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 model & community benchmark when you need a fast style baseline before rewriting your own prompt.
- It is especially helpful if your target overlaps with Neon, Portrait, Cinematic 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 Neon, Portrait, Cinematic, so those should usually stay in your first rewrite.
- This kind of case is strongest when you watch deltas: what changed, what broke, and which prompt choice caused that shift.
- 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 Neon, Portrait, Cinematic, 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 Neon, Portrait, Cinematic but switch the subject matter?
- Which part of the result comes from section-level structure (Model & Community) 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
Goal: Create a glossy, high-contrast YouTube-style tech video thumbnail about choosing between {argument name="tool one name" default="Codex"} and {argument name="tool two name" default="Hermes"}. Canvas: 4:3 landscape thumbnail, 1024×768 composition, dark black-to-charcoal studio background with a dramatic white spotlight shining down from the top center, subtle smoky haze, cinematic rim lighting, and a premium “oily” glossy thumbnail look. Layout: Center a young male presenter from chest up, facing camera, wearing a plain black V-neck T-shirt. His face should be intentionally anonymized with a smooth blurred rectangular skin-tone mask. His arms are raised symmetrically, palms open upward as if weighing two choices. Place exactly 2 floating option graphics above his hands: on the left, a glowing blue cloud-shaped terminal icon with a white command prompt symbol; on the right, a black-and-white anime-style female avatar bust with glossy hair and a white outline glow, also anonymized with a small blurred square over the face. Text content: Add exactly 2 stacked text lines across the lower third. Top line: large bold white Chinese text with black shadow, {argument name="top headline text" default="到底选"}. Bottom line: huge mixed gold-and-white text reading {argument name="bottom comparison text" default="Codex 还是 Hermes?"}; make “Codex” and “Hermes?” metallic gold with bevel, gradient, black outline, and drop shadow, while the middle Chinese word stays white. Include one small golden star lens flare near the right side of the word “Hermes”. Subject details: The presenter has short messy brown hair lit by the overhead spotlight, natural hands with visible palms, and a neutral pose suggesting comparison or uncertainty. The left icon should glow electric blue with a neon rim; the right anime avatar should be monochrome with strong white edge highlights. Visual style: Hyper-polished Chinese tech creator thumbnail, sharp subject cutout, intense contrast, glossy 3D text, dramatic lighting, saturated highlights, clean composition, no extra logos, no watermark, no additional text.
