資訊圖表與卡片

舞步分解樣片表

把一段舞蹈或動作拆成十六格編號且帶時間碼的閃燈照片,排在一張黑色樣片表上,每一格的人、服裝和場地都相同

更新日期:

完整提示詞

英文提示詞包含建議的範例需求。生成前請調整主體和細節。原始範例輸入及生成參數尚未完全核實。

推薦模型: GPT Image 2

Lay out one horizontal contact sheet that breaks the dance, pose sequence, or physical action named in the user request into numbered steps. Build a four-by-four grid of sixteen frames on a black poster ground with thin gutters, treating every frame as a direct-flash snapshot from one continuous session so the same person, outfit, location, and energy carry across the sheet. Work from an uploaded photo when provided, holding identity, clothing, hair, and setting steady; with text alone, invent one consistent subject. Give each frame a genuinely different stage of movement, labeled with a short all-caps title at top left, running timestamp at top right, and lower-case instruction caption of about five words along the bottom. Set titles in bold white italic capitals and captions in small clean type. Place one centered white summary line beneath the grid. Keep hard flash highlights, deep falloff into shadow, and natural motion blur in hair and limbs so it reads as a real session rather than a render. No extra panels, logo, watermark, or unrelated text. User request: rooftop night party, sparkly outfit, sixteen steps of a fast freestyle routine

官方範例

舞步分解樣片表
範例模型: Seedream 5.0 Lite
舞步分解樣片表
範例模型: Seedream 5.0 Lite

來源與署名

由 OmniArt 改編及重寫,以下列出來源署名、修改說明及使用條件

  • Y2K Rooftop Dance Tutorial Sheet · Syed Abuthahir ∞

    YouMind-OpenLab/awesome-gpt-image-2

    CC BY 4.0 repository license; original author and source attribution retained from the YouMind catalog.

    Rewritten and consolidated into an OmniArt recipe archetype; template tokens removed; named people, brands, platforms, games, and film IP generalized; no raw prompt text or source image copied.

來源與署名

相關的提示詞配方