Social media post dark silhouette poster design from photo prompt
A complex prompt for transforming uploaded photos into a split-layout poster: original photo on top, flat silhouette still life on dark ground below, with specific artistic constraints.
by 小小东·CC-BY-4.0 license·via YouMind (CC BY 4.0)·Source ↗
Use now
| 1 | Please turn each uploaded photo into an independent high-end design poster, do not stitch images together, output each photo separately. Use a 3:4 vertical composition, split into two halves like a folded card, with the fold line exactly on the horizontal centerline, both halves equal height, do not draw the fold line itself. |
| 2 | |
| 3 | Top half retains the original photo, preserving subject identity, structure, pose, realistic texture, natural lighting, and original color atmosphere, only applying slight high-end color grading to give it an art magazine, indie publication, and exhibition image quality. To fit the aspect ratio, naturally extend the environment background but do not stretch, distort, or change the subject; crop as panorama, leave sky above the subject's head, do not crop the top. No text in the top half, all text appears only in the bottom half. |
| 4 | |
| 5 | Bottom half extracts only the most recognizable **subject, outline, structure, pose, and narrative relationships** from the photo, reconstructing them as a **Flat Silhouette Still Life on a Dark Ground**. Do not copy the photo completely, but compress the subject and a few adjacent items into flat silhouettes without outlines or internal details, making the correspondence with the top photo immediately identifiable. **Must have several unoutlined flat silhouettes overlapping into a cluster standing on a solid dark background, with only one block noticeably brightest, popping out as if lit**, this defines the style, missing it fails. |
| 6 | |
| 7 | Bottom half requires new artistic judgment. Even if the original has poor composition, messy background, or small subject, save it by **removing environment, converting to front/side view, moving scattered items close into a cluster**; arrange silhouettes of varying heights staggered, as if quietly placed on an invisible surface. If the photo is a scene (street, corridor, landscape, interior), take only the most representative single object or fragment, do not draw the rest, do not draw the whole scene. |
| 8 | |
| 9 | Form focuses on **unoutlined front/side silhouette blocks**: each shape expressed with one color block, soft edges with slight hand-cut undulations, almost no internal structure, only using darker same-color small blocks where necessary to indicate openings, gaps, or turns. People, animals, buildings, objects, plants, and landscapes are unified into flat front or side silhouettes, depth read only through occlusion and color shade, no perspective or projection. |
| 10 | |
| 11 | Texture is **fine dry-brush gouache granules**: dark background and each silhouette covered with very fine powdery speckles, making color surfaces soft and slightly velvety; stop here, no scratches, stains, folds, or aging effects. |
| 12 | |
| 13 | Composition uses **a medium-sized silhouette cluster + large dark negative space**. Bottom half drawn as **panorama**, as if photographer stepped back, subject complete with empty space around, smaller than intuition suggests; **leave sky** above subject, like mounting header wider than footer, nothing touches the central fold. Silhouette cluster slightly off-center, base line on invisible horizontal, other side left for text. Prefer things quietly crowded together rather than spread across the canvas. |
| 14 | |
| 15 | Color extracted from the top photo's most emotional hues, remixed into **deep ground plus low-saturation pink-grey blocks**: darkest photo color further dimmed keeping some hue as majority background; other colors desaturated mixed with grey/white becoming soft pink-grey blocks; only one block lifted brightest near warm-white, sole highlight. Adjust warmth/coolness per photo, avoid pure black, high saturation, and gradients. |
| 16 | |
| 17 | Text minimal editorial intervention, any language, no fixed title. Only one short name or word taken from specific things, places, actions, or details in the photo, no subtitles or second lines; text very small, much smaller than subject, using **thin serif uppercase glyphs** in dark space beside silhouette cluster, color one shade lighter than brightest, separated by quiet distance. No generic inspirational slogans. |
| 18 | |
| 19 | Overall like a still life illustration in indie publication or art postcard: dark ground, unoutlined silhouettes, overlapping layers, one bright color plane and thin small text composing quiet, warm, slightly nocturnal atmosphere. |
| 20 | |
| 21 | Avoid full scene replication, filled backgrounds, cartoonish feel, template poster look, avoid isolated silhouettes, adding outlines, multiple equally bright blocks without focus, 3D lighting, vivid candy colors, and overly neat vector edges. |
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.