OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
日文极简认知PPT脚本与插图提示模板
Japanese Minimalist Cognitive PPT Script and Illustration Prompt Template
将文章或转录整理为日文优先的10–15页极简认知PPT脚本，并为每页生成配套黑白版画风横幅插图提示。
提示词 / Prompt
中文提示词
以用户上传的参考图作为主要可见人物的面部身份依据。在不与身份参考冲突的情况下，保留来源的场景、造型、服装、姿势、构图、光线和视觉风格。 你负责一个演示文稿脚本与插图提示词工作流。将以下来源材料整理成连贯、日文优先的认知类幻灯片：短い散歩は注意を切り替え、考えを整理するための小さな習慣になる。歩きながら景色の変化に気づき、気になった問いを一つだけメモする。散歩そのものが問題を解決すると断定せず、観察と振り返りの時間として使う。週に数回、無理のない距離から始め、続けやすい道を選ぶ。。使用 11 页、16:9 画幅，主要以 Japanese 撰写幻灯片文案；仅在确有帮助时少量使用英文关键词。 先按逻辑顺序提炼7–9个核心要点，再依照以下叙事路线编排指定页数；可合并或拆分相邻部分，但整体论述必须连贯：封面、现状/问题、核心洞察、核心框架、方法/步骤、案例或对比、常见误解、行动清单、结尾格言。每页只讨论一个观点。标题须为不超过15个日文字符的具体断言或问题；每页列3–5条具体要点，每条不超过18个日文字符；幻灯片下方另写60–120字符的第一人称补充说明。约80%的信息应能从画面和简短文案中直接理解；不得编造来源中不存在的事实。 每页依次输出：页码与标题、画面内准确标题和要点、补充说明，以及一条独立插图提示。每幅插图均为横向 16:9 黑白钢笔蚀刻风画面，采用细密分层交叉排线、点描、刮板肌理与纸纹，配合戏剧性明暗、深阴影、丰富中间调和清晰高光；以渺小的人类/宇航员剪影对照巨大的未知。采用以下光线方向：Dramatic chiaroscuro with crisp highlights and deep layered cross-hatched shadows.。在适合的画面中使用这些背景意象：A vast dark doorway-like void, textured paper space, and a simple path or ledge that establishes scale.。各页都保持同一位成年小比例人物，由上传的身份参考提供身份线索，但脸部细节不应成为视觉主体。 每条插图提示用约80–120个日文字符描述该页场景、人物状态、巨大元素与光影。插图底部15–20%必须留作纯黑横条；横条中以清晰易读的白色无衬线字，将该页准确标题居中，将准确的3–5条日文要点左对齐。不得嵌入其他文案。所有页面统一采用此布局与黑白处理。每幅图末尾均附负面约束：彩色、照片式灰度、写实摄影、喷枪柔化、平滑涂抹、模糊、低细节、平光、卡通、动漫、赛璐璐、水印、标志、署名、界面元素或外框。不要声称特定渲染器或分辨率。 以可转入幻灯片的清晰结构化文本返回，并明确区分每页标题、要点、补充说明和插图提示。默认来源材料只是完整示例，不代表用户未来提供的其他来源事实。
English prompt
Use the uploaded reference image as the facial identity reference for the main visible person. Keep the source scene, styling, clothing, pose, composition, lighting and visual style unless they conflict with the identity reference. You are a presentation-script and illustration-prompt workflow. Transform this source material into a coherent Japanese-first cognitive slide deck: 短い散歩は注意を切り替え、考えを整理するための小さな習慣になる。歩きながら景色の変化に気づき、気になった問いを一つだけメモする。散歩そのものが問題を解決すると断定せず、観察と振り返りの時間として使う。週に数回、無理のない距離から始め、続けやすい道を選ぶ。. Use 11 pages in 16:9 format and write slide copy primarily in Japanese; use only occasional English keywords when genuinely useful. First extract 7–9 key points in logical order. Then write the requested number of pages following this arc, combining or splitting adjacent sections as needed while keeping the whole narrative coherent: cover, status quo/problem, key insight, core framework, methods/steps, case or contrast, common misconception, action checklist, closing maxim. Each page addresses one viewpoint. Use concrete assertion/question titles of at most 15 Japanese characters, 3–5 specific bullets of at most 18 Japanese characters each, and a 60–120-character supplementary explanation below the slide written in first person. Keep about 80% of each slide understandable from its visual and short copy alone; do not invent facts absent from the source. For every page, output: slide number and title; exact on-image title and bullets; supplementary explanation; and one separate illustration prompt. Each illustration is a horizontal 16:9 monochrome pen-and-ink engraving with detailed layered cross-hatching, stippling, scratchboard and paper-grain texture, dramatic chiaroscuro, deep shadows, rich midtones, crisp highlights, and a tiny recurring human/astronaut silhouette against a gigantic unknown. Use this lighting direction: Dramatic chiaroscuro with crisp highlights and deep layered cross-hatched shadows.. Use these background motifs where relevant: A vast dark doorway-like void, textured paper space, and a simple path or ledge that establishes scale.. Keep one consistent small adult figure, guided by the uploaded identity reference, without making facial detail dominant. Each illustration prompt must describe the page-specific setting, the figure's state, the vast element, and light/shadow in roughly 80–120 Japanese characters. Reserve the bottom 15–20% of the illustration as a solid black horizontal bar. Inside it, place the exact page title centered and the exact 3–5 Japanese bullets left-aligned in white, legible sans-serif lettering. No other embedded copy. Apply the same layout and monochrome treatment to every page. Negative constraints for each image: color, photographic grayscale, photorealism, airbrush, smooth shading, blur, low detail, flat lighting, cartoon, anime, cel shading, watermark, logo, credit, UI, or outer frame. Do not claim a specific renderer or resolution. Return clean structured text that can be transferred into slides; keep each page's title, bullets, note, and illustration prompt clearly separated. The defaults are a complete illustrative source, not facts about another source the user may later supply.
探索更多图片和视频提示词 · 生成图片 · 生成视频 · 在 AI 画布中创作
相关作品
- 90年代冷色调仙侠风翡翠绿汉服人像
Ethereal 9:16 full-body portrait of a clearly adult Chinese woman in jade-green xianxia-inspired hanfu amid layered gauze curtains, silver ornaments, and cold teal moonlight with nostalgic 1990s fantasy-drama diffusion.
- 超精细3D漫画球星收藏级海报
Reusable 4:5 sports-memorabilia poster template for a named football player, combining a stylized likeness, current kit, chronological miniature career display, trophies, milestone props, and engraved nickname plaque.
- 复古赛车海报设计提示词
Reusable 4:5 vertical retro racing poster template with a centered front-facing car hero view, integrated geometric landscape graphics, fictional brand mark, slogan, and distressed vintage print finish.
- Q版角色聊天表情包生成指令
Reusable template for a consistent chibi chat-sticker character showing one clear emotion and action at a time, with a reserved Chinese-copy area and white or transparent background.
- 认识蜜蜂儿童科普百科海报
Colorful classroom infographic poster centered on a friendly fuzzy honey bee, with modular anatomy, life-cycle, superpower, and conservation sections in a soft cream honeycomb design.
- 时尚色块拼贴人像摄影
Premium fashion-campaign collage of five adult European models in separate rounded geometric panels, using royal blue, crimson, emerald, mustard, and white luxury color fields with clean studio flash.