facial identity, face shape, facial features, skin tone, hairstyle, hair volume, and natural real-life appearance. Do not copy the original background, lighting, clothes, pose, or image quality from the uploaded portrait. Create a highly realistic vertical wide-angle action portrait in an indoor dessert shop or café. The subject is crouching low toward the camera in a dynamic playful pose, with one hand stretched very close to the lens, palm facing forward, creating strong foreground perspective and mild wide-angle distortion. The other arm is lifted upward in an energetic motion. The head is slightly lowered, with a casual cap or suitable accessory partially shadowing the upper face, but the visible facial features must still match the uploaded person naturally. Around the subject, several desserts appear suspended in mid-air: rolled crepes, layered tiramisu cake slices, rainbow cake, cream splashes, cocoa powder, crumbs, and milk-like dessert cream exploding around the foreground. The effect should feel like a frozen high-speed photography moment, playful and surreal, but still physically believable. Add realistic splashes on the floor and in the air, with natural motion direction, depth, and perspective. Generate suitable clothing automatically based on the uploaded person’s appearance and style. The outfit should feel casual, youthful, comfortable, and visually compatible with the dessert shop scene, but do not fix the exact clothing. Avoid logos, readable brand names, or watermarks on clothing or background. Use a low-angle camera close to the floor, vertical 3:4 composition, ultra-wide lens feeling, strong foreground hand perspective, dynamic depth, realistic indoor ceiling lights, soft ambient café lighting, natural shadows, realistic skin texture, slight motion energy, high-resolution commercial creative photography style. The image should look like a real camera photo with a creative advertising concept, not an anime image, not a plastic AI render, and not overly polished. Negative Prompt: watermark, logo, text, brand name, Chinese watermark, AI watermark, anime, cartoon, illustration, 3D render, plastic skin, overly smooth skin, doll-like face, fake face, over-beautified features, wrong identity, different person, distorted face, extra fingers, missing fingers, broken hand, unnatural palm, deformed limbs, messy anatomy, floating objects without perspective, unrealistic dessert scale, low quality, blurry face, bad lighting, harsh overexposure, pasted face, collage look, duplicated person, unreadable text, cluttered background, dirty floor, horror expression, uncanny valley.
