Write once, run forever
A Skill captures the prompt engineering once. Every future run is just swapping variables — no copy-paste between models, no version drift.
162 community-built SKILLs you can run again and again. A SOLO Skill is one prompt + one output. A COMBO Skill chains 2–5 steps for richer multimodal pipelines. Pick one, swap variables, generate.
SOLO = single prompt, instant output. COMBO = 2–5 step pipeline (e.g. research → image → video).
Takes a user-uploaded portrait photo along with optional inputs (gender/age, hair texture, style preference, goals) and outputs a poster-quality hairstyle diagnosis report. The report includes geometric facial analysis overlays, 12 scientifically justified hairstyle recommendations with fit scores and rationale, a Top 3 conclusion, and a maintenance guide — styled for salon display, social sharing, or image consulting.
Takes 5 character parameters — character name, outfit style, primary color, shoe style, and color palette — and generates a professional ancient Chinese fantasy costume design reference sheet (角色设定图) rendered by GPT Image 2. Outputs a dark navy 3:2 widescreen infographic with 7 structured regions: identity block, full-body illustration, exploded outfit layers, accessory close-ups, shoe detail panel, three-view silhouettes, and color swatches. Ideal for game art pipelines, cosplay design, and fantasy character development.
Takes any theme, keyword, or short phrase as input and outputs a detailed GPT image generation prompt for a collector-grade LEGO brick-aesthetic typography concept poster. Automatically extracts core keywords, selects theme-aligned brick color palettes, derives visual metaphors, and composes multi-zone exhibition-style poster layouts. Ideal for designers, educators, brand creatives, and LEGO enthusiasts wanting typographic art concepts.
Takes a reference character image and a target year as input, then generates a single print-ready A4 portrait anime-style calendar poster. The output is a 3×4 grid showing all 12 months with accurate date grids, the character in 12 unique seasonal outfits and poses, watercolor pastel backgrounds, and hand-drawn doodle decorations. Ideal for fan art creators, kawaii merchandise designers, and personalized gift printing.
Transforms any city's metadata into a museum-quality vintage collectible postage stamp poster at 3:4 aspect ratio. Takes 8 user-supplied variables (city name, native script, air mail translation, denomination, issue year, coordinates/tagline, country, and stamp date) and outputs a richly detailed, anatomically authentic philatelic art poster in a 1950s–1970s lithograph aesthetic with perforated edges, postmark overlay, and retro travel-poster illustration.
Takes five brand identity variables (brand name, tagline, product type, accent color, hero voice-over line) and generates a single print-ready image via GPT Image 2 — a 12-panel cinematic storyboard arranged with labeled still-frame scenes, warm cream palette, 35mm film-grade aesthetics, and a branded footer. Ideal for luxury fragrance campaigns, editorial pitches, and high-end lifestyle brand presentations.
Recebe descrições textuais e parâmetros visuais (tema, estilo, iluminação, composição, formato) e gera prompts fotorrealistas e cinematográficos em inglês, otimizados para ferramentas de IA como GPT Image, Runway, Kling e Sora. Ideal para criadores de conteúdo, designers e profissionais de marketing que precisam de imagens e vídeos indistinguíveis da realidade.
Takes personal diary content (text narration, dated entries) and optional reference photos as input, then outputs structured comic panel sequences with cohesive visual generation prompts. Automatically segments diary events into panels, rewrites content in comic-style language, applies consistent character styling, and synthesizes ready-to-use image generation prompts. Ideal for turning daily journals into stylish illustrated comic diary pages.
Describe your fight scene — combatants, elemental powers, and mood — and get a director-ready 8-panel stick-figure storyboard prompt. Each frame includes motion trails, elemental FX, and cinematic camera directions. Perfect for manga artists, animators, and game designers who want to previs action sequences fast.
Takes subject photos, descriptions, scene details, and camera settings as inputs to generate hyper-detailed image. Recreates early 2000s/2010s consumer digital camera aesthetics with nested LCD-screen compositions, period-accurate UI overlays (timestamps, battery icons, mode indicators), and candid portrait styling. Ideal for nostalgic photography art, retro-style portrait generation, and era-accurate digital camera simulations.
Takes a reference photo and 6 user-defined variables (easel style, outdoor setting, outfit, caricature art style, and optional direction) to generate a single photorealistic image. The output portrays the subject sitting beside an easel displaying a recognizable caricature of themselves. Ideal for portrait artists, social media content creators, and editorial photography concepts.
Takes an uploaded anime character illustration plus dance style parameters and outputs a fully annotated, production-ready dance reference sheet prompt. Generates structured multi-panel layouts in Japanese anime design document style, including turnaround views, 6-step pose sequences, expression charts, hand gestures, footwork diagrams, and rhythm memos. Ideal for animators, idol game developers, and character designers.
Takes an uploaded character reference image and analyzes visible costume components, colors, aterials, and style. Outputs a structured multi-view costume breakdown sheet prompt ready for GPT Image generation, plus a reusable IP-neutral style template. Ideal for costume designers, concept artists, and game/anime creatives needing detailed garment reference sheets.
Takes a product name, optional product image (any quality), optional copywriting, and style/audience preferences as input. Outputs a publication-ready horizontal commercial banner image alongside a creative rationale and the raw generation prompt used. Ideal for e-commerce ads, social media banners, promotional campaigns, and retail display materials requiring agency-quality visuals without a design team.
Recebe tema educativo, região brasileira, descrição de cena e personagens ativos e gera storyboards completos de histórias em quadrinhos infantis. Produz prompts visuais em inglês para geração de imagem no estilo cartoon brasileiro (referência Turma da Mônica), diálogos em português do Brasil e notas pedagógicas integradas. Ideal para educadores, autores de livros infantis e criadores de conteúdo cultural brasileiro.
Takes a character group reference (image or text description) and generates a vivid, natural-language image generation prompt featuring all characters in a dynamic 'glancing back at the viewer' ensemble portrait composition. Supports 2–12 characters, multiple art styles, and customizable mood, setting, and color tone. Ideal for fan art, franchise portraits, family scenes, and team illustrations.
Users upload a casual headshot to generate professional ID/portrait photos in multiple styles (student, corporate, resume, etc.). The AI preserves original facial features, applies optional makeup and skin beautification, replaces backgrounds, and adapts clothing/collar to the chosen style. Suitable for visa photos, student IDs, resumes, and corporate profiles.
Takes a user-provided theme (e.g., cat, Mario, strawberry) along with style tone, color count, and complexity level, then outputs a high-resolution pixel-art style Perler/Hama bead pattern image. Features a single centered subject on a pure white background using 6–12 flat solid colors. Ideal for beginner and intermediate crafters looking to replicate patterns with physical Perler or fuse beads.
Transforms any city name into a premium editorial-style illustrated typography travel poster. Takes six inputs — city name, color palette, background color, tagline, descriptor words, and subtitle. Each letter of the city name becomes an illustrated window of local landmarks and culture, arranged in a 16:9 widescreen five-zone layout. Ideal for rapid multi-city poster generation with zero post-editing.
Takes an uploaded food photo plus brand and menu details, then outputs a ready-to-render GPT-Image prompt for a 2:3 vertical Food Hero Explainer Poster. Preserves the dish's original appearance while elevating it to premium commercial quality with brand zone, ingredients panel, selling points, price block, and social CTA row. Ideal for restaurant ads, delivery platforms, and social media campaigns.
Input a character description with accent and base colors to generate a professional 4K blueprint-style concept sheet featuring front/side/back tri-views, close-up detail inserts, and annotated component labels on a clean white background. Ideal for game design, animation, and concept art documentation.
Takes a user-uploaded themed Bingo card image and produces one shuffled variant by repositioning existing cell elements only. It extracts all cell contents (text, icons, colors, fonts), randomly reassigns their grid positions using a Fisher-Yates shuffle, and reconstructs a visually faithful output card. The FREE cell stays locked. No content is added, removed, or visually altered. Ideal for game hosts needing unique card variants from a master template.
Input a story brief and style preferences; output a fully assembled image prompt for a 3-panel comic strip with per-panel scene breakdowns, consistent characters, and style tags. Ideal for creators, educators, and storytellers who want quick visual narratives.
接收用户输入的修仙世界内容变量(报纸名称、主新闻标题、主视觉人物、第二新闻主题、萌宠栏目、底部广告),自动生成信息密集、多栏网格排版的竖版古风修仙报纸海报提示词。适用于AI绘图平台生成古代报纸风格的修仙幽默海报图像。
Takes a character reference image and styling preferences as input, then outputs detailed image-generation prompts for multiple outfit variants. Automatically extracts character traits (skin tone, hair, body type) from the uploaded image and locks them as a consistency anchor across all generated looks. Ideal for character designers, AI artists, game developers, and fashion concept creators who need structured, reusable outfit prompt templates.
Input any concept or knowledge topic, and this tool generates an American comic book-style image prompt featuring an original superhero explaining the concept. Outputs a structured prompt for AI image generation plus hero name, panel layout, and concept summary. Ideal for educators, content creators, and visual learners.
输入角色参考图或文字描述,输出适配Nano Banana 2模型的全维度角色深度解构卡提示词JSON,包含全身立绘、服装拆解、表情组、道具叙事、材质特写等多模块全景排版,适用于游戏/动漫角色设计手册制作场景。
Turn any product into a full visual pack: hero shot, 4 angle photos, a catchy tagline, and rich description copy — ready to publish anywhere.
Takes tactical FPS map parameters (map name, theme, view angle, key zones, art style, atmosphere, and special elements) and outputs a single fluent natural-language image generation prompt. Designed for CrossFire and Counter-Strike style map concept art, covering archetypes like desert, urban, industrial, and castle environments for use with AI image generators.
Upload a food photo and receive a vintage-style hand-drawn cookbook page complete with illustrated ingredients, kitchen tools, handwritten recipe text, and warm pastel aesthetics. Ideal for food bloggers, recipe creators, and nostalgic culinary art lovers.
Takes game parameters (type, theme, grid size, content type, card count, color mode) and generates a structured, print-ready game card image prompt. Supports Bingo, Word Bingo, Trivia Grids, and holiday variants. Outputs a natural-language image generation prompt optimized for GPT Image, with randomized cell content, column constraints, FREE space handling, and black-and-white print formatting for home printing on A4/Letter paper.
Input a travel destination, dates, landmarks, and decorative preferences to generate a richly detailed, photorealistic AI image prompt for a hand-drawn Traveler's Notebook spread with ink-and-watercolor aesthetics. Ideal for travel journalers, scrapbook designers, and AI art creators.
Input brand name, colors, products, and style details to generate a fully parameterized ultra-realistic miniature brand showroom image prompt. Outputs a complete final_prompt, negative_prompt, and model parameters optimized for 1:1 square-format commercial photography generation.
Takes user-provided male character details, Chinese fantasy scene elements, calligraphy text, and style preferences as inputs. Outputs an ultra-detailed English image generation prompt structured around a double exposure silhouette poster composition, blending ink wash aesthetics, xianxia architecture, eastern dragons, and anime art styles in a teal-green monochromatic mood. Ideal for game promo art, fantasy poster design, and Genshin-style fan art creation.
A complete multi-brand advertising campaign package covering ad copy, visual creatives, and video spots — designed for brands launching simultaneous campaigns across digital and social channels.
Takes a franchise character name and series as input, then automatically derives personality archetype, signature colors, pose style, and outfit redesign parameters to output a single cohesive natural-language image generation prompt. Produces vertical anime × streetwear × graphic poster prompts ready for GPT Image, ideal for fan art, creative campaigns, and character reimagining projects.
Takes a character name, visual description, and optional reference image as inputs, then generates a detailed GPT Image prompt for a collector-grade luxury anime commemorative stamp sheet featuring 6–9 emotionally distinct stamps. Each stamp includes gold foil borders, perforated edges, wax seals, postmarks, and serial numbers, with strict full-face visibility enforced across all stamps. Ideal for fan art collectors, anime merchandise designers, and philatelic-themed illustration projects.
参照画像(人物写真)をアップロードすると、顔・肌色・髪型などのアイデンティティを完全保持したまま、16枚のPixar風3D chibiキャラクタースタンプを4×4グリッドの統合画像として生成します。商業販売・SNS配布に対応した高品質出力が可能です。
Input a person, plant, or animal subject along with style preferences to generate a museum-grade scientific encyclopedia infographic. Outputs a single high-density illustrated panel with anamorphic 3D central subject, 6–8 annotated knowledge modules, leader-line networks, and aged-parchment aesthetic with calligraphic typography.
Input a character description, outfit details, and optional variant panel settings to generate a ready-to-submit multi-panel 3D Pixar-style character sheet prompt. Outputs a structured image generation prompt featuring a hero panel plus up to 6 variant panels with consistent face/hairstyle, cinematic lighting, and optional signature branding.
Upload a reference photo of any real person to generate a premium cinematic manga portrait. Preserves 100% facial identity (bone structure, expression, hair, mustache, costume, pose) while applying hyper-realistic manga stylization with dramatic cinematic lighting and dynamic black-and-white panel backgrounds. Output is a single 3:4 ratio image at 2K or 4K resolution.
A structured storyboard template that pairs scene descriptions with visual panels, ideal for film pre-production, animation planning, or creative pitches.
Input a food recipe with ingredients, sauces, and cooking methods to generate a structured Midjourney infographic prompt. Outputs a color-coded step-by-step visual diagram prompt with legend specs and panel layout, ideal for creating shareable recipe infographics.
上传参考图片,输入地点名称和时代设定,系统将生成具有对角线撕裂效果的双时代对比海报。左上层展示过去时代,右下层展示未来场景,撕裂边缘带有纸张质感和阴影效果,地点名称以跨时代字体横跨画面,适用于城市主题、文化对比、时空穿越等创意海报设计。
Takes a user's raw scene concept and optional parameters (camera movement, time of day, atmosphere, duration, resolution) and outputs a deployment-ready Studio Ghibli-style video generation prompt in JSON format, optimized for xAI Video (Grok) with Miyazaki's signature aesthetic.
Takes six broadcast scene parameters (sport type, match time, outfit, team colors, scoreboard text, and network logo) and outputs a photorealistic GPT Image 2 prompt plus a 16:9 freeze-frame still of a glamorous female spectator in a packed stadium crowd. Ideal for viral social content, cinematic sports edits, and AI video seed frames.
Takes a character reference image and optional styling hints to generate a fully scripted 16-frame 'Get Ready With Me — Outfit Edition' storyboard collage prompt. Outputs a high-fidelity image generation prompt for a 4×4 grid at 1080×1350px, along with detected visual style and character description. Ideal for content creators, illustrators, and fashion storyboard artists.
Takes a character's name and personality traits as input and outputs a single anime-style illustration of that character proudly holding an open sketchbook displaying their own hilariously idealized, personality-driven self-portrait. Useful for fan art creation, character visualization, creative writing companions, and anime-style OC (original character) showcases.
A structured lesson plan template for teachers covering subject, audience, grade level, and lesson type — with sections for rationale, objectives, key points, teaching methods, and the full instructional process.
Takes user-defined character features (hair, eyes, outfit, accessories, background, mood, color palette, typography) and outputs a production-ready Midjourney natural-language prompt for psychedelic anime album cover art. Ideal for creating Y2K retro-futurist Vocaloid/J-pop idol posters with maximalist superflat graphic design aesthetics and neon rave visuals.
Takes a creative theme idea and target audience (kids or adults) as input, then generates a print-ready black-and-white line art coloring page. Suitable for educators, parents, artists, and hobbyists who want custom coloring pages on demand.
Input a character concept with optional details (hair, eyes, outfit, accessories, pose, background) and receive a fully structured Midjourney/GPT Image prompt for a full-body kawaii streetwear anime character illustration, suitable for game or commercial art use.
장면 이름(빵집, 도서관 등)을 입력하면 등축(isometric 2.5D) 건축 단면 삽화용 프롬프트를 자동 생성합니다. 층별 레이아웃, 의인화 동물 캐릭터, 외부 환경까지 포함한 긍정/부정 프롬프트와 생성 파라미터를 JSON으로 출력합니다.
Upload a portrait photo to generate a hyper-realistic 8K split-face image: left half bathed in warm daytime sunlight with sunflowers and butterflies, right half in cool moonlit night with stars and moths. Ideal for artistic duality portraits and cinematic visual storytelling.
Transform a person's description or photo reference into a cinematic 3D scene where the subject dramatically breaks through a torn paper screen, surrounded by a realistic social media profile UI.
Takes a brand name (well-known or custom) along with mascot visuals, brand colors, and slogans, then outputs a hyper-detailed anime hypebeast streetwear commercial poster in a vertical Japanese ad layout. Ideal for marketers, streetwear brands, and creative agencies wanting culturally resonant, visually dominant brand poster concepts.
Takes an uploaded anime character reference image and optional style tone preference, then analyzes face shape, hair type, color, and aesthetic to generate 5 best hairstyles, 5 hairstyles to avoid, and 5 color palettes. Ideal for fan artists, character designers, and anime enthusiasts.
Converts interior space descriptions or reference images into clean 2D architectural blueprint floor plans. Input a room layout description and preferences; output a top-view technical drawing with walls, doors, furniture symbols, and optional dimensions in blueprint or black-white style.
Input a Langrisser II character name with optional faction, platform version, and layout preferences. Outputs structured image generation prompts for high-definition final-class portraits and class promotion tree diagrams, formatted as encyclopedia-style visual atlas entries faithful to the 1994 JRPG source art.
Input a reference image of a character, and output hand-drawn sketchbook-style character illustration prompts that retain the character's identity. Supports composite media such as colored pencils, ink lines, and cross-hatching, and automatically overlays comic book doodle decorative elements, suitable for character design, concept illustration, style transformation, and other scenarios.
Input product name, type, design style, and color preferences to generate high-fidelity web UI mockups. Outputs photorealistic, production-ready interface designs with proper layout hierarchy, component semantics, and brand identity. Suitable for SaaS apps, dashboards, landing pages, and e-commerce platforms.
生成《Vogue》风格的高对比度黑白肖像海报。支持文字描述或上传参考图(写实/二次元均可),自动转换为超写实时尚大片质感。适用于人像、人物与动物组合、时装概念等场景。
Takes character customization inputs (hair color, eye color, outfit color, slime color, and optional extra details) and outputs a fully structured Midjourney-ready prompt string. Designed for generating deadpan chibi vinyl figure poster illustrations with streetwear, slime drip, graffiti typography, and toxic kawaii aesthetics. Ideal for designer toy artists, streetwear creators, and urban kawaii illustrators.
输入参考图片或文字描述,生成植物大战僵尸风格的像素艺术图像。支持图生图像素化转换和文生图场景构建,自动融入PVZ经典植物角色作为装饰,适用于游戏风格创意图像生成场景。
用户上传一张图片并选择母语与目标学习语言,系统自动识别图中物品、人物、场景等元素,生成带有手写风格词汇标注(含词性、译文、发音)的沉浸式语言学习教学卡片,适用于词汇记忆与场景化语言学习。
Genera logotipos profesionales a partir de descripciones textuales. El usuario proporciona el nombre de marca, sector, estilo visual y preferencias de color; el sistema produce un logotipo optimizado, descripción de decisiones de diseño y variantes alternativas. Ideal para emprendedores, agencias y equipos de branding.
Upload your photo to receive a magazine-grade Before & After style upgrade report. The AI analyzes your look and generates a polished layout with upgraded outfit, layering, accessories, and styling — preserving your identity while delivering a visible, trend-forward transformation styled as a professional fashion stylist proposal board.
Upload a portrait reference image and configure scene, tone, and detail settings to generate an optimized cinematic double-exposure prompt. Outputs a photorealistic, city-fused portrait prompt with dual-tone color grading (warm orange/cyan), bokeh depth, and nano-model optimization for commercial-grade visual generation.
Upload a portrait photo to generate a cinematic dual-self composition where the real photorealistic subject and a warm hand-drawn cartoon twin share a quiet urban street moment. Ideal for social media, artistic self-portraits, and introspective visual storytelling.
用户上传产品包装参考图,输入品牌名、主色调、产品类型等参数,输出适配Nano Banana 2模型的英文3D磨砂半透明玻璃材质渲染提示词及模型配置,适用于高端商业产品可视化场景。
Input a subject name and optional reference images to generate a photorealistic technical infographic with white blueprint-style annotations, dimension callouts, sketch insets, and component labels. Ideal for product showcases, engineering visuals, and educational content.
输入人物或生物描述,自动生成专业的Midjourney全身画像提示词,支持30种场所(如城市、酒吧、学校等)、多风格、氛围选择,支持cosplay/纹身、自定义物种,智能调配1:1和9:16构图比例。
Input a theme (e.g., Animals, Christmas, Food) and visual style preferences to generate a print-ready 5x5 bingo card image. Outputs a high-resolution card with 24 unique themed items, each with an icon and text label, plus a FREE center cell. Ideal for classroom activities, party games, and educational use.
输入产品名称和语言偏好,自动识别产品类别与主色调,生成专业级液态玻璃风格Bento网格信息图(16:9,2K分辨率),包含8个模块卡片,适用于产品展示、电商详情页、营销物料制作场景。
Upload a portrait photo and input a gamer tag to generate a 16-bit retro arcade pixel-art character prompt. Preserves only face and hair likeness, reimagines outfit, hairstyle, accessories, and background as vibrant pixel-art spectacle. Outputs a ready-to-submit prompt for Nano Banana 2 image generation.
Takes product details, mascot description, screen type, and UI parameters as input, then outputs a production-ready gamified UI image prompt optimized for the Nano Banana 2 model, complete with variable map and model parameters for rapid product customization.
Takes a speaker name and AI model name as inputs, then generates a deployment-ready photorealistic press conference image prompt. Outputs a structured prompt string with branded stage elements, lighting directives, and resolution/aspect-ratio parameters. Ideal for AI product launch announcements and tech event media assets.
Upload a product image (jewelry, clothing, or accessory) along with style preferences to generate photorealistic virtual model showcase visuals. The system preserves product details, maps items onto anatomically accurate models with matched lighting, and outputs e-commerce-ready high-resolution images suitable for platform listings.
Input a knowledge topic and key points, output a warm Japanese healing-style scrapbook infographic (3:4 vertical, Morandi palette). Suitable for educators, content creators, and knowledge visualization needs.
Input a structure or world subject plus theme/color/zone parameters to generate a precision-engineered generative image prompt for publication-quality vertical cross-section infographics with dollhouse interior narrative density, archival parchment aesthetics, and strict typographic hierarchy.
Input a scientific subject (animal, plant, mineral, element, celestial body, etc.) and receive a publication-grade vertical infographic encyclopedia card. Combines natural history illustration aesthetics with modular encyclopedia typography, producing high-resolution, socially shareable, collectible-quality science visual cards.
Input a theme, illustration style, and character preferences to generate a complete print-ready paper doll set. Output is a high-resolution 1:1 square image featuring one base character, 3–6 interchangeable outfits with fold tabs, and matching accessories — suitable for children's products and Etsy commercial listings.
将概念性的角色、场景、道具描述转化为结构化的插画生成提示词。输入角色特征、道具、场景元素、文字内容和风格偏好,输出完整的英文提示词、视觉层级、风格标签和构图建议。适用于AI绘画工具(如Midjourney、DALL-E)的提示词创作场景。
Input a food/drink product name and category, select UI style and lighting preferences, and receive an optimized 4K image generation prompt featuring a POV supermarket scene with futuristic glassmorphism AR nutrition overlays. Ideal for pitch decks, social media, and retail tech demos.
Input character parameters (subject, outfit, action, expression) and receive an optimized black-and-white Notion-style editorial illustration prompt. Ideal for generating consistent monochrome character illustration series for productivity tools, documentation, and editorial design.
Takes a food concept (e.g., Malatang, Ramen, Bubble Tea) and optional parameters like gender, color palette, and cultural style, then outputs a fully structured, game-quality anime character design sheet prompt. Designed for use with GPT-image models, it generates multi-panel reference layouts covering turnaround views, expression sheets, outfit details, and color swatches for food personification characters.
Input any subject, concept, or knowledge point (with optional reference images and icon hints), and get a detailed English prompt for AI to generate a healing, 2D Japanese-style scrapbook infographic. Ideal for educators, designers, or knowledge visualization tasks.
Users upload a reference photo and select style preferences; the tool analyzes the image and generates an optimized Midjourney prompt to convert the photo into a clean black-and-white line drawing. Suitable for portraits, pets, landscapes, products, and architectural scenes.
A high-impact product video featuring a kiwi fruit exploding mid-air with vibrant green pulp and seeds scattering, culminating in a sharp Minute Maid Kiwi Juice bottle reveal. Designed for advertising and social media product promotion.
Input comic universe details (series name, heroes, villains, SFX text, year, resolution) to generate optimized image prompts for 3D vinyl toy pop-up diorama scenes rendered in open-book vintage comic style on a wooden desk. Outputs a final prompt, negative constraints, and scene weight summary for Nano Banana 2.
Input a restaurant brand name and business category (plus optional details like slogan, color, and style) to generate a professional English image prompt for a multi-touchpoint brand visual matrix board, along with an inferred brand profile summary. Ideal for restaurant branding, packaging design, and visual identity projects.
A dynamic video content blueprint for a beautiful girls live streaming showcase, featuring engaging intro clips and highlight reels optimized for social and streaming platforms.
Takes a subject, two gradient ink colors, resolution, and aspect ratio as inputs to generate optimized nano-model image generation prompts for fluid ink-flow fine art illustrations. Outputs a structured JSON with a finalized prompt, negative hints, and a style tag. Suitable for AI artists, designers, and illustrators seeking consistent minimalist ink aesthetics.
Upload a face photo to generate a hyper-realistic 3D caricature of the person bursting out of a cracked smartphone screen. Customize attire, held object, and background style. Outputs a 2K square image with cinematic lighting and exaggerated large-head caricature styling.
Upload a portrait photo to transform it into a dramatic street-art/pop-art silhouette poster. The tool preserves facial likeness while rendering a bold dark silhouette against a vibrant yellow background with expressive brushstrokes and splatter effects. Supports 1:1, 3:4, and 16:9 aspect ratios.
Generates a complete, print-ready children's game based on a user-specified theme and game type, including a fun title, 6–8 age-appropriate game items, clear play instructions, and a matching illustrated game card image.
基于用户上传的参考图像,生成一幅戏剧性风格的数字绘画肖像。画面采用黑白红黄四色配色,背景为抽象垂直分割的颜料条纹,突出人物向上凝视的坚定眼神和面部力量感。适合作为激励海报使用,输出高分辨率图像。
Input a reference scene image, location type, weather condition, and Kanto Pokémon ID to generate a new pixel RPG exploration scene. Maintains 45° isometric perspective continuity, applies unique weather effects, and places a non-repeating Gen I companion behind the player sprite. Ideal for Pokémon-style game scene creation and narrative progression.
Input an evolutionary theme (e.g., 'Western Art Development') and optional parameters like stage count or reference images. Outputs a 4K isometric pixel art museum timeline with bilingual labels, era-accurate symbolism, color palettes, and a stage manifest. Ideal for infographic design, visual storytelling, and academic illustration.
Upload a building model or sketch image and configure style, material, lighting, and environment options to generate a photorealistic architectural exterior rendering. Ideal for architects, designers, and developers needing high-quality proposal visuals with accurate geometry preservation.
Takes a user-uploaded portrait photo plus occasion details (signpost destinations, cake message, outfit/props, resolution) and outputs a hyper-detailed, studio-quality image generation prompt that fuses the real person's facial likeness into a photorealistic beach-themed birthday cake scene with miniature figurine topper.
Input an astronomy topic and diagram preferences (type, audience level, resolution, aspect ratio, accent color, scale reference), and receive a structured image generation prompt with layout zones, label coverage, and style tags for science education illustrations.
Input a topic and optional content for each of 9 grid cells; output a 3:4 vertical nine-grid poster optimized for Xiaohongshu (Little Red Book) with minimalist skeuomorphic illustration style, creamy-beige palette, and large readable typography. Ideal for female-oriented lifestyle, wellness, and beauty content creators.
输入人物描述、风格偏好和参考图片,输出结构化的图像生成提示词。专注于电影级肖像摄影,包含精准的灯光、构图、氛围控制。适用于AI绘画工具(如Midjourney/Stable Diffusion)的专业级人物肖像创作场景。
Input brand assets (logo URL, product image, brand colors, and campaign details) to generate photorealistic 16:9 luxury advertising visuals meeting LV/Celine/Bottega Veneta CGI standards. Outputs production-ready ad images with precise logo, product, watermark, and typography placement, plus a layout confirmation report.
Upload a portrait photo and article title to generate stylized 16:9 header images. The tool reconstructs the person in multiple AI art styles and color schemes, composing a blog/note-ready banner with the title text on the left and the figure on the right.
Input an animal species, outfit style, and holiday theme to generate photorealistic, child-friendly felted wool animal character illustrations. Outputs a studio-quality image with authentic fiber texture, matte diffuse lighting, and hand-crafted aesthetics. Ideal for IP creation, seasonal greeting cards, and children's content.
Input a brand name and color to generate a photorealistic CGI prompt for a 3D inflatable graffiti-style type sculpture. Outputs a Midjourney/SDXL-compatible image prompt featuring Wildstyle letter fusion, asymmetric spike eruptions, monochromatic latex material, and pure white studio staging.
Transform any subject into a brand-ready 3D matte clay icon. Input a character, pose, emotion, and color palette; receive a ready-to-submit image generation prompt with style enforcement tokens and variable summary. Ideal for app icons, sticker sets, and consistent character series.
输入品牌名称和产品类型(服装/食品/汽车/科技),自动生成工业DIY美学的多层拼贴海报AI提示词。输出包含中英双语完整场景描述、3D产品渲染、撕裂纸质照片堆叠、物理纹理样本和品牌图形元素,支持1K/2K/4K分辨率及多种宽高比,适配Nano Banana 2模型规范。适用于品牌方快速生成专业级海报视觉方案。
输入服装风格、促销文案和可选人脸图片,输出商业级超写实时尚广告海报。支持换脸融合、精确排版控制和影棚级灯光渲染。适用于电商促销、品牌宣传、杂志广告等场景。
上传一张角色画像,为其生成具有代表性的专属金句卡,排版参考名人语录风格(16:9 2K,Nano)。
用户上传照片并指定风格、文字等参数,AI自动识别图像主体,生成符合印刷规格的明信片正面设计稿,输出包含渲染提示词、图像参数及文字区域坐标的结构化JSON,适用于旅行纪念、节日祝福等个性化明信片制作场景。
Input a healing stationery brand name or series theme; outputs a detailed English flat lay mockup image prompt plus layout description. Ideal for cultural creative merchandise sets (20+ products) with dreamy forest/moon/animal aesthetics, ready for AI image generation tools.
Input a Chinese character and style preferences (font style, grid type, paper texture) to generate a print-ready 5-cell calligraphy practice template image prompt. Cell 1 shows the reference character, cell 2 shows a ghost tracing guide, and cells 3–5 are blank practice spaces.
Input a notable person's name and optional style preferences; output a detailed, editorial-grade infographic poster image prompt featuring a photorealistic/illustrative central portrait, career timelines, product references, annotated callouts, and bold graphic design elements. Ideal for tribute posters, educational visuals, and editorial design.
Input a brand name, campaign theme, and plush character name to generate a complete, advertising-grade image generation prompt for a commercial campaign poster featuring a plush/stuffed character. Suitable for brand marketing, seasonal campaigns, and IP character promotions.
Input a sacred beast theme (Azure Dragon/White Tiger/Vermilion Bird/Black Tortoise/Qilin) and visual state (activated/static) to generate a production-ready image prompt for a traditional Chinese Five Elements card border with protected center blank zone.
Input city, location, museum name, designer, style preference, and color scheme to generate a complete A1 exhibition panel prompt for a High-Tech/Modernist public art museum, including a bird's-eye rendering and full architectural analysis diagrams at 3 PM lighting.
Input a city name, its iconic landmarks, and a promotional slogan to generate a production-ready image prompt for a city poster. Output includes a detailed English prompt featuring S-curve silk composition, double-exposure scroll transition and ink-wash landmark illustration — optimized for AI image generation.
Upload any everyday photo and receive a cozy, journal-style annotated image prompt. The system detects visible elements, generates warm handwritten English captions (≤6 words each), maps semantic decorations (steam, stars, hearts, arrows), and assembles a complete image generation prompt that overlays thin white one-stroke outlines and dashed arrow guides over the original photograph.
Upload a portrait photo and provide persona details to generate a photorealistic LinkedIn profile card UI mockup prompt. Outputs a full image generation prompt preserving the character's facial likeness within a circular avatar frame, complete with LinkedIn UI elements (name, title, skills, endorsements, connections) in the official blue-white color scheme.
Input any domain (DevOps, UI Design, Data Science…) and get a prompt for a dense grid poster of real, brand-accurate tool icons on a 1:1/3:2/2:3 canvas. GPT Image 2 fits as many verified tools as the frame allows.
输入产品名称和语言偏好,自动分析产品类别与主色调,输出可直接提交给图像生成模型的液态玻璃Bento风格16:9产品信息图提示词,适用于电商、营销、产品展示场景。
Input a game concept with theme, component type, paper size, and age group to generate print-ready tabletop game component images (boards, cards, tokens, score sheets) optimized for home printing with cut guides and CMYK-safe colors.
User uploads a base photo and provides graffiti customization options (tag text, creature descriptions, colors, symbols). The AI overlays a 90s NYC sticker-bomb graffiti illustration layer on top of the preserved realistic photo, outputting a composite zine-style poster at 1080×1350px with a layer placement description.
Input a subject, color palette, and headline text to generate a cinematic 9:16 vertical poster collage featuring four stacked rounded-rectangle background panels with distinct poses and a bold white-outlined foreground cutout figure. Ideal for fashion, branding, and editorial design.
Input character details for up to 4 panels (subject, outfit, color palette, vibe) plus global style and effects preferences. Outputs a single ready-to-submit image generation prompt for a cinematic diagonal 4-panel split-screen action collage with manga-inspired borders and photorealistic render quality.
Input a food item name and output settings to generate a precision-crafted exploded vertical infographic prompt. Ideal for commercial food photography AI generation, producing layered ingredient breakdowns with studio lighting, infographic labels, and high-fidelity texture descriptors for nano generative models.
Input a brand name and optional details (iconic product, colors, staff uniform, scene props) to generate a publication-ready Cinema 4D-style 3D chibi miniature concept store image prompt. Outputs a complete image generation prompt, style tags, and brand color palette. Ideal for social media creatives, brand campaigns, and concept visualization.
Input a country name and preferences to generate a cohesive kawaii chibi-style sticker sheet featuring iconic food, landmarks, and traditional objects. Outputs a high-resolution, print-ready sticker sheet with pastel colors, glossy finish, and die-cut outlines. Ideal for sticker printing, digital use, or cultural merchandise design.
Takes structured daily journal inputs (date, mood, events, quotes, style preferences) and renders them into beautifully formatted, handwritten-style planner pages. Supports multiple aesthetic styles (Hobonichi, TN, Bullet Journal) and outputs either a styled Markdown journal page or an image-ready layout description. Ideal for personal planners, travel journals, and daily reflection pages.
Input a reference portrait image and travel destination details to generate a photorealistic editorial travel composite prompt. Outputs an identity-locked, cinematic scene-building prompt suitable for luxury magazine-grade image generation, including terrain maps, landmarks, floating props, and typography overlays.
Input a subject, two pastel colors, resolution, and aspect ratio to generate an optimized image prompt for large-scale chalk pastel mural art. Outputs a structured prompt with style tags, color blending logic, and composition notes. Ideal for street art, mural design, and textured wall art creation.
Input a city name and optional parameters (landmark count, resolution, reference images) to generate a hyper-detailed isometric 3D diorama image prompt. Output includes a final prompt, negative hints, and model optimization notes for AI image generation tools.
Input a profession name and optional reference images to generate an 8K ultra-photorealistic cinematic freeze-frame of that professional slipping on a banana peel mid-air, surrounded by 10–15 floating profession-specific props, with meme-grade comedic aesthetics. Ideal for humorous occupational content, social media memes, and viral visual storytelling.
Input a superhero name and optional settings to generate a cinematic image of the character physically tearing through their vintage comic book page into the real world, complete with era-accurate art style, 3D sound effects, and matching desk environment.
Input a country name and optional settings to generate a hyper-realistic 3D travel guide infographic poster. Outputs a detailed image-generation prompt featuring raised terrain maps, miniature landmark models at accurate coordinates, national flag, decorative travel props, and editorial typography. Ideal for travel brands, content creators, and designers.
Input a subject, decorative elements, and two accent colors to generate an optimized image generation prompt for cute flat vector cartoon illustrations on black backgrounds. Ideal for AI art tools creating two-tone symbolic icons and character illustrations.
Accepts character descriptors (subject, action, emotion, colors) and outputs optimized image generation prompts in a unified 3D kneaded-clay icon style. Ideal for app icons, stickers, and IP character design. Returns a structured JSON with final_prompt and render parameters.
Input a subject and two contrast colors to generate an optimized pop surrealism image prompt. Outputs a nano-model-ready prompt (≤120 tokens) with style tags, color logic, and dreamlike narrative elements. Ideal for AI image generation with hyper-saturated, exaggerated visual aesthetics.
Takes a product name, character style, colors, and structural mechanic as input, then outputs a fully optimized image prompt for generating high-end creative packaging mockups where the box structure and cartoon character expression form a unified face illusion visual system.
Takes a product name, background description, aspect ratio, and resolution as inputs, then outputs a studio-grade advertising prompt ready for high-fidelity image generation. Ideal for commercial packshot photography of luxury goods, skincare, beverages, electronics, and fashion accessories.
Upload a portrait photo to generate a hyper-realistic 8K cinematic image where a miniature dancing version of yourself stands on your smartphone screen. Uses forced perspective illusion, 50mm lens bokeh, and natural outdoor lighting. Ideal for creative social media portraits and artistic self-expression.
Input a city name and rendering parameters (resolution, lighting, cloud density, aspect ratio) to generate a photorealistic infinity-loop (∞) tiny planet aerial drone image with accurate geographic landmarks, waterways, and road networks. Ideal for cinematic city visualization and aerial art creation.
Converts a portrait photo into a high-fidelity dark monochrome engraving illustration. Users upload a reference image and select style, palette, lighting, and resolution options. Output is a cinematic 9:16 vertical portrait with classical printmaking textures, crosshatching, and gothic dark-fantasy atmosphere.
Input a brief scene description to generate a photorealistic Japanese TV program screenshot. The AI automatically infers program type (news, variety, talk show, documentary), composes contextually accurate Japanese on-screen text (headlines, subtitles, banners), and renders authentic broadcast-style visuals with overlays. Ideal for creative projects, mockups, and entertainment content.
Takes a product name and packaging type as primary inputs, along with optional brand tone, resolution, and aspect ratio, then outputs a portfolio-grade industrial packaging design board prompt featuring a central 3D hero render, six technical views, dieline layout, dimension annotations, and style tags — ready for Nano Banana 2 image generation.
Upload a box dieline reference image and input brand/product details to generate a print-ready flat packaging layout with all panels visible, graphic design applied across every face, and full CMYK compliance. Ideal for packaging designers and brand teams.
Input beauty product details (bottle material, cap color, liquid color, ingredients) and receive an optimized AI image generation prompt for luxurious, layered infographic visuals. Ideal for high-end skincare and cosmetic brand content creation.
输入海报主题、受众、风格、视觉元素、情感基调等参数,输出可直接驱动图像生成模型的英文提示词、中文说明、推荐分辨率与比例及风格标签。适用于教育活动、节日庆典、校园展览等场景的海报设计。
用户输入车辆参考图或车型名称,并描述情景(如雨夜追车),系统生成符合GTA5线上模式风格的英文图像生成提示词,输出包含完整提示词、风格标签和模型参数的JSON对象,适用于AI图像生成场景。
输入人物特征(性别、发型、服装、表情等)和风格需求,自动生成符合电影摄影标准的赛博朋克人像提示词,适用于AI图像生成工具。输出中英双语提示词、负面提示词和技术参数,支持参考图智能提取视觉元素。
输入Logo文本和风格偏好,自动生成符合AI图像模型规范的专业提示词。支持热血战斗、缤纷流行、恐怖惊悚、赛博朋克四种风格,可自定义分辨率、比例和背景色,输出包含正向/负向提示词的完整指令集。
基于用户输入/上传参考图,生成通用化提示词工程,以下文提示词为公式模板,生成工程:“ 创作一张 [2:3] 海报,海报中心呈对角线撕裂,展现京都两个截然不同的时代。在左上方撕裂的图层中,展示 1920
根据用户描述或参考图,生成一组时尚大片风格的三联画作品。用户可自定义人物特征、服装风格、场景氛围和超现实元素。系统将生成高质量的多格构图图片,适用于时尚摄影、品牌宣传、艺术创作等场景。
专为创作电影级奇幻骑士场景设计的提示词工程。用户输入场景描述和风格偏好,系统生成符合 Nano Banana 2 模型规范的高质量提示词,支持自定义画面比例、分辨率、参考图和氛围设定,适用于电影概念设计、游戏美术、奇幻插画等专业创作场景。
基于用户上传的角色参考图和文本描述,生成电影级微距摄影场景:数十个微型角色在巨大的开放漫画书上协作创作自己的故事。支持自定义角色动作、漫画风格、光照氛围等参数,输出高精度的角色一致性画面,适用于创意视觉叙事、角色IP衍生内容、艺术摄影作品等场景。
A Skill captures the prompt engineering once. Every future run is just swapping variables — no copy-paste between models, no version drift.
COMBO Skills chain text + image + video steps with cross-step references. The hard wiring is done — you just hit Run.
Download originals at full resolution. No watermark, commercial use OK. Forking a Skill makes a private copy you can edit and re-publish.
Browse SOLO or COMBO Skills above. Each card shows what kind of output to expect.
Subject, style, length — only the meaningful inputs are exposed. The prompt structure stays locked-in.
SOLO returns in seconds. COMBO runs each step in sequence with progress visible per step. Outputs are yours.
A SOLO Skill is a single prompt template tuned for one model — one input, one output. A COMBO Skill is a 2–5 step pipeline that wires multiple models together (e.g. research the topic, generate a hero image, then turn it into a 10-second video). The library shows both side-by-side; the colored pill on each card tells you which type it is.
No. Camika provides access to GPT Image 2, Nano Banana Pro, Seedance, xAI, Suno, and others through one account. Sign in with email or Google to try them — each generation costs a few credits depending on model.
Yes. After signing in you can fork any Skill or build a new one in the Workshop. SOLO Skills publish from the Workshop SOLO tab; COMBO Skills come out of the Workshop COMBO builder. Once published they appear in the public library here.
A pasted prompt is text. A Skill is a parameterized template that runs against a specific model with the right defaults (aspect ratio, sampler, length cap). It's also versioned, has run statistics, and — for COMBO — carries the multi-step plumbing.
Yes. Outputs you generate on Camika are yours to use commercially per each underlying model's content policy. No watermark is added.
Skills are tuned and re-benchmarked when underlying models change. The community library surfaces the most-used Skills first; lower-performing Skills get pruned. Forking a Skill makes a frozen copy you control — pin it to today's behavior if you depend on exact output.
Sign up free. No card required.
Create free account