[{"data":1,"prerenderedAt":70},["ShallowReactive",2],{"detail-uidesign-aigenerated-2861":3},{"image":4,"related":16},{"id":5,"url":6,"thumb":6,"prompt":7,"prompt_cn":8,"prompt_en":7,"tags":9,"title":12,"source_repo":13,"date":14,"width":8,"height":8,"slug":15,"urlWebp":6,"thumbWebp":6},2861,"\u002Fimage\u002F53a22e28e92e45f8.webp","gpt image 2生图能力真的恐怖啊，这是我的提示词： 01 前端（用户看到的部分） 是什么：前端就是界面，是用户能看见、能点、能操作的部分。 在哪里：网页、小程序、App 的界面。 用什么做：HTML（结构）、CSS（样式）、JavaScript（交互）。 02 后端（背后处理的部分） 是什么：后端就是幕后大脑，负责逻辑和运算。 在哪里：服务器上，用户看不见。 作用： 处理登录注册 计算价格、推荐商品 接收前端请求、返回数据 常用的编程语言：Java、Python、Go、JavaScript（Node.js） 03 数据库（记忆的部分） 是什么：数据库就是用来存储和管理数据的。 存什么：账号、密码、订单、库存… 常见的数据库： MySQL、PostgreSQL（关系型，像表格一样） MongoDB（文档型，像文件夹一样） 04 SaaS（软件即服务） 是什么：SaaS = Software as a Service（软件即服务）。 核心特点： 打开网页\u002F小程序\u002FAPP就能用 按月或按年订阅 常见形式：网站、移动 App、小程序都可以是 SaaS。 05 总结 前端：用户看到和操作的界面 后端：背后运行的逻辑和计算 数据库：存放和管理数据的地方 SaaS：把软件做成服务，用户随时通过网络使用 前端展示 → 后端处理 → 数据库存储 → SaaS 是交付方式 帮我针对上面的内容画一张易于理解的图",null,[10,11],"UI Design","AI Generated","AI-Generated Soft Toned UI","EvoLinkAI\u002Fawesome-gpt-image-2-API-and-Prompts (case 122)","2026-06-18","uidesign-aigenerated-2861",[17,26,35,44,53,62],{"id":18,"url":19,"thumb":19,"prompt":20,"prompt_cn":8,"prompt_en":20,"tags":21,"title":23,"source_repo":24,"date":14,"width":8,"height":8,"slug":25,"urlWebp":19,"thumbWebp":19},2371,"\u002Fimage\u002Fd4ede253a6094734.webp","Research LIME Drug Design and make a detailed infographic about it",[22,11],"Creative Composite","AI-Generated Creative Research LIME Drug Design","EvoLinkAI\u002Fawesome-gpt-image-2-API-and-Prompts (case 48)","creativecomposite-aigenerated-2371",{"id":27,"url":28,"thumb":28,"prompt":29,"prompt_cn":8,"prompt_en":29,"tags":30,"title":32,"source_repo":33,"date":14,"width":8,"height":8,"slug":34,"urlWebp":28,"thumbWebp":28},2340,"\u002Fimage\u002F31c4b5485c3f4044.webp","このキャラクターと背景を元に、 公式設定資料のようなキャラクターシートを作成してください。\n・正面、側面、背面の3面図を含める ・キャラクターの表情バリエーションを追加\n・衣装や装備の詳細パーツを分解して表示 ・カラーパレットを追加 ・世界観の簡単な説明を入れる\n・全体は整理されたレイアウト\n（白背景、図解風）\n・アスペクト比16：9\n\n高解像度、プロのコンセプトアートスタイル",[31,11],"Character Design","Character Official Character Sheet (JP) Design","EvoLinkAI\u002Fawesome-gpt-image-2-API-and-Prompts (case 5)","characterdesign-aigenerated-2340",{"id":36,"url":37,"thumb":37,"prompt":38,"prompt_cn":8,"prompt_en":38,"tags":39,"title":41,"source_repo":42,"date":14,"width":8,"height":8,"slug":43,"urlWebp":37,"thumbWebp":37},2448,"\u002Fimage\u002F9e02b001e64e4f82.webp","mobile phone photo, old CCD camera aesthetic, harsh flash, grainy, dim messy indoor lighting, candid snapshot feeling, slight motion blur, young Korean female idol, soft innocent look",[40,11],"Portrait Photography","AI-Generated Soft Toned Smartphone","EvoLinkAI\u002Fawesome-gpt-image-2-API-and-Prompts (case 12)","portraitphotography-aigenerated-2448",{"id":45,"url":46,"thumb":46,"prompt":47,"prompt_cn":8,"prompt_en":47,"tags":48,"title":50,"source_repo":51,"date":14,"width":8,"height":8,"slug":52,"urlWebp":46,"thumbWebp":46},2479,"\u002Fimage\u002F9e818d56672044a5.webp","A highly detailed anime-style full-body character portrait of {argument name=\"character name\" default=\"Hermes\"}, a delicate futuristic girl sitting curled up with her knees hugged to her chest, gazing softly at the viewer with a calm, slightly melancholic expression. She has extremely long {argument name=\"hair color\" default=\"silver-lilac\"} twin tails with soft bangs, glossy lavender eyes, porcelain skin, and ornate crystal hair accessories including 3 large ribbon bows and a jeweled tiara-like headpiece. Her outfit is an elaborate translucent idol-tech dress in {argument name=\"outfit color\" default=\"pink, lavender, and violet\"}, featuring off-shoulder puff sleeves, layered ruffles, faceted gemstone-like fabrics, a huge floral bow at the waist, dangling crystal charms, garter details, patterned thigh-high stockings, and glossy bow heels. Surround her with a luminous cyber dreamscape in {argument name=\"background palette\" default=\"neon violet and electric blue\"}: transparent holographic panels, floating glass cubes, sparkling particles, geometric prisms, glowing wireframe lines, and digital UI windows suspended in space. Include 5 readable interface text elements scattered in the background: \"ERROR.\", \"Code-\", \"return\", \"area x1\", and \"404\". Make the whole image feel like a luxurious AI avatar reference illustration, mixing ethereal fantasy and cyberspace aesthetics, with crystalline light refractions, dramatic glow, high detail, intricate lace and gem textures, and a polished premium gpt-image-2 anime rendering.",[49,40,10],"Tech\u002FFuturistic","AI-Generated Illustrated and Neon-Lit Jewelry","EvoLinkAI\u002Fawesome-gpt-image-2-API-and-Prompts (case 93)","techfuturistic-portraitphotography-uidesign-2479",{"id":54,"url":55,"thumb":55,"prompt":56,"prompt_cn":8,"prompt_en":56,"tags":57,"title":59,"source_repo":60,"date":14,"width":8,"height":8,"slug":61,"urlWebp":55,"thumbWebp":55},2705,"\u002Fimage\u002F14ef9777c7134458.webp","I asked GPT Image 2 to spill the beans on alien life.\n\ndo this for alien disclosure: \u003Cinstruction>\nRole: You are \"The Declassification Officer,\" creating visually compelling intelligence dossiers.\n\nGoal: Produce a single vertical declassified case-file image about the chosen subject.\n\nPhase 1: Subject Classification\n- Analyze the input subject and reinterpret it as a high-priority intelligence target, anomaly, person of interest, secret invention, or unexplained event.\n- Assign:\n  - Case ID\n  - Threat level\n  - Classification level\n  - Status (active, missing, monitored, contained, unresolved)\n\nPhase 2: Document Structure\nDesign the image as a realistic but stylized dossier page with the following sections:\n- Header: agency-style title, case number, classification stamp.\n- Mugshot or main visual of the subject.\n- Summary paragraph.\n- Notable traits or observed abilities.\n- Timeline of 3–5 incidents.\n- Redacted notes.\n- Location sightings or evidence callouts.\n- Bottom section with stamp marks, signatures, and warnings.\n\nPhase 3: Visual Style\n- The entire output must be a single image.\n- Style: aged paper, photocopy texture, ink stamps, mild wear, redactions, handwritten annotations, paperclip shadows.\n- Include visual evidence elements such as photo corners, sticky notes, fingerprints, circles, arrows, highlighted lines.\n- Use readable layout and believable bureaucratic typography.\n\nPhase 4: Tone\n- Tone should be suspenseful, intriguing, and slightly cinematic.\n- Can be serious or humorous depending on the input.\n- Keep all content fictionalized if needed.\n\nOutput: One high-detail declassified dossier poster as a single finished image.\n\u003C\u002Finstruction>",[40,58,10],"Poster Design","Cinematic and Poster Furniture in Office Environment","EvoLinkAI\u002Fawesome-gpt-image-2-API-and-Prompts (case 186)","portraitphotography-posterdesign-uidesign-2705",{"id":63,"url":64,"thumb":64,"prompt":65,"prompt_cn":8,"prompt_en":65,"tags":66,"title":67,"source_repo":68,"date":14,"width":8,"height":8,"slug":69,"urlWebp":64,"thumbWebp":64},2816,"\u002Fimage\u002F8d6b187230ac4b18.webp","GPT Image 2を使って、OpenClawの情報を調べてドンキの広告ポップ風に実際のドンキに貼っているような感じで画像生成してください",[10,11],"AI-Generated UI Don Quijote Promo Pop","EvoLinkAI\u002Fawesome-gpt-image-2-API-and-Prompts (case 34)","uidesign-aigenerated-2816",1781759314002]