| 1 | Output a single independent 4:5 vertical commercial poster, no collage, no multi-grid generation. Use an original fictional brand, do not imitate existing brand packaging, logos, or advertisements. Text should only use the brand name, main title, and category explicitly listed in the prompt, do not fabricate prices, award information, parameters, dates, origins, or slogans. The image should reach a level of completion suitable for creative direction review, with realistic structure, credible materials, clear layout, and no watermarks. |
| 2 | |
| 3 | Theme: Dessert audit sample. Original brand "SOFT LAB", product "CARAMEL PUDDING", main title "MELT". |
| 4 | |
| 5 | Use a warm cream-colored seamless background. Place a real caramel pudding slightly below center, with a smooth surface featuring fine air bubbles, caramel sauce flowing slowly down one side, and soft contact shadows on the white porcelain plate. In the middle background, stand four thick but not exaggerated cream-colored letters "MELT", with letter material resembling cooled fine sugar frost. |
| 6 | |
| 7 | Core composition type: "Single Dessert - Temperature Direction - Typeface Gradient". Establish a clear temperature change from left to right: M remains dry crystalline; E edges show slight caramel wetness; L lower part slightly softens; T's bottom corner contacts caramel sauce and slowly melts. Changes must be continuous, restrained, and gravity-compliant, with all four letters remaining fully readable. Use two or three extremely thin hand-drawn arrows to annotate "Cooling / Contact / Softening", do not add long explanations. Write "SOFT LAB" at the top, "CARAMEL PUDDING" at the bottom. |
| 8 | |
| 9 | Colors should only use cream white, caramel brown, and a small amount of dark coffee. Avoid multiple desserts, food splashes, exaggerated lava, cartoon expressions, recipe information, prices, promotional stickers, or children's illustrations. |
Discussion
Alternatives
Banner Design - Multi-Format Creative Banner SystemTell us what your banner is for and what it should say, and get back polished, ready-to-post cover and ad images sized correctly for each platform.Paper Poster (HTML): measurement-gated poster generationDEFAULT poster pipeline — build an academic conference poster (ICML/NeurIPS/ICLR/CVPR/...) as a single HTML/CSS file with measurement-driven hard gates, real paper figures, a two-hue design-token system, and print-ready PDF via headless Chromium. Use when the
Qiaomu codex imagegenGenerate or edit images with Codex's built-in image generation from any agent, through an MCP tool or a plain CLI. For every image request it first proposes at least four divergent style directions (24 distilled templates, 48 presets, 20 Mondo poster artists), lets the user pick, expands the prompt, generates, and checks the result. Scenario craft for 视频封面, 视频海报, 小红书配图, 公众号封面, X 封面, 朋友圈海报, 书籍封面, 专辑封面, 产品海报, 人物写真, 节气海报, 展览海报, PPT 页面, 图生图. Use for 生图, 配图, 海报, 封面, "给我几个风格", "用 Codex 画一张". Excludes: editing photos with local tools, charts or diagrams from data, UI mockups, video generation, or anything that needs an API key-based image service.PromptfilmPromptfilm — turns one sentence into a researched 3D motion graphic — one self-contained real-time HTML file (Three.js) that loops seamlessly and records straight into a video — 9:16 for Shorts/Reels by default, or 16:9, 1:1, 4:5; captions in one or two languages (English + the requester's language by default); paced the way the requester edits; checked by automated QA, a fresh-eyes visual review and a delivery gate; reviewed and exported as a frame-exact MP4 in a local Studio. Use it for any motion graphic — product ads, game or app demos, journeys through scale (Earth to the universe, a chip down to atoms), how-it-works explainers, recreations of a known scene, logo stings, data stories — when the user asks for a motion graphic, a 3D animation or video as HTML, or "an HTML like the cosmic-scale / Blackwell one", even naming only a topic (often in Korean, e.g. "…모션그래픽 만들어줘", "…부터 …까지 확대하는 영상 html 만들어줘"); and for follow-ups on such a film ("리뷰 반영해줘", "mp4로 뽑아줘", "스튜디오 열어줘").
Qiaomu codex imagegenGenerate or edit images with Codex's built-in image generation from any agent, through an MCP tool or a plain CLI. For every image request it first proposes at least four divergent style directions (24 distilled templates, 48 presets, 20 Mondo poster artists), lets the user pick, expands the prompt, generates, and checks the result. Scenario craft for 视频封面, 视频海报, 小红书配图, 公众号封面, X 封面, 朋友圈海报, 书籍封面, 专辑封面, 产品海报, 人物写真, 节气海报, 展览海报, PPT 页面, 图生图. Use for 生图, 配图, 海报, 封面, "给我几个风格", "用 Codex 画一张". Excludes: editing photos with local tools, charts or diagrams from data, UI mockups, video generation, or anything that needs an API key-based image service.PromptfilmPromptfilm — turns one sentence into a researched 3D motion graphic — one self-contained real-time HTML file (Three.js) that loops seamlessly and records straight into a video — 9:16 for Shorts/Reels by default, or 16:9, 1:1, 4:5; captions in one or two languages (English + the requester's language by default); paced the way the requester edits; checked by automated QA, a fresh-eyes visual review and a delivery gate; reviewed and exported as a frame-exact MP4 in a local Studio. Use it for any motion graphic — product ads, game or app demos, journeys through scale (Earth to the universe, a chip down to atoms), how-it-works explainers, recreations of a known scene, logo stings, data stories — when the user asks for a motion graphic, a 3D animation or video as HTML, or "an HTML like the cosmic-scale / Blackwell one", even naming only a topic (often in Korean, e.g. "…모션그래픽 만들어줘", "…부터 …까지 확대하는 영상 html 만들어줘"); and for follow-ups on such a film ("리뷰 반영해줘", "mp4로 뽑아줘", "스튜디오 열어줘").Browse more free AI prompts or everything in Design.