Prompt Library

有来有往才有温度：端午邻里互赠海报

尊享非遗美味北京烤鸭高端商业海报

黑色连体衣与长筒袜日系女子人像

adult East Asian woman in her twenties, Japanese ethnicity, long straight brown hair, neutral expression with a slight gaze at camera, sitting on a wooden floor against a plain white wall. She is wearing a black thin-strap bodysuit and sheer black over-the-knee stockings. Her pose is seated sideways with legs tucked, showing the curve of her hip. Soft natural indoor lighting, high resolution, 8k, shot with a portrait lens, sharp focus on subject. #AIArt #AImodel

暗黑吕布双形态Boss设定

Lu Bu game boss design, Red Hare and Sky Piercer, dark evolution form dual form comparison

晴升智能晾衣机品牌KV首屏设计

维港明月金雕纸艺：中秋拱形窗花

夏日清凉制冰机即时成冰商业视觉海报

北宋阳谷县银铺掌柜姚二郎影视设定图

水母主题高级美甲写实特写

A photorealistic close-up of exquisitely groomed female hands featuring luxury gel nail art inspired by 'Jellyfish'. The nails are designed with translucent oceanic gradients, bioluminescent glow effects, and delicate hand-painted patterns mimicking jellyfish tentacles. The set includes a combination of solid bases with pearlescent finishes and intricate artistic details using iridescent glitter and silver foil. The overall style is elegant, clean, and sophisticated, reflecting high-end beauty editorial photography. Focus is sharp on the nail textures and glossy finish, with soft natural lighting and a shallow depth of field. The background is a dreamlike, blurred underwater atmosphere with shimmering light reflections. 4K ultra HD, realistic skin texture, premium salon aesthetic. --ar 3:4

蜀韵中秋竹林熊猫剪纸窗花

Framepack 28 摄影包专业电商详情页设计

东方克制美学香氛品牌社交媒体宫格视觉

钴蓝月白海浪刺绣内衣多视图设计提案

怀旧平成风精细墨绘侧颜人像

Person and [XXX], close-up side-profile portrait, both facing the same direction. Illustrated in a nostalgic Heisei-era Japanese style with rich dark ink. Hand-drawn line art with visible sketch-like strokes, premium paper texture, refined and elegant sketch aesthetic, light and airy composition, minimalist visual style, sophisticated and timeless atmosphere. Generous negative space, completely white background, large margins on all four sides. Subtle and minimal color accents only. Subjects centered, clean composition. No text, logos, signatures. Ultra-high resolution, icon-friendly, square 1:1 format, highly detailed, delicate linework, premium editorial illustration quality.

极简大地风美食汉堡摄影

Minimal earthy food product photography of a gourmet burger placed on a rustic wooden table, warm beige textured plaster wall background, soft natural sunlight from the side, shallow depth of field, cinematic shadows, organic aesthetic styling, tiny scattered dried flowers and ceramic bowl with stones beside the burger, whimsical white hand-drawn doodle fairy character floating behind the burger with magical bubbles and sparkles, clean premium branding vibe, cozy eco-friendly atmosphere, ultra realistic, editorial food campaign, muted brown and cream tones, high detail, soft focus, 1:1 composition

滨海弧形木构书屋建筑设计推演手稿

真实人物与墙壁涂鸦影子交互人像

Use the uploaded character reference image as the strict identity and outfit reference. Preserve the reference character’s: - face identity - facial proportions - eye shape - nose - lips - skin tone - hairstyle - hair color - visible hair accessories - overall recognizable vibe - outfit and styling shown in the reference image Do not hardcode any specific character traits that are not present in the uploaded reference. All identity, hairstyle, accessories, and clothing details must be inferred directly from the uploaded reference image. Create a high-quality mixed-style vertical portrait showing: 1. a realistic full-body version of the uploaded character/person 2. a black hand-drawn doodle-shadow version of the same character/person on the wall beside them Core concept: The real person and their doodle-shadow are doing a playful mischievous pose together. The real person performs a cute realistic version of the pose, while the doodle-shadow performs a much more exaggerated, chaotic, cartoonish version of the same pose idea. The mood should feel cute, playful, mischievous, stylish, funny, and social-media-friendly. Real person: - Must remain realistic and photogenic - Must wear the same outfit style and key visible details from the uploaded reference image - Do not replace the reference styling with unrelated fashion - Expression should be cute, slightly confused, mildly embarrassed, playful, as if thinking: “Why am I doing this with my shadow?” - The real person should not stand stiffly - The real person should actively participate in the pose, but in a natural realistic way Doodle-shadow: - Must be a black hand-drawn sketch version of the same person, drawn directly on the wall - Not a realistic second person - Not a normal physical shadow - Not a full-color anime character - Black sketch line-art only - Should resemble the person through hairstyle silhouette, accessories, outfit silhouette, and pose structure - The doodle-shadow should look more energetic, sillier, and more chaotic than the real person - Add manga-like motion lines, hearts, stars, sparkles, and comic marks around the doodle if helpful Random mischievous pose rule: The pose must NOT be fixed. For each generation, invent a new playful mischievous pose for both the real person and the doodle-shadow. The real person and the doodle-shadow should share the same general pose idea, but they do not need to match perfectly. The real person performs a cute realistic version. The doodle-shadow performs a much more exaggerated, chaotic, cartoonish version. Do not repeatedly use pointing poses. Do not repeatedly use finger-gun poses. Do not repeatedly use the same standing pose. Do not always make both figures simply point at each other. Create a different mischievous pose each time. Possible pose directions are loose inspiration only, not a fixed menu: - playful idol pose - silly dance pose - leaning sideways with one arm curved overhead - making a big heart pose - cheeky wink pose - hands near cheeks in a cute teasing pose - exaggerated “ta-da!” pose - mock surprise pose - playful running-in-place pose - mischievous tiptoe pose - arms stretched in opposite directions - pretending to sneak away - cute troublemaker pose - dramatic overreaction pose - goofy victory pose - playful balance pose - playful peekaboo pose - shy but mischievous pose - cute overconfident pose The final pose should feel fresh, cute, mischievous, and slightly chaotic. The real person should look like they are reluctantly playing along. The doodle-shadow should look like it is having way too much fun. Composition: - vertical 4:5 or 9:16 - show the real person in full-body or nearly full-body framing - place the real person on one side of the frame - place the black doodle-shadow on a clean wall beside them - the doodle-shadow should be roughly the same height or slightly taller - keep enough space around both figures so the full pose is visible - the connection between the real person and the doodle-shadow must be clear at a glance Background: - simple clean indoor studio wall or minimal room corner - white, cream, or pale gray wall - clean floor - soft natural sunlight patch or gentle wall shadow allowed - keep the background uncluttered Lighting: - soft natural studio lighting - bright, clean, polished, playful mood - keep the real person’s face clearly visible Style quality: - realistic human photography - black hand-drawn doodle-shadow on wall - matching mischievous pose interaction - strong identity resemblance - outfit and styling faithfully based on the uploaded reference - cute and stylish mixed-media portrait - clean composition - social-media-friendly - no obvious AI artifacts Negative prompt: hardcoded blue hair when not in reference, hardcoded cloud clip when not in reference, hardcoded fish clip when not in reference, hardcoded school uniform when not in reference, outfit change unrelated to reference, realistic second person, normal reflection, normal shadow only, solid black monster shadow, horror shadow, creepy shadow, full-color illustration, cartoon human, anime human, weak resemblance, unrelated sketch character, messy wall, cluttered background, repeated pointing pose, repeated finger-gun pose, same pose every time, fixed pose, boring mirrored pose, stiff pose, identical pose repetition, real person not matching shadow pose, text, watermark, logo, distorted body, extra limbs, extra fingers, bad hands

海边夕阳日系清透超写实女性人像

3:4 vertical, single ultra-realistic outdoor portrait photography, young adult Asian female, fair and transparent skin, delicate and natural facial features, real facial details, long black hair gently blown by the sea breeze, faint smile, gentle and comfortable temperament. The character wears a white loose shirt, paired with an off-white short skirt and simple thin-strap sandals, standing by the sea walkway guardrail. The sunset is setting on the sea level, the water surface has golden reflections, there are faint mountain shadows and a very small boat in the distance, the overall atmosphere is quiet, clean, and healing. The camera is a low-angle shot, but do not exaggerate touching the ground, no big foot perspective, no oversized feet, no wide-angle distortion. The character's full body is in the frame, the face is clear and natural, the features are real and beautiful, the figure is slim, and the proportions are stretched. The image retains a lot of sky and sea surface, letting the environment participate in the composition. The photography style is a combination of real life sense and Japanese-style transparency, sunset backlight, soft golden rim light on the edges of the hair strands, natural skin tone, retaining real skin texture, no excessive skin smoothing, no plastic face, no internet celebrity fake face, no manga feel, no 3D rendering, no text, no watermark.

红色丝绒巨型高跟鞋奢华时尚海报

"Cinematic high-fashion poster featuring a massive, 10-foot tall ruby-red velvet stiletto heel with gold filigree and a diamond-encrusted ankle strap. A beautiful woman in a matching floor-length silk red evening gown leans elegantly against the giant shoe. The setting is a palatial ballroom with marble floors, crystal chandeliers, and golden architecture. Sophisticated gold typography at the top reads 'VÉRITÉ - L’ÉLÉGANCE ROUGE' and at the bottom 'THE ICONIC RED STILETTO - A Statement of Pure Luxury'. Hyper-realistic, 8k resolution, luxury aesthetic."

城市门票微缩景观艺术插画

Create a highly detailed, premium travel-art illustration featuring a hand holding a [CITY-SPECIFIC TICKET/PASS] in the foreground. The ticket acts as a portal to [CITY NAME], with a realistic miniature city scene emerging from the ticket. A signature transportation element ([CITY VEHICLE]) breaks out of the ticket frame in 3D perspective, extending toward the viewer. Behind the ticket, one iconic landmark ([HERO LANDMARK]) rises prominently and realistically, becoming the main architectural focal point. Surrounding the scene are only 3–4 clean hand-drawn doodle elements representing the city's identity, such as district names, local symbols, or famous locations. Use minimal doodles, lots of negative space, and avoid clutter. Include tiny realistic people interacting with the scene, such as commuters, tourists, street vendors, cyclists, or photographers, scaled appropriately to create a miniature-world effect. Style: photorealistic travel photography combined with elegant black-ink sketchbook doodles. Clean composition, premium editorial design, soft warm lighting, shallow depth of field, realistic textures, subtle shadows, Instagram-worthy travel artwork. Composition hierarchy: 1. Emerging vehicle 2. Hero landmark 3. Ticket/pass 4. Minimal doodle elements Avoid: crowded layouts, excessive text, too many landmarks, busy backgrounds, duplicated symbols, excessive arrows, stickers, or decorative icons. Aspect ratio: 1:1 square. Quality: ultra-detailed, cinematic, sharp focus, professional travel poster aesthetic.

节奏之美：中国女性拳击训练商业海报

艺术感动感模糊电影质感人像大片

Intentional artistic motion-blur portrait, shot on a smartphone or long-exposure camera. Extreme close-up of a woman with a loose braided low bun and a long face-framing strand covering half her face. Looking down and to the side, one eye mostly hidden, lips slightly parted. Large statement gold earrings, bare shoulders, smooth glowing skin, soft peach blush, subtle highlighter, delicate makeup, defined lashes, matte dusty-rose lips with darker liner. Eye-level framing, face slightly right of center. Neutral light gray or white background. Soft natural window light, warm creamy golden tones. Strong intentional motion blur throughout the image, especially in the earrings and hair, with slightly sharper focus at the center of the face. Cinematic fashion editorial aesthetic, elegant, mysterious, atmospheric, minimal noise, soft contrast, warm color grading. Vertical 9:16.

仿生设计办公产品2x2概念展示板

2x2 grid, office products, 4 empires, 16:9 input ::= [product_domain] + [biological_source_set] + [panel_count] select concept_board from biomimicry_design_lab where domain = [product_domain] and product_count = ai_infer([panel_count], default="small family set") and pairing_logic = { mode: "one biological inspiration per product", biological_sources: [biological_source_set], product_types: ai_infer([product_domain], "distinct household or lifestyle devices"), mapping_rule: "match each product function with a biologically meaningful animal form" } and render_structure = { layout: "clean modular grid", panel_style: "one concept per panel", per_panel_content: [ "product name generated from animal + device logic", "category", "function", "hero product render", "feature callouts with leader lines", "small icon row for capabilities" ] } and industrial_design_language = { style: "premium contemporary consumer product concept art", materials: "matte polymers, brushed metals, soft-touch finishes", realism: "photoreal product visualization", environment: "minimal domestic surfaces" } and inference_rules = { do_not_copy_existing_objects: true, infer_form_from_animal_morphology: true, infer_features_from_behavior: true, infer_ui_elements_from_product type: true } and exclusions = [ "no fantasy creature styling", "no toy-like proportions unless functionally justified", "no random decoration", "no brand logos", "no collage inconsistency" ];

高明度电子印刷感城市图文海报

Centered around any subject object, presented as high-brightness, clean posters with a slight electronic printing feel integrating images and text. The visual forms an asymmetrical balance between a broad white space at the top and the subject image at the bottom: push the most recognizable entity or scene of the subject from the bottom toward the center, creating a clear sense of scale compression; edges retain a natural photographic texture, with parts crossing into the title area and obscuring a few letterforms, allowing text and imagery to interweave rather than being partitioned top and bottom. Add a layer of theme-derived forms close to the lens at the bottom, with edges heavily blurred and a translucent colored mist sweeping across the subject to create a lightweight foreground floating sensation, while the distant environment is compressed into a low-detail dark band. The entire frame is covered with extremely dense, uniformly thick horizontal fine lines that run through the white space, imagery, and text, appearing faintly in bright areas and clearly overlaid in dark parts, creating a texture where screen scanning meets fine mesh printing, while remaining bright and clean without stains or yellowing. The upper part uses a set of oversized English script as the strongest visual action, with long ascenders, descenders, and swirling ligatures spanning the width, creating intense tension through thin strokes and local heaviness; below and within it, high, thin, and condensed Chinese display characters with a strong vertical feel are embedded, with tall faces and dense structures; the two sets of typefaces cross through and overlap each other, leaving small breathing spaces and avoiding formal centering. Break down a small amount of theme information into short sentences, scattered around the edges and gaps of the main subject, using thin Song-style structures or high-contrast serif fonts to maintain a small font size, loose character spacing, and restrained line spacing; individual pieces of information enter thin elliptical frames or stay close to the edges, forming an editorial rhythm. Colors do not have fixed hues: extract a high-saturation accent color from the theme's mood, used centrally for the large titles, script writing, and fine line markers; establish a bright background with large areas of near-white or extremely light cool neutral colors; derive deeper, quieter support colors from the theme environment to press down on the lower image, while the main subject maintains soft light neutral colors, and vibrant colors echo only in the text and a few out-of-focus patches in the foreground. Keep the area of the accent color restrained, its brightness clear, and the overall color gamut clean, allowing the cool white space and vivid text to produce a sober yet poetic tension. Lighting uses soft diffused illumination, with transparent highlights and layers in the shadows; the image may have slight low-resolution sampling and horizontal line interference, but without adding grain, fading, or heavy shadows. The reading path is first captured by the script title spanning the top, then falls to the central subject object, and finally circles through the scattered short sentences to the bottom; the overall relationship of interwoven oversized script, high and thin Chinese characters, full-width scanning lines, and subject imagery must be maintained to avoid degrading into ordinary photographic layout. Subject: Good morning copy + good morning + Do's and Don'ts of the day + 2026-08-04 + classic city elements. A total of 10 different cities. Avoid identical color schemes, avoid identical hues, and avoid identical layouts. A total of 10 images.