MMCPMarkets
YO

youmind-openlab/awesome-gpt-image-2

Developer tools
8,8 тыс. stars Качество 85 Тренд 85
Repository Install

💡 🎬 Take it further with — pair GPT Image 2 stills with Seedance for jaw-dropping AI videos, 2000+ prompts to explore 👉 awesome-seedance-2-prompts

Обзор

💡 🎬 Take it further with — pair GPT Image 2 stills with Seedance for jaw-dropping AI videos, 2000+ prompts to explore 👉 awesome-seedance-2-prompts

README

💡 🎬 Take it further with Seedance 2 — pair GPT Image 2 stills with Seedance for jaw-dropping AI videos, 2000+ prompts to explore 👉 awesome-seedance-2-prompts

🚀 Awesome GPT Image 2 Prompts

🎨 A curated collection of creative prompts for OpenAI’s GPT Image 2

⚠️ Copyright Notice: All prompts are collected from the community for educational purposes. If you believe any content infringes on your rights, please open an issue and we will remove it promptly.

🌐 View in Web Gallery

👉 Browse on YouMind GPT Image 2 Prompts Gallery

Why use our gallery?

Feature GitHub README youmind.com Gallery
🎨 Visual Layout Linear list Beautiful Masonry Grid
🔍 Search Ctrl+F only Full-text search with filters
🤖 AI One-Click Generation - AI one-click generation
📱 Mobile Basic Fully responsive
🏷️ Categories - Category browsing

🏷️ Browse by Category

📖 Table of Contents

🤔 What is GPT Image 2?

GPT Image 2 (codename “duct-tape”) is OpenAI’s next-generation image model. Community testing highlights a leap in these areas:

  • 🎯 Pixel-Perfect Text Rendering — Native-quality text in Chinese, English, and Japanese, no typos or warped glyphs
  • 🎨 Cross-Image Consistency — The same character, style, or IP stays identical across a series, down to the pixel
  • ⚡ Commercial-Grade Illustration — Illustration output is ready to ship without manual polish
  • 🌈 True Art Style Induction — Creatively evokes the feeling of a style rather than merely approximating references
  • 🔧 Storyboard & Product Series — Ideal for storyboards, IP characters, and multi-panel product visuals
  • 📐 Multi-Language Design — Social cards, banners, and posters with accurate multilingual typography in one shot

📚 Learn More: See community testing in our report summary

🚀 Raycast Integration

Some prompts support dynamic arguments using Raycast Snippets syntax. Look for the 🚀 Raycast Friendly badge!

Example:

A quote card with "{argument name="quote" default="Stay hungry, stay foolish"}"
by {argument name="author" default="Steve Jobs"}

When used in Raycast, you can dynamically replace the arguments for quick iterations!

📊 Statistics

🔥 Featured Prompts

⭐ Hand-picked by our team for exceptional quality and creativity

No. 1: VR Headset Exploded View Poster

📖 Description

Generates a high-tech exploded view diagram of a VR headset with detailed component callouts and promotional text.

📝 Prompt

{
  "type": "exploded view product diagram poster",
  "subject": "VR headset",
  "style": "clean high-tech 3D render, studio lighting, glowing accents",
  "background": "{argument name=\"background color\" default=\"soft purple and blue gradient\"}",
  "header": {
    "logo": "∞ {argument name=\"product name\" default=\"Meta Quest 3\"}",
    "subtitle": "{argument name=\"main catchphrase\" default=\"まったく新しい現実を、まったく新しい構造から。\"}"
  },
  "layout": {
    "centerpiece": "vertically stacked exploded view of a VR headset showing 9 distinct layers of internal components: outer shell, camera sensors, motherboard with chip, pancake lenses, internal frame, battery packs, side straps, top strap, and facial interface cushion.",
    "callout_labels": {
      "count": 8,
      "left_side": [
        "Snapdragon® XR2 Gen 2\n圧倒的な処理性能でリアルタイムな体験を。",
        "調整可能なIPD機構\n幅広いユーザーに快適なフィット感を。",
        "精密設計されたヘッドストラップ\n快適さと安定性を追求したエルゴノミクス。"
      ],
      "right_side": [
        "フェイスプレート\n洗練されたデザインと最適な重量バランス。",
        "トラッキングカメラ\n高精度な位置トラッキングと環境認識を実現。",
        "パンケーキレンズ\n薄型設計で広い視野角と鮮明な映像を提供。",
        "高性能バッテリー\n長時間駆動を支える最適化された電源設計。",
        "柔らかなフェイスインターフェース\n長時間でも快適な装着感を実現。"
      ]
    },
    "footer": {
      "left_text_block": {
        "headline": "{argument name=\"bottom headline\" default=\"体験は、構造から進化する。\"}",
        "body": "一つひとつのパーツに、没入体験を支える最先端テクノロジーとこだわりの設計。Meta Quest 3は、未来を感じさせる体験を内部から生み出しています。"
      },
      "right_logo": "∞ Meta"
    }
  }
}

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 2: Illustrated City Food Map

📖 Description

Generates a hand-drawn, watercolor-style tourist map featuring numbered local food specialties, landmarks, and a legend.

📝 Prompt

{
  "type": "illustrated map infographic",
  "style": "{argument name=\"art style\" default=\"watercolor and ink hand-drawn illustration on vintage parchment\"}",
  "title_section": {
    "text": "{argument name=\"city name\" default=\"成都\"} {argument name=\"map title\" default=\"吃货暴走地图\"}",
    "mascot": "cartoon red chili pepper wearing sunglasses and giving a thumbs up"
  },
  "border": "{argument name=\"border decoration\" default=\"vine of green leaves and red chili peppers\"}",
  "layout": {
    "background": "textured beige parchment paper with yellow roads, blue rivers, and green park areas",
    "sections": [
      {
        "title": "landmarks",
        "count": 6,
        "illustrations": ["traditional pavilion", "traditional monastery", "modern skyscraper with climbing panda", "tall TV tower", "traditional gate", "industrial buildings"],
        "labels": ["人民公园", "文殊院", "IFS", "339电视塔", "宽窄巷子", "东郊记忆"]
      },
      {
        "title": "food_spots",
        "count": 12,
        "illustrations": ["mapo tofu", "dumplings in chili oil", "skewers in pot", "sticky rice balls", "egg baking cake", "nine-grid hotpot", "sweet potato noodles", "cold skewers", "spicy mixed dish", "covered tea bowl", "ice jelly dessert", "spicy rabbit heads"],
        "labels": ["1 陈麻婆豆腐", "2 钟水饺", "3 春熙路", "4 宽窄巷子·三大炮", "5 建设路·叶婆婆蛋烘糕", "6 玉林路·小龙坎火锅", "7 香香巷·肥肠粉", "8 武侯祠大街·钵钵鸡", "9 东郊记忆·冒椒火辣", "10 人民公园·鹤鸣茶社", "11 锦里古街·冰粉", "12 双流老妈兔头"]
      },
      {
        "title": "图例",
        "position": "bottom-right",
        "count": 5,
        "items": ["red dot", "green house", "green tree", "blue line", "yellow double line"],
        "labels": ["美食地点", "地标景点", "公园绿地", "河流湖泊", "主要道路"]
      }
    ],
    "centerpiece": "giant panda sitting and eating bamboo",
    "bottom_right_extras": ["vintage compass rose with N, S, E, W", "disclaimer text '温馨提示：吃辣需谨慎，肠胃要保护~' with a red chili pepper icon"]
  }
}

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 3: Momotaro Explainer Slide in Hybrid Style

📖 Description

A prompt that combines the simple, warm aesthetic of Irasutoya illustrations with the high-information density characteristic of Japanese government slides.

📝 Prompt

Create an explanatory slide ({argument name="format" default="ponchi-e diagram"}) for {argument name="theme" default="Momotaro"} that fuses the gentle atmosphere of "Irasutoya" with the overwhelming information density of "Kasumigaseki slides".

🖼️ Generated Images

Image 1
Image 2

📌 Details

👉 Try it now →

No. 4: E-commerce Live Stream UI Mockup

📖 Description

Generates a realistic social media live stream interface overlaying a portrait, featuring customizable chat messages, gift popups, and a product purchase card.

📝 Prompt

{
  "type": "live stream UI mockup",
  "subject": {
    "description": "portrait of {argument name=\"host name\" default=\"Elon Musk\"}, smiling, wearing a black t-shirt with a white technical schematic graphic",
    "background": "left side shows a screen with '{argument name=\"left background logo\" default=\"SPACEX\"}' text, right side shows a red '{argument name=\"right background logo\" default=\"Tesla T logo\"}' and a dark car"
  },
  "ui_overlay": {
    "top_header": {
      "host_info": "avatar, name '{argument name=\"host name\" default=\"Elon Musk\"}', subtext '55.6万本场点赞', red '关注' button",
      "rank_badge": "gold coin icon with '全站第1名'",
      "viewer_stats": "3 top viewer avatars with '12.3w', '8.6w', '5.7w', total '68.7万', 'X' close button",
      "right_links": "'更多直播 >', '礼物展馆 0/24' with blue '经典' tag"
    },
    "mid_left_gifts": {
      "count": 2,
      "items": [
        "avatar '科技爱好者', '送小心心', heart icon x 1314",
        "avatar '星辰大海', '送火箭', rocket icon x 666"
      ]
    },
    "bottom_left_chat": {
      "system_message": "level 37 badge '宇宙漫游者 加入了直播间'",
      "message_count": 7,
      "messages": [
        "小火箭: 马斯克！未来可期！🚀",
        "future: 特斯拉Model 2什么时候出？",
        "星空梦想家: SpaceX今年能上火星吗？",
        "AI探索者: Neuralink进展如何？",
        "帅气的网友: 马总好！",
        "Mars: 第一次来你的直播，超激动！",
        "用户123: 讲讲AI吧，会取代人类吗？"
      ]
    },
    "bottom_right_product_card": {
      "hot_tag": "orange '热卖 x 1888'",
      "image": "Tesla Cybertruck",
      "title": "{argument name=\"product name\" default=\"特斯拉Cybertruck 电动皮卡\"}",
      "price": "{argument name=\"product price\" default=\"¥ 1,618,000\"}",
      "button": "red '抢' button",
      "floating_animation": "translucent hearts floating up the right edge"
    },
    "bottom_bar": {
      "input_field": "'说点什么...'",
      "icons": ["smiley face", "three dots", "shopping cart", "gift box", "share"]
    }
  }
}

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 5: Anime Martial Arts Battle Illustration

📖 Description

Generates a dynamic, high-impact anime illustration of two female characters fighting in a traditional dojo with elemental energy effects.

📝 Prompt

An anime-style illustration of a {argument name="action type" default="high-impact martial arts battle"} between two young female fighters in a {argument name="setting" default="traditional wooden martial arts dojo"}. In the foreground, a girl with black hair in a high bun wears a {argument name="character 1 color theme" default="red and white"} Chinese-style martial arts outfit with baggy pants. She is in a dynamic, low, forward-thrusting stance, surrounded by swirling red energy and water splashes. In the background to the right, a girl with light purple hair in twin buns wears a {argument name="character 2 color theme" default="green and purple"} Chinese dress with gold embroidery and black tights. She is leaping through the air in a flying kick pose, surrounded by swirling blue energy. The wooden floorboards are splintering from the intense impact, with debris and dust flying through the air. Above them hangs a weathered wooden sign with the text "{argument name="sign text" default="武術会"}". The scene features dramatic lighting, a low-angle dynamic perspective, and intense action effects.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 6: 3D Stone Staircase Evolution Infographic

📖 Description

Transforms a flat evolutionary timeline into a realistic 3D stone staircase infographic with detailed organism renders and structured side panels.

📝 Prompt

{
  "type": "evolutionary timeline infographic",
  "instruction": "Using REFERENCE_0 as a structural base, transform the flat vector design into a highly realistic 3D infographic. Replace the smooth ramps with distinct stone steps and upgrade all organisms to photorealistic 3D models.",
  "style": {
    "background": "{argument name=\"background style\" default=\"vintage textured parchment paper\"}",
    "staircase": "{argument name=\"staircase material\" default=\"realistic textured stone blocks\"}",
    "subjects": "{argument name=\"organism style\" default=\"highly detailed photorealistic 3D renders\"}"
  },
  "layout": {
    "main_title": "{argument name=\"main title\" default=\"人类演化\"}",
    "sections": [
      {
        "position": "left sidebar",
        "count": 8,
        "labels": ["L0: 单细胞生命", "L1: 多细胞生物", "L2: 动物界", "L3: 脊索动物", "L4: 上陆革命", "L5: 哺乳纲", "L6: 人科演化", "L7: 智人纪元"]
      },
      {
        "position": "top right",
        "title": "获得的功能 / 失去的功能",
        "description": "Legend with plus and minus icons"
      },
      {
        "position": "bottom center",
        "title": "演化关键里程碑",
        "count": 6,
        "description": "Timeline with a silhouette graphic of 6 figures showing ape-to-human evolution"
      }
    ],
    "centerpiece": {
      "description": "Winding stone staircase with 25 numbered steps featuring specific organisms.",
      "count": 25,
      "notable_elements": [
        "Step 07: Jellyfish",
        "Step 09: Ammonite",
        "Step 10: Trilobite",
        "Step 24: Walking human",
        "Step 25: {argument name=\"future evolution concept\" default=\"glowing cosmic silhouette with a question mark\"}"
      ]
    }
  }
}

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

📋 All Prompts

📝 Sorted by publish date (newest first)

No. 1: Profile / Avatar - Candid Nighttime Flash Photography Portrait

📖 Description

A prompt for generating spontaneous, high-ISO flash photography with a Y2K digital camera aesthetic, featuring a subject in a moody urban setting.

📝 Prompt

A candid nighttime street portrait of a young woman with long black hair wearing oversized rectangular glasses and a dark brown oversized knit sweater. She raises her hand toward the camera, partially covering her face, creating a playful "no photos" pose. Shot with an iPhone flash, featuring strong motion blur, soft focus, cinematic low-light atmosphere, glossy white tiled wall on the side, dark urban street with distant streetlights, Y2K aesthetic, natural skin tones, moody, spontaneous, unedited, 35mm flash photography, high ISO, authentic nightlife vibes, vertical composition (9:16). A candid flash photo of a young woman at night wearing a blue-and-white striped puff-sleeve dress. She smiles subtly while covering part of her face with her hand, creating a playful and shy expression. Captured with direct iPhone flash and intentional motion blur, soft focus, glossy tiled wall beside her, dark city sidewalk with blurred streetlights in the background, nostalgic 2000s digital camera aesthetic, cinematic, natural lighting, realistic skin texture, casual street photography, dreamy nightlife mood, vertical composition (9:16). Candid nighttime flash photography, direct iPhone flash, motion blur, soft focus, playful hand covering the face, glossy tiled wall, dark city street, blurred streetlights, authentic street photography, Y2K digital camera aesthetic, nostalgic, cinematic, realistic, natural skin tones, shallow depth of field, unedited, spontaneous moment, high ISO, grainy, vertical 9:16.

🖼️ Generated Images

Image 1
Image 2

📌 Details

👉 Try it now →

No. 2: Profile / Avatar - Luxury Boutique Hotel Mirror Selfie

📖 Description

A sophisticated prompt for generating a high-end fashion mirror selfie in a luxury boutique hotel elevator, featuring a Korean female idol in a denim romper.

📝 Prompt

Authentic luxury mirror selfie inside a {argument name="setting" default="contemporary boutique hotel elevator"} during a quiet afternoon. An exceptionally beautiful {argument name="subject" default="Korean female idol"} stands naturally in front of a brushed stainless-steel mirror wearing an {argument name="clothing" default="strapless light-wash denim corset romper"} with a sculpted waistline and structured tailoring, decorative flap pockets, taupe suede knee-high boots. Platinum-blonde hair with soft movement and delicate flyaway strands, hydrated skin with visible pores, minimal Korean editorial makeup, calm introspective expression. Boutique hotel elevator with brushed steel walls, smoked bronze mirror panels, walnut trim, stone flooring, brass accents, warm architectural LED lighting, subtle daylight entering through opening doors, quiet luxury atmosphere. Documentary-fashion hybrid inspired by Mark Borthwick, Mario Sorrenti, Cass Bird, Lachlan Bailey, and Vogue Korea. Hasselblad X2D, 50–55mm lens, f/1.2, shallow depth of field, creamy cinematic bokeh, Kodak Portra 400 and Kodak Vision3 250D color science, Boutique Hotel Neutral LUT, authentic optical rendering, urban travel fashion diary, lived-in elegance, captured rather than generated, 3:4 aspect ratio.

🖼️ Generated Images

Image 1
Image 2

📌 Details

👉 Try it now →

No. 3: Profile / Avatar - Car Interior Selfie Portrait Photography

📖 Description

A comprehensive prompt for generating a high-quality smartphone-style selfie of a woman in a car interior, focusing on realistic skin texture, lighting, and natural depth of field.

📝 Prompt

Theme:
{argument name="theme" default="heat through the lens"}

Subject:
{argument name="aspect ratio" default="portrait 3:4"}. In a bright daytime car interior, a woman sits sideways on the rear seat, extending one arm toward a smartphone to take a selfie. The person occupies a large portion of the screen from the center to the right, with the face and upper body as the main focus, while including part of the waist and thighs. Leave a wide space on the left for the black seat and the green outside the window.

Character and Expression:
{argument name="character profile" default="Bright ivory-beige skin with pale pink complexion and natural texture. Delicate highlights on cheeks, nose tip, shoulders, and collarbone. Rose pink blush, pink-brown eyeshadow, long thin eyelashes, natural eye bags, soft light brown eyebrows, and sheer pink-beige lip gloss. Tilting the head slightly to the left, looking at the camera through thin champagne-brown lenses. Lips slightly open, tip of the tongue slightly touching the lower bottom lip, a mature expression that isn't too provocative."} ...

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 4: Profile / Avatar - Urban Balcony Editorial Portrait

📖 Description

An editorial fashion portrait of a young woman on a high-rise balcony with a cinematic city skyline backdrop.

📝 Prompt

Ultra-realistic portrait of a beautiful young {argument name="ethnicity" default="East Asian"} woman standing on a high-rise balcony overlooking a modern city skyline during soft daylight. She has long, slightly messy dark brown hair, natural makeup, and a calm expression while looking directly at the camera. She is wearing a {argument name="clothing" default="white ribbed crop top"}, light blue denim jeans with a visible Calvin Klein waistband, and an oversized white shirt draped off her shoulders. Cinematic lighting, shallow depth of field, soft gray tones, photorealistic skin texture, editorial fashion photography, {argument name="lens type" default="85mm"} lens, bokeh background, luxury magazine aesthetic, subtle sparkle effects around the subject, highly detailed, 8K, vertical composition (3:4).

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 5: Profile / Avatar - Cinematic Face Reference Portrait

📖 Description

A high-detail cinematic portrait prompt designed to work with an uploaded face reference, emphasizing fabric textures and sunset lighting.

📝 Prompt

Use the uploaded face as the exact facial reference and preserve all facial features, skin tone, hairstyle, and identity. Create a cinematic low-angle portrait shot on a 50mm lens with a shallow depth of field and realistic lighting. The man is casually leaning against a weathered concrete railing with both elbows resting on it. He is wearing a {argument name="clothing material" default="premium black silk"} shalwar kameez with the sleeves rolled up, {argument name="accessory" default="dark rectangular sunglasses"}, a white wristwatch on his left wrist, and a stylish chain bracelet on his right wrist. He is looking upward toward the right with a calm, confident expression. The background features a {argument name="time of day" default="golden-yellow sunset"} with warm cinematic light, soft bokeh, and subtle lens flare. Ultra-realistic, highly detailed skin texture, natural color grading, HDR, professional photography, sharp focus on the face, 8K resolution, premium editorial portrait, dramatic composition.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 6: Profile / Avatar - Sunglasses Interior Fashion Portrait

📖 Description

A sophisticated prompt for an indoor fashion portrait of a woman wearing sunglasses, with a focus on lighting and material textures.

📝 Prompt

Theme:
{argument name="theme" default="gaze through sunglasses"}

Subject:
Depict a mature woman relaxing in a bright indoor setting. A vertical fashion portrait showing the person from the top of the head to below the waist, positioned slightly to the right of center. A mature, well-proportioned figure with a slim waist and natural feminine curves.

Character and Expression:
{argument name="character profile" default="Dark brown short bob. Hair ends move naturally in and out below the chin, with thin see-through bangs over the forehead. Elegant Japanese-style makeup with brown eyeshadow, thin eyeliner, delicate lashes, pale coral pink blush, and matte pink-beige lips."} Tilting the head slightly left, staring straight at the camera from under brown lenses. A modest, confident smile on the lips.

Clothing and Pose:
{argument name="outfit" default="An ivory fine-ribbed knit camisole crop top. Deep V-line but the chest is naturally covered, clearly showing the stretch and seams of the soft knit."} The bottom is a matching room-wear style design. The person raises her right hand to the front of her face, lightly pushing down the bridge of the sunglasses with the tip of her index finger. The other fingers are naturally bent. The left arm is extended to the lower right, resting weight as if supporting the seat. The upper body is slightly tilted to the right, and the waist is gently twisted in the opposite direction.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 7: Profile / Avatar - Soft Japanese Lifestyle Portrait

📖 Description

A photorealistic prompt for a gentle and minimalist indoor portrait of a woman, featuring soft natural lighting and realistic skin details in a Japanese lifestyle aesthetic.

📝 Prompt

{argument name="subject" default="A young adult East Asian woman"} sitting in {argument name="setting" default="a minimalist white interior space"}, medium close-up to half-body composition, centered slightly left. Body leaning slightly forward, shoulders naturally inward, arms forward, pose is quiet, relaxed, and slightly fragile. Head slightly tilted, facing the camera, gaze is calm, soft, and slightly detached, lips naturally parted, no obvious smile.

Exquisite soft oval face, almond-shaped dark brown eyes, natural thin eyebrows, slender bridge of the nose, light nude pink lips. Very light makeup, only natural eyelashes, slight eyeliner, and soft blush. Fair warm skin tone, retaining real pores, fine peach fuzz, natural skin variations, soft highlights, and light shadows, no plastic smoothing.

Deep dark brown long hair, naturally loose, voluminous with slight messy waves. Fluffy but real hair strands, with some wisps falling on forehead, eyes, cheeks, neck, and chest, creating a casual, unstyled home texture.

She wears {argument name="clothing" default="a thin white loose shirt"}, buttons partially undone, fabric soft and slightly wrinkled with a light semi-transparent gauzy feel; collar and one shoulder naturally sliding off, revealing neck, collarbone, and a white spaghetti strap camisole underneath. Overall clothing is fresh, clean, and subtle, not overexposed.

Background is a minimalist white or light gray wall, no clutter, quiet and clean space. Light is soft natural window light or high-key studio diffused light, coming from the front left, very shallow shadows, overall low saturation and low contrast, dominated by cream white, light gray, and natural skin tones. Photography style: 85mm portrait lens, f/1.8, shallow depth of field, eyes and face in focus, soft background blur, slight film grain, real photographic texture, Japanese soft lifestyle portrait, photorealistic.

Avoid: Cartoon, CG, illustration, over-smoothing, heavy makeup, exaggerated expressions, exaggerated body, wrong fingers, deformed arms, messy background, strong HDR, over-sharpening, text, watermarks, logos.

🖼️ Generated Images

Image 1
Image 2
Image 3

📌 Details

👉 Try it now →

No. 8: Profile / Avatar - Seaside Shoreline Portrait

📖 Description

A highly descriptive prompt for a realistic portrait of a woman on a rocky beach, featuring intricate details of skin, water droplets, and natural lighting.

📝 Prompt

Theme:
{argument name="theme" default="profile cloaked in the tide"}

Subject:
A realistic 3:4 portrait of a woman in her 20s standing on a rocky beach. The person is placed slightly to the right of the center, captured from the top of the head to the waist bone. The upper body occupies about 70% of the screen, with the arm and blue sea on the left, and a blurred rocky area on the lower right.

Character and Expression:
Bright ivory-beige skin with natural pale pink color. Realistic skin texture with small glints on cheeks, nose tip, shoulders, and collarbone, showing pores and fine texture. Pale rose blush, champagne beige and pink-brown eye makeup, long thin eyelashes, natural eye bags, soft light brown eyebrows, and sheer pink-beige lips. A neat profile facing right, chin slightly tucked, gaze cast diagonally downward. Mouth lightly closed with a quiet and calm expression.

Clothing and Pose:
{argument name="outfit" default="An ivory triangle bikini with a delicate woven pattern. Thin shoulder and side straps follow the skin naturally, with light tension and fine wrinkles in the fabric."} The body is twisted about 30 degrees to the right, with the left shoulder slightly forward. The left arm is lowered near the waist with the elbow loosely bent. The abdomen is naturally extended, and the center of gravity between the shoulders, ribcage, and hips is continuous.

Environment and Light:
{argument name="environment" default="A clear coastal day. The foreground is the person, the middle ground is the dark blue sea surface, and the background is an out-of-focus rocky reef and low coastline. Strong warm sunlight from the top left illuminates the forehead, bridge of the nose, shoulders, chest, and left side of the abdomen."} Soft blue reflections from the sky and sea are added on the opposite side, maintaining three-dimensionality without overly hard shadows. Fine water droplets are scattered on the skin and hair.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 9: Profile / Avatar - Rooftop Sheer Blouse Portrait

📖 Description

A high-end fashion photography prompt for a woman in a sheer blouse on a city rooftop, featuring backlighting and a bright blue sky background.

📝 Prompt

Theme:
{argument name="theme" default="white cloaked in the sky"}

Subject:
A mature woman standing on a rooftop in a sunny city. The person is placed slightly to the right of center, captured from the top of the head to the thighs. The body occupies about 70% of the screen, looking quietly down at the low-positioned camera.

Character and Expression:
Bright skin with a natural complexion, sophisticated facial features. Sophisticated Japanese-style makeup with pink-beige lips, pale rose blush, thin brown eyeliner, and eyelashes that emphasize length without being overdone. Dark brown shoulder-length bob with thin bangs and layers around the face, hair ends and loose hairs swaying in the wind. Chin slightly tucked, looking at the lens with a calm, mature gaze, lips slightly open.

Clothing and Pose:
{argument name="outfit" default="A lightly sheer ivory white blouse. Soft, not-too-deep V-neck, loose long sleeves, thin cuffs. Paired with a simple skin-toned beige camisole underneath, with just enough transparency for the chest and body silhouette to look elegant."} Bottom is a pale ecru high-waisted pleated mini skirt. Upper body slightly tilted forward, shoulders relaxed, arms naturally lowered at sides. The thin fabric of the blouse and skirt hem sway gently in the wind, creating natural folds and shadows around the waist.

Environment and Light:
{argument name="environment" default="A rooftop of an urban apartment building. Metal fence at waist height, low-rise residential and apartment buildings in the distance, no text or logos. Most of the background is a vivid blue sky and three-dimensional white cumulus clouds. Warm backlighting from the low sun at the bottom left edges the hair, cheeks, neck, and thin blouse fabric in gold."} Soft reflected light from the sky and rooftop floor fills the face. One small circular lens flare is left near the waist.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 10: Profile / Avatar - Window Lit East Asian Portrait

📖 Description

A realistic vertical portrait prompt for creating an intimate indoor window-lit photo of a young woman with natural hair and soft expression.

📝 Prompt

Create a photorealistic vertical 3:4 portrait of a young East Asian woman with {argument name="hair color" default="natural deep brown"} long hair, slightly messy loose strands, and realistic airy texture. She sits indoors beside a bright window on the left, leaning slightly forward with one forearm resting across the lower frame and her other hand lifted near her hair in a delicate relaxed gesture. She looks directly at the viewer with calm, subtly alluring eyes, a soft neutral expression, natural makeup, smooth fair skin, softly defined brows, small nose, and slightly parted rosy lips. She wears a fitted {argument name="top color" default="black"} short-sleeve low scoop-neck top and a white lace choker with a small cross pendant. Use warm natural window light from the left, soft shadows on the right side of her face, gentle highlights in the hair, shallow depth of field, realistic skin texture, and a muted beige-gray wall background with a visible window ledge. Frame from upper torso to head, centered slightly right, intimate editorial portrait style, high-resolution DSLR realism, no hat, no glasses, no text, no watermark, no extra people.

🖼️ Generated Images

Image 1
Image 2
Image 3
Image 4

📌 Details

👉 Try it now →

No. 11: Profile / Avatar - Profile Portrait with Red Candy

📖 Description

A mood-driven prompt for an indoor portrait of a woman sitting on a bed, holding a red lollipop, emphasizing soft natural light and a doll-like aesthetic.

📝 Prompt

Subject:
{argument name="subject" default="Profile through a candy"}

Main Character:
{argument name="main character" default="Vertical 3:4. An adult woman sitting on a bed in a bedroom with soft natural light"}, placed large in the center-right of the screen. Medium-close view from the top of the head to below the thighs. The person occupies most of the frame, showing both legs in the foreground, depicting the moment she silently looks to the side with a red lollipop on her stick against her lips.

Person/Expression:
Bright ivory-beige skin with a smooth texture containing a hint of pink flush. Delicate highlights on the cheeks, nose tip, shoulders, collarbones, and legs. Makeup is elegant doll-like Japanese style, with pale rose pink blush, champagne beige and pink brown eyeshadow, long thin eyelashes, natural tear bags, light brown soft eyebrows, and glossy pink-beige lips. Small, clear catchlights in the eyes. Face is slightly toward the front, with only the eyes drifting to the left, showing a calm, contemplative expression. Hair is bright milk tea ash brown medium-long. Thin see-through bangs, layers along the face, ends curled loosely inward, with natural bundles and fine stray hairs, meticulously drawing soft gloss.

Clothing/Pose:
A room dress with thin shoulder straps and small floral patterns scattered on a pale ivory background. The chest has a shallow V-line with fine lace trim, gathers in the center, and a small ribbon, naturally reconstructed as a different design with a similar vibe. Without overemphasizing exposure, it depicts the soft drape of the fabric and natural wrinkles along the body. The person sits on the bed with both legs out and slightly bent. She holds the white stick of the candy with her own right hand, and the red candy is lightly touching the center of her lower bottom lip. Her left hand is on the bed by her side, slightly supporting her upper body. Shoulders are relaxed, and the overall physique is supple and mature.

Background/Light:
A white window frame and windowsill shelf on the left of the screen, with a transparent glass vase on top holding pale pink and white small flowers. The bed has pale floral patterned sheets and pillows. The background is a beige wall with few unnecessary items, creating a quiet and lived-in interior. The main light source is soft morning-to-midday natural light coming from the top-left window. Warm light hits the left cheek, shoulder, arm, hair surface, and legs, with shadows falling gently on the right and inside the body. The overall tone is based on cream, beige, and pale pink, with the red candy as a small focal point of color.

Composition/Camera:
Vertical 3:4. Camera is at an almost eye-level position, slightly higher than the person's chest. Face is placed in the upper center, with legs largely in the foreground to create depth. The window and vase are tucked into the left edge, leaving some margin in the direction her gaze is headed. Natural perspective around 50mm, with sharp focus on the face, eyes, candy, and fingertips, while the background is softly blurred.

Texture/Style:
Natural and high-quality indoor portrait photography. Soft film-like atmosphere, low contrast, warm color temperature, and delicate skin texture depiction. Meticulously expresses each strand of hair, fine patterns on the floral fabric, reflections on the glass vase, and the transparent gloss of the candy surface. Avoids excessive skin correction, resulting in a quiet and intimate finish like a magazine room portrait.

Negative:
Young-looking face, unnatural gaze, extra fingers, missing fingers, fused fingers, broken limbs or joints, poor contact between candy and lips/fingers, unnatural gravity, incorrect perspective, shadows inconsistent with the light source, overexposure, excessive skin correction, plastic-like skin, garbled text, logo, watermark.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 12: Profile / Avatar - Shh Finger on Lips Beauty Portrait

📖 Description

A minimalist beauty portrait prompt featuring a woman making a ‘quiet’ gesture, emphasizing soft lighting, ivory tones, and high-end photographic quality.

📝 Prompt

Subject:
{argument name="subject" default="Finger touching lips"}

Main Character:
{argument name="main character" default="A photorealistic vertical 3:4 portrait of a single woman sitting on the floor in a bright room"}. The person is placed center-right, captured from the top of the head to the thighs. The upper body occupies about two-thirds of the frame, with the face, fingertips, and chest naturally drawing the eye.

Person/Expression:
A natural and realistic individual with a calm, mature femininity. Hair is a short milk tea brown bob ending at the chin, with thin clumped bangs and fine stray hairs along the cheeks. Pale rose blush, pink-brown eye makeup, delicate long eyelashes, and sheer pink-beige lips. Head is slightly tilted to the left, looking at the camera with a quiet and somewhat suggestive expression.

Clothing/Pose:
A halter-neck dress with small ivory pleats, tied at the neck. Shoulders and arms are exposed, showing a silhouette with a naturally full, mature feminine bust line and soft body curves. No gloves. A 'shh' gesture where she bends her right elbow and stands her right index finger vertically to lightly touch the center of her lips. Other fingers are relaxed and naturally bent. The left arm is extended from the front of the body toward the knees in a stable sitting posture with one knee slightly raised. Accurately depicts the contact between finger and lip, and the overlapping of shoulders, arms, and chest.

Background/Light:
A minimal interior unified in white and pale beige. A large window in the back left, and a white vase with blurred small plants in the back right. The background is bright and organized, with no text or logos. Soft midday natural light enters from the top-left window, creating faint highlights on the forehead, bridge of the nose, cheeks, shoulders, collarbones, and arms. Shadows fall thinly to the bottom right, with shadows also lifted gently by reflections from the white floor.

Composition/Camera:
Vertical 3:4. A light low-angle shot from slightly below chest height, with the natural compression of an 85mm portrait lens. Face is in the upper center, fingertips right in front of the face, and the chest in the lower center. Narrow margin above the head, leaving a bright space for the window on the left. Focus on the eyes and lips, with the background largely and softly blurred. Avoid excessive wide-angle distortion.

Texture/Style:
A clean, high-brightness Japanese beauty photo. Soft gradations, low contrast, and a color palette centered on ivory and pale pink. Skin is not made too uniform, naturally leaving fine pores, vellus hair, cheek flush, and lip moisture. Meticulously expresses each strand of hair, the thinness of the pleated fabric, and the delicacy of fingertips and nails.

Negative:
Young-looking face, unnatural facial features, unnatural gaze, excessively exaggerated physique, extra fingers, missing fingers, fused fingers, poor contact between lips and fingers, broken joints, confusion of left and right arms, incorrect perspective, shadows inconsistent with the light source, plastic-like skin, excessive skin correction, garbled text, logo, watermark.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 13: Profile / Avatar - Chibi Purple Space Girl

📖 Description

Generates a cute chibi anime girl sitting on a purple planet against a mostly empty black cosmic background, suitable for avatars or hidden-reveal visuals.

📝 Prompt

Create a vertical 9:16 anime illustration with a vast nearly pure black empty sky occupying most of the canvas and a tiny cute chibi girl placed near the bottom center. The character is {argument name="character type" default="a small anime-style female avatar"} with oversized sparkling purple eyes, a surprised open-mouth expression, soft blush, and long fluffy {argument name="hair color" default="lavender-purple hair with peach-pink highlights"} that curls around her shoulders. She wears a dark purple space-inspired hoodie or dress with subtle orange trim, white socks, and purple shoes, and has a small rounded purple hair clip with little star sparkles on one side. She sits on the curved edge of a large purple-orange planet at the very bottom of the image, hugging {argument name="plush toy" default="a cute purple teddy-bear-like plush with black bead eyes and a small orange-purple triangular nose"}. Add exactly two small yellow star-shaped cushions or star charms on the planet, one to the left of the girl and one to the right. Use a dreamy kawaii chibi style, soft glossy shading, pastel violet and warm peach highlights, delicate rim light, crisp clean edges, and a transparent-feeling black cosmic background with no visible text, no logo, no border, and no extra characters. Keep the girl small in scale with abundant empty space above her, centered horizontally and positioned in the lower fifth of the canvas.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 14: Profile / Avatar - Sunlight Contours Indoor Portrait

📖 Description

A highly detailed cinematic prompt for a 2:3 vertical indoor portrait featuring a young woman by a summer window at sunset, focusing on lighting, shadows, and realistic textures.

📝 Prompt

Theme:
{argument name="theme" default="Contours of Sunlight"}

Subject:
A vertical 2:3 indoor portrait. A young adult woman sits quietly by a summer window in the center of the frame. Capture from the face down to the chest, arms, and one bent knee, with the person occupying about 80% of the screen. Focus on her gaze and face while clearly showing the streaks of light falling on her shoulders and arms.

Person/Expression:
Fair ivory-beige skin with a pale pink flush and natural texture. Delicate highlights on cheeks, tip of nose, lips, shoulders, and collarbone. Pale rose pink blush, champagne beige and pink brown eyeshadow, long slender eyelashes, natural tear troughs, soft light brown eyebrows, and sheer pink beige gloss lips. Lips are slightly parted, head tilted slightly to the right, looking at the camera with calm eyes. Small, clear catchlights in the eyes.

Clothing/Pose:
{argument name="clothing" default="Layer an ivory lace camisole with thin straps under a thin, sheer gown"}. The gown falls naturally from both shoulders, creating soft drapes on the outside of the arms. Lean the upper body slightly forward and bring both arms toward the front of the body. Include one bent knee in the lower left of the frame, showing natural tension and fine wrinkles in the thin fabric of the clothing. Dainty gold necklace and long dangling earrings.

Background/Light:
A quiet interior with a wooden-framed window in a blend of Japanese and Western styles. In the background, place wooden furniture, glass bottles, and small houseplants out of focus. Strong evening sunlight shines through the window at the top left at a low angle, casting long narrow window frame shadows diagonally across her forehead, cheeks, neck, shoulders, and arms. The light is a deep amber; lit areas are bright and glossy, while the shadow side sinks into deep brown. Add golden rim lighting to the silhouette of the hair and leave warm reflected light in the background.

Composition/Camera:
Vertical 2:3, medium close-up leaning toward bust-up. Place the face slightly above the center of the frame, with a small margin at the top of the head and the chest and one knee at the bottom. The camera looks down gently from a position slightly higher than eye level. 85mm equivalent portrait lens, shallow depth of field. Focus on both eyes and lips, softening the background. Vividly depict the three-dimensionality of the face, window shadows, and the flow of hair.

Texture/Style:
Realistic fashion portrait. Cinematic color grading centered on warm tones. Skin is not overly uniform, naturally retaining pores and fine peach fuzz. Hair is {argument name="hair color" default="bright milk tea ash brown"}, with thin see-through bangs, face-framing layers, and medium-long length below the shoulders. Ends are loosely curled inward, with fine highlights, a soft sheen, and naturally rendered stray hairs. Clearly differentiate the material textures of delicate lace, thin fabric, and metal accessories.

Negative:
Unnatural face, unnatural gaze, asymmetrical eyes, extra fingers, missing fingers, fused limbs, broken joints, unnatural contact between clothing and body, floating accessories, incorrect perspective, shadows inconsistent with the light source, excessive skin correction, plastic-like skin, text, logos, watermarks.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 15: Profile / Avatar - Paris Balcony Selfie

📖 Description

A photorealistic lifestyle prompt for creating a red-haired woman taking a breakfast selfie on a Paris balcony with the Eiffel Tower behind her.

📝 Prompt

Create a photorealistic wide-angle selfie on a Parisian apartment balcony in warm morning sunlight. A young woman with {argument name="hair color" default="vivid red"} shoulder-length wavy hair, fair skin, blue-green eyes, subtle makeup, and a gentle confident smile holds the camera with her left arm extended toward the viewer, creating strong close-up foreground arm perspective. She wears a fitted short-sleeve {argument name="dress color" default="deep royal blue"} dress and holds a clear glass of orange juice in her right hand at waist level. The background shows an elegant Haussmann-style Paris street with cream stone buildings, wrought-iron balcony railing, leafy green trees, and the Eiffel Tower visible in the distance on the left, softly out of focus. On the right side of the balcony is a small round marble café table with exactly 5 visible breakfast items: 1 vase filled with white daisies, 1 white espresso cup on a saucer, 1 cappuccino cup on a saucer with latte foam, 1 golden croissant on a small plate, and 1 woven café chair behind the table. Use natural golden-hour lighting, realistic skin texture, crisp facial detail, shallow depth of field, vibrant but believable colors, elegant travel lifestyle photography, vertical 4:5 composition, no text, no watermark, no extra people.

🖼️ Generated Images

Image 1
Image 2

📌 Details

👉 Try it now →

No. 16: Profile / Avatar - Minimal Hand-Drawn Sketch Watercolor Portrait

📖 Description

A complex structured prompt for a museum-quality hybrid of pencil illustration and watercolor painting, designed for luxury editorial portraits with a creative and sophisticated mood.

📝 Prompt

{ "title": "Universal_SketchPortrait_Identity_v1", "style": { "type": "Premium Hand-Drawn Sketch + Watercolor Portrait", "genre": "Editorial Fine Art", "quality": "Ultra HD 8K", "render_engine": "Photorealistic + Pencil Illustration Hybrid", "detail_level": "Maximum", "color_palette": { "primary": [ "#1F1F1F", "#F5F2EC", "#C77B3F", "#D6D2CC" ], "accent": [ "#8A8A8A", "#B48A62" ] }, "finish": "Museum Quality", "look": "Luxury Minimal Editorial" }, "subject": { "gender": "{argument name="gender" default="Unisex"}", "age": "{argument name="age range" default="18-35"}","ethnicity": "Universal", "body_type": "Average", "expression": "Calm, Thoughtful, Confident", "eye_direction": "Looking Left", "pose": { "angle": "Three Quarter Profile", "head_rotation": "35° Left", "camera_position": "Eye Level", "hand_position": "Right Hand Supporting Chin", "shoulders": "Relaxed" }, "hair": { "length": "Medium", "style": "{argument name="hair style" default="Naturally Messy"}", "texture": "Curly / Wavy", "color": "Dark Brown to Black" }, "facial_features": { "jawline": "Defined", "skin_texture": "Natural","facial_hair": "Optional Light Beard / Clean Shave", "nose": "Natural", "lips": "Neutral" } }, "outfit": { "upper": { "type": "Polo Shirt", "fit": "Regular", "color": "#2B2B2B", "collar": "White Contrast", "sleeves": "Half" }, "accessories": { "headphones": { "type": "Over Ear", "material": "Metal + Leather", "color": "Silver" }, "eyewear": { "type": "Black Sunglasses", "lens": "Dark Tint" } } }, "art_style": { "base": "Pencil Sketch", "secondary": "Ink Cross-Hatching","painting": "Soft Watercolor Wash", "line_style": { "type": "Loose Expressive Lines", "density": "High", "random_sketch_marks": true }, "brushwork": { "style": "Traditional Illustration", "texture": "Paper Grain Visible" } }, "lighting": { "type": "Soft Natural Daylight", "direction": "Front Left", "contrast": "Medium", "shadow": "Soft", "highlights": "Natural Skin Highlights" }, "background": { "type": "Minimal Paper", "color": "#F6F2EB", "texture": "Fine Watercolor Paper", "elements": ["Abstract Pencil Strokes", "Ink Splatters", "Loose Construction Lines" ], "depth": "Flat Minimal" }, "composition": { "aspect_ratio": "4:5", "framing": "Upper Body Portrait", "subject_alignment": "Center", "negative_space": "Large", "cropping": "Chest Up" }, "camera": { "lens": "85mm Portrait", "focus": "Face", "depth_of_field": "Shallow", "sharpness": "Ultra Sharp" }, "materials": { "paper": "Cold Press Watercolor Paper", "pencil": "Graphite 2B-8B", "ink": "Fine Liner","paint": "Transparent Watercolor" }, "render_settings": { "resolution": "8192x12288", "sampling": "Maximum", "dynamic_range": "High", "noise": "Very Low", "texture_quality": "Ultra" }, "mood": { "keywords": [ "Creative", "Minimal", "Elegant", "Modern", "Editorial", "Calm", "Artistic", "Sophisticated" ] }, "negative_prompt": [ "Low quality", "Blurry", "Low resolution", "Extra fingers", "Extra hands", "Extra limbs", "Bad anatomy", "Deformed face", "Crossed eyes", "Duplicate accessories" ] }

🖼️ Generated Images

Image 1
Image 2

📌 Details

👉 Try it now →

No. 17: Profile / Avatar - Sunny Beach Portrait of a Smiling Woman

📖 Description

A comprehensive prompt for generating a photorealistic portrait of a young woman at the beach, focusing on natural textures, summer lighting, and a friendly expression.

📝 Prompt

Subject:
{argument name="subject" default="Smile at the water's edge"}

Main Character:
{argument name="main character" default="A vertical portrait of a woman in her 20s standing on a sunny beach, captured from the top of her head to her upper thighs"}. The person is placed large in the center of the frame, with her upper body occupying about two-thirds of the screen. Set against a background of clear blue sea, white waves, and a bright sandy beach, she is turning a friendly smile toward the camera.

Person/Expression:
Bright ivory-beige fair skin with a subtle pink natural flush. Delicate highlights on the cheeks, tip of the nose, shoulders, and collarbones, with a realistic skin texture that leaves slight pores and texture. Pale rose pink blush, champagne beige and pink-brown eye makeup, long slender eyelashes, natural tear bags, soft brown eyebrows, and sheer pink-beige gloss lips. Small, clear catchlights in the eyes. A bright and healthy smile with the mouth naturally open, looking directly at the camera.

Clothing/Pose:
An ivory-white halter-neck bikini without decorations. The top has modest gathers and thin shoulder straps, while the bottoms have side ribbon ties at both hips. The person places her own right hand near her ear, lightly adjusting her hair with her fingertips. Her left arm is naturally down by her side, and her upper body is slightly tilted forward. A natural standing posture with relaxed shoulders and a light twist in the hips. Wet stray hairs follow her cheeks and neck.

Background/Light:
The foreground is a pale sandy beach reflecting sunlight. In the middle ground, white waves wash up diagonally, and in the background, a turquoise blue to light blue sea surface stretches out. Warm summer sunlight enters from the top left of the screen, brightly illuminating the face, shoulders, collarbones, and upper surfaces of the arms. Soft shadows are cast under the chin, chest, and inside the arms, with a pale blue reflection from the sea surface added thin to the shadow side of the skin.

Composition/Camera:
Vertical 9:16. A light high-angle shot looking down from a slightly high position. The person's face is in the upper center, the torso in the center, and the thighs at the bottom. Very little head space, with soft margins for the sea and sand on the sides. Natural perspective equivalent to 35-50mm. Focus accurately on the eyes and face, softly blurring the waves and sea surface in the background. A bright and open beach portrait.

Texture/Style:
A live-action photograph. Meticulously describes natural fine skin texture, moisture-laden hair clumps, fine vellus hair, and thin wrinkles in the fabric. Avoids excessive skin beautification, maintaining a bright high-key tone while suppressing overexposure. Transparent summer colors, soft contrast, and photo-book quality with a sense of cleanliness.

Negative:
Young-looking face, unnatural smile, unnatural gaze, extra fingers, missing fingers, fused fingers, confusion of left and right hands, broken joints, unnatural body shape, clothing digging in, poor fabric connection, floating strings, incorrect perspective, shadows inconsistent with the light source, plastic-like skin, excessive skin correction, text, logo, watermark.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 18: Profile / Avatar - Mirror Selfie in Urban Store

📖 Description

A candid full-body mirror selfie prompt of a stylish woman in a retail environment, using a reference image for her outfit.

📝 Prompt

A candid, full-body mirror selfie captures a stylish young woman with {argument name="hair style" default="wavy, dark hair"} and {argument name="sunglasses style" default="trendy sunglasses"}. She is posing in an urban clothing store, wearing a outfit from second image. She is taking the photo with her phone . The background shows retail displays, racks with T-shirts (one featuring a Stussy logo), a mannequin wearing a cap, and an industrial-style ceiling with track lighting.

🖼️ Generated Images

Image 1
Image 2

📌 Details

  • Author: K
  • Source: Twitter Post
  • Published: July 24, 2026
  • Languages: en

👉 Try it now →

No. 19: Profile / Avatar - Realistic Japanese Badminton Selfie

📖 Description

Generates a highly authentic smartphone-style selfie of a young Japanese woman on an indoor badminton court, emphasizing natural lighting and candid aesthetics.

📝 Prompt

Ultra-realistic smartphone selfie of a beautiful {argument name="subject" default="young Japanese woman"} with smooth porcelain skin, soft natural facial features, large warm brown eyes, glossy pink lips, and a sleek {argument name="hairstyle" default="short black bob haircut"}, wearing a {argument name="headband" default="white athletic headband"}. She is standing on an indoor badminton court while holding a pink-and-black badminton racket in one hand and taking a selfie with the other from a high overhead angle. She wears a black-and-white sports jersey, matching athletic shorts, and bright yellow badminton shoes, smiling softly at the camera with a relaxed, cheerful expression. The background features a realistic indoor sports hall with green badminton courts, gray flooring, court lines, and bright overhead lights. The image looks exactly like it was casually captured using a modern flagship smartphone, featuring natural indoor lighting, authentic skin texture, subtle HDR, slight front-camera wide-angle distortion, realistic sensor noise, mild handheld imperfections, balanced exposure, and soft computational photography. No DSLR look, no studio lighting, no heavy beauty filters, no artificial bokeh, and no AI-perfect sharpness—just a genuine candid mobile phone selfie with a realistic social media aesthetic.

🖼️ Generated Images

Image 1
Image 2

📌 Details

👉 Try it now →

No. 20: Profile / Avatar - Crystalline Cybernetic Anime Girl

📖 Description

Generates a luminous geometric anime close-up of a cybernetic girl surrounded by glass shards and pastel prismatic light.

📝 Prompt

Create a luminous vertical anime portrait of {argument name="character name" default="a mysterious cybernetic girl"} in an elegant geometric illustration style. The composition is an extreme close-up from the shoulders up, slightly tilted, with the face centered and cropped tightly by the top and sides. She has soft short wavy {argument name="hair color" default="silvery white hair with pale pink and cyan reflections"}, long wispy bangs covering part of her forehead, a delicate pale face, a tiny neutral mouth, and an expression that feels calm, doll-like, and unsettling. Her left eye is a large glossy black mechanical eye with concentric blue rings, while her right eye glows pale pink with a hypnotic spiral iris; add fine eyelashes and subtle blush around both eyes. She wears a loose translucent white shirt or robe with a low neckline, rendered with iridescent cyan, pink, and lavender highlights. Surround her with exactly 18 visible floating geometric fragments: 6 translucent cyan glass shards, 5 black triangular prism shards, 4 white angular polygon shards, and 3 small gold-edged triangular pieces. Some shards overlap her hair and cheek like fractured crystal plates, including one translucent shard crossing the right eye and cheek. Add thin circular orbit lines and faint technical arcs in the background, plus scattered prismatic light streaks and sparkles. Use a high-key white background flooded with overexposed light, pastel cyan and pink rim lighting, glossy glass refractions, chromatic aberration, soft bloom, and very clean detailed anime linework. The mood should be futuristic, ethereal, fragile, and crystalline, with no text, no watermark, and no extra characters.

🖼️ Generated Images

Image 1
Image 2

📌 Details

👉 Try it now →

No. 21: Social Media Post - Photo to Anime Transformation

📖 Description

A versatile prompt to transform a real-life photo into two distinct anime styles: Urban Pop and Dreamy Fantasy, while maintaining identity.

📝 Prompt

Create TWO completely different anime illustrations from the uploaded everyday photo while preserving the same person's identity. Keep the facial shape, facial feature proportions, recognizable hairstyle, age impression, and overall personality consistent, but fully transform the image into a vibrant, high-quality anime style. Both images should be unmistakably animated rather than photorealistic, with expressive linework, clean cel shading, bold graphic shadows, vivid high-saturation colours, crisp facial detail, and a polished poster-quality finish. IMAGE 1 — {argument name="style one" default="Urban Pop Anime"} A playful, energetic anime poster with a dynamic wide-angle perspective and dynamic pose. The character has an expressive smile, lively hand gesture, and confident body language. Reimagine the background as a colourful anime city filled with neon signs, floating hearts, sparkling stars, comic speech bubbles, motion lines, kawaii stickers, tiny mascots, hand-drawn doodles, colourful geometric graphics, and fun sound effects. The composition should feel youthful, exciting, bold, and instantly eye-catching, with excellent visual hierarchy and strong social-media appeal. IMAGE 2 — {argument name="style two" default="Dreamy Fantasy Anime"} Create a completely different composition with a magical fantasy atmosphere. Use a {argument name="perspective" default="cinematic low-angle perspective"} and graceful, expressive pose with flowing movement. Replace the original background with a whimsical fantasy world featuring glowing skies, floating islands, oversized flowers, magical sparkles, butterflies, glowing stars, cute fantasy creatures, ribbons, clouds, colourful gradients, decorative frames, and elegant anime-inspired graphic elements. The mood should feel charming, emotional, imaginative, and visually rich while maintaining a clean silhouette, expressive face, polished illustration quality, and a vibrant, premium anime aesthetic suitable for viral social-media artwork.

🖼️ Generated Images

Image 1
Image 2

📌 Details

👉 Try it now →

No. 22: Social Media Post - Modern Interior Apartment Portrait

📖 Description

A high-detail portrait prompt for a serene lifestyle scene in a modern apartment, focusing on natural lighting and realistic skin textures.

📝 Prompt

A young adult East Asian woman standing in a modern apartment dining/living area, half-body to upper-body composition, centered slightly to the right. She leans back naturally, arms extended behind her with hands resting on the edge of a {argument name="furniture" default="dark wooden dining table"}, creating a smooth curve. Her head is slightly tilted back and to the left, facing the camera with a calm, confident, slightly lazy gaze and lips naturally parted.

She has a soft, delicate oval face, almond-shaped dark brown eyes, natural thin eyebrows, light nude pink lips, and light makeup. Fair, warm skin retaining real pores, fine vellus hair, natural skin tone variations, and soft highlights—no plastic airbrushing. Long dark black-brown hair flows naturally, soft and slightly voluminous, with some strands falling on her shoulders and chest.

Wearing a {argument name="top" default="white slim-fit long-sleeve crop top"} knotted at the chest, soft and form-fitting fabric revealing the midriff; paired with {argument name="trousers" default="white loose lounge pants"} with a high elastic waist; a thin silver waist chain or pearl-like decoration at the waist. Overall refreshing, clean, and lifestyle-oriented.

Background is a modern residential interior: curtains and soft window light on the left, a dark door frame behind; transparent shoe boxes stacked on the back right with a white helmet on top, next to a TV and dark furniture; wooden dining table and chairs in the foreground. Clean but with a real lived-in feel.

Lighting is natural daylight from the left, soft side-lighting, low saturation and contrast overall, with a real photographic texture. Style: 85mm portrait lens, f/2, shallow depth of field, sharp subject, slight background blur, subtle film grain, photorealistic.

Avoid: Cartoon, CG feel, excessive airbrushing, exaggerated body proportions, incorrect fingers, deformed limbs, heavy makeup, cluttered background, strong HDR, over-sharpening, text, watermarks, logos.

🖼️ Generated Images

Image 1
Image 2
Image 3
Image 4

📌 Details

👉 Try it now →

No. 23: Social Media Post - Realistic Mountain Valley Travel Portrait

📖 Description

Generates a breathtaking cinematic travel photo of a woman in a European alpine setting, emphasizing natural lighting and autumn aesthetics.

📝 Prompt

Ultra-realistic cinematic travel photograph of a young woman standing peacefully behind a rustic weathered wooden fence, facing the camera with her front fully visible while maintaining a calm, serene expression. She gently rests one hand on the wooden fence and naturally gazes toward the camera, creating a timeless editorial travel portrait. She wears a {argument name="sweater" default="cozy oversized moss-green fuzzy knit sweater"} layered over a {argument name="skirt" default="flowing ivory-white skirt"}, creating a soft autumn aesthetic. Her dark brown hair is neatly tied into a low bun with a delicate yellow floral scrunchie, subtly illuminated by warm golden-hour sunlight.
In front of her stretches a {argument name="scenery" default="picturesque European mountain valley"} filled with rolling emerald-green meadows, winding country roads, scattered traditional alpine farmhouses, and a charming white church with a tall pointed steeple nestled in the village below. Golden autumn trees are scattered across the hillsides, adding vibrant seasonal contrast.
The dramatic background features towering jagged snow-capped mountain peaks rising sharply beneath a vast blue sky filled with soft layered clouds. Warm sunlight breaks across the valley, creating beautiful highlights on the grass while deep mountain shadows add depth and atmosphere. The composition emphasizes scale, tranquility, and wanderlust, with the woman positioned in the foreground as the focal point against the magnificent alpine scenery.
Shot in a premium travel-photography style with natural lighting, ultra-realistic textures, crisp mountain details, HDR dynamic range, vibrant yet true-to-life colors, cinematic depth, atmospheric perspective, sharp focus throughout, subtle bokeh, National Geographic quality, luxury travel magazine aesthetic, peaceful mood, breathtaking scenery, 8K ultra-high resolution, photorealistic, vertical composition (3:4 aspect ratio).

🖼️ Generated Images

Image 1
Image 2

📌 Details

👉 Try it now →

No. 24: Social Media Post - High-End Fashion Editorial Portrait

📖 Description

A premium studio portrait of a stylish African man, preserving identity from an uploaded image with a minimalist baby-blue aesthetic.

📝 Prompt

Use the uploaded image as the facial identity reference for the subject. Preserve his natural facial structure, skin tone, hairstyle, facial proportions, and overall identity accurately. Create an ultra-realistic, high-end fashion editorial portrait of a {argument name="subject" default="stylish young African man"} seated confidently on a clean studio floor in a relaxed, sophisticated pose. He is wearing a {argument name="outfit" default="vibrant pink short-sleeve textured overshirt layered over a crisp white long-sleeve shirt, paired with relaxed-fit light blue denim jeans, clean white socks, and premium tan leather lace-up boots"}. He wears sleek black rectangular sunglasses and a subtle premium gold wristwatch, adding a refined contemporary touch. His pose is natural and confident, with one arm casually raised near his head while the other supports his relaxed seated position. Maintain a tasteful, modest, polished appearance with no excessive exposure. Set the scene against a {argument name="background" default="minimalist bright baby-blue studio background with a matching seamless floor"}, soft diffused professional lighting, subtle natural shadows, and a clean luxury fashion campaign aesthetic. The composition should feel youthful, stylish, confident, modern, and premium, with balanced colours and excellent visual harmony. Capture the subject in sharp focus with realistic skin texture, natural facial features, accurate body proportions, detailed fabric and denim textures, photorealistic materials, cinematic yet soft lighting, and professional high-end fashion photography quality. Full-body composition, vertical portrait, editorial magazine style, luxury fashion campaign, ultra-detailed, photorealistic, 4K resolution, realistic anatomy, natural pose, premium studio photography, clean composition.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 25: Social Media Post - 1970s Monochrome Windswept Portrait

📖 Description

A vintage-style black-and-white close-up portrait with film grain, high contrast, and a windswept outdoor aesthetic.

📝 Prompt

Create a 1970s black-and-white close-up portrait in a {argument name="setting" default="windswept outdoor setting"}, black and white noise . Camera/look: eye-level, front ¾ view (~30° off-axis); 85–105 mm portrait perspective; vertical 2:3, tight head-and-shoulders crop; shallow DoF f/2.8–f/4; subject centered . Lighting: hard natural sunlight from upper camera-left with minimal fill; crisp shadows; subtle rim on hair; sky as bright mid-tone background; no blown highlights.Pose & expression: subject faces camera, chin slightly down, {argument name="pose" default="lips parted with a cigarette held between them"}; gaze relaxed/half-lidded; hair blown across the face by wind, partially covering one eye.Wardrobe & styling: dark collared shirt with open neck; thin black neck scarf tied loosely; no logos/jewelry.Grade: {argument name="film style" default="high-contrast monochrome with rich blacks"}, bright highlights, medium–heavy film grain (Tri-X/HP5 vibe), slight halation, faint vignette; keep skin texture natural (no plastic smoothing).Composition: simple sky background, no extra props; clean verticals; ensure sharp focus on near eye and cigarette.Output: high-resolution, editorial/classic cinema mood; no text or watermarks.

🖼️ Generated Images

Image 1
Image 2

📌 Details

  • Author: K
  • Source: Twitter Post
  • Published: July 25, 2026
  • Languages: en

👉 Try it now →

No. 26: Social Media Post - Streetwear Portrait Fisheye Lens

📖 Description

A high-fashion streetwear portrait of a young man captured with a wide-angle fisheye lens in a studio setting, emphasizing a modern Gen Z aesthetic.

📝 Prompt

Ultra realistic high fashion streetwear portrait of a young man photographed in a clean white studio using an ultra wide fisheye lens from a high overhead angle. The subject is looking directly into the camera with a confident, slightly serious expression while lightly holding the brim of his {argument name="headwear" default="trucker cap"} with one hand and keeping the other hand inside his hoodie pocket. He wears an {argument name="clothing" default="oversized charcoal black hoodie layered over a white T shirt"}, loose faded gray baggy jeans with a silver wallet chain, black and white sneakers, a thin silver chain necklace with a small star pendant, a silver bracelet, and a small hoop earring. The trucker cap has a royal blue front panel, bright yellow curved brim, light gray mesh back, and a small embroidered patch logo on the front. Messy medium length dark brown hair peeks out naturally from beneath the cap, framing the face. The lighting is {argument name="lighting" default="soft, diffused studio lighting"} with subtle shadows, producing natural skin tones and gentle contrast. Minimalist seamless white backdrop with no props. Strong perspective distortion from the fisheye lens emphasizes the cap and upper body while slightly shrinking the legs and feet. The image features a circular fisheye vignette with dark edges surrounding the frame, giving an immersive lens effect. Editorial fashion photography, modern Gen Z streetwear aesthetic, premium clothing campaign, authentic pose, crisp textures, realistic fabric folds, detailed skin, sharp eyes, cinematic color grading, shallow depth of field, ultra detailed, 8K resolution, DSLR quality, commercial fashion shoot, natural proportions, photorealistic. Camera: 8mm fisheye lens, high angle, top down perspective, f/2.8, ISO 100, 1/200s, centered composition, ultra sharp focus, subtle filmic contrast, clean studio environment.

🖼️ Generated Images

Image 1
Image 2

📌 Details

👉 Try it now →

No. 27: Social Media Post - Minimalist Studio Lifestyle Portrait

📖 Description

A professional photography prompt for creating a photorealistic lifestyle portrait of a woman in a minimalist studio, featuring soft lighting and an artistic gallery aesthetic.

📝 Prompt

A photorealistic lifestyle portrait of a {argument name="subject" default="beautiful young woman"} sitting cross-legged on a smooth floor in a modern minimalist studio, smiling softly at the camera. She has long light brown hair styled in a loose side braid with soft face-framing strands, natural glowing skin, subtle makeup, defined brows, warm hazel eyes, and a gentle, confident expression. She wears a {argument name="outfit" default="fitted black ribbed long-sleeve top"}, high-waisted light gray cuffed trousers, and chunky white sneakers. One elbow rests on her knee while her hand lightly touches her head, creating a relaxed editorial pose. Behind her is a {argument name="background" default="large monochrome black-and-white portrait of herself"}, softly blurred, adding depth and an artistic gallery aesthetic. Soft diffused studio lighting, neutral gray tones, shallow depth of field, creamy bokeh, cinematic color grading, luxury fashion editorial, ultra-realistic skin texture, balanced composition, 85mm lens, f/1.8, HDR, 8K, premium magazine photography.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 28: Social Media Post - Pastel Manga Selfie Collage

📖 Description

Generates a six-panel pastel anime manga page of a pink-haired girl taking selfies on a sunny seaside cafe terrace.

📝 Prompt

Goal: Create a bright shoujo manga-style one-page collage showing a cheerful teen idol girl filming social-media selfies on a sunny seaside cafe terrace.

Canvas: Vertical A4 manga page, full color, soft pastel palette, no black panel borders; use six irregular rounded panels separated by thick white gutters, with cute sticker doodles in the margins. High-detail anime illustration, sparkling highlights, airy summer atmosphere, blue sky and ocean visible beyond balcony railings.

Main character: A cute anime girl with {argument name="hair color" default="cotton-candy pink"} twin-tail hair, large pink eyes, small flower hair clips, expressive rosy cheeks, and a lively idol-like personality. She wears a translucent lavender sailor-collar blouse with puffy sleeves, a purple bow at the collar, a layered ruffled short skirt, and a large pale-blue waist ribbon tied in a bow. Keep the same character design consistent in every panel.

Layout: Include exactly 6 panels. Panel 1, large upper-left: close-up selfie angle, the girl holds a pink smartphone decorated with white cherry blossoms toward the viewer, smiling with mouth open on a balcony under a blue sky; sun doodle and small sparkles nearby. Panel 2, upper-right: full-body pose, she stands on one leg and winks while holding a selfie stick with the same phone attached, terrace tables and plants behind her, heart and music-note doodles. Panel 3, middle-left: side view at a small cafe table, she leans forward adjusting or checking the phone on a small tabletop tripod; include a lemon drink with straw; add a speech bubble reading {argument name="speech bubble 1" default="よしっ"}. Panel 4, middle-right: she stands thoughtfully by the balcony with hands near chest, ocean and potted plants behind; add a thought bubble reading {argument name="thought bubble" default="うーん..."} and a small countdown bubble reading {argument name="countdown text" default="3... 2... 1..."}. Panel 5, lower-left: close-up three-quarter view, she smiles and holds the phone while raising one finger as if announcing another take; add a red handwritten speech bubble reading {argument name="speech bubble 2" default="もう一枚!"}, plus tiny beach/palm doodles. Panel 6, lower-right: she sits on the terrace floor or low seat near a table with the lemon drink, winking and making a playful finger pose, ocean view in the background, hearts, flowers, sparkles, and tiny wing doodles.

Visible repeated elements: exactly 6 appearances of the same girl, exactly 3 visible pink smartphone setups or phones held prominently in panels 1, 2, 3, and 5 if partially repeated as the same device; exactly 3 text bubbles with Japanese text plus 1 countdown bubble; include cute doodles such as 3 hearts, 4 flowers, 1 sun, 1 palm tree, 1 music note, 1 winged icon, and small sparkle marks.

Visual style: Highly polished Japanese AI manga illustration, soft watercolor-like lighting, clean line art, pastel lavender and pink color harmony, glossy eyes, delicate fabric transparency and ruffles, warm sunlight, depth of field, cheerful influencer-vlog mood. Avoid realism, avoid dark shadows, avoid extra characters, avoid logos or watermarks.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 29: Social Media Post - Japanese Night Street Candid Portrait

📖 Description

A moody, nostalgic candid portrait prompt of a woman on a quiet Japanese city street at night with authentic iPhone-style low-light photography.

📝 Prompt

A candid cinematic night street portrait of a {argument name="subject" default="young woman walking along a quiet urban sidewalk in Japan"}, captured on {argument name="camera" default="an iPhone"}. She has long, wavy dark brown hair with a single thin braid framing one side of her face, soft natural makeup, and a subtle smile while glancing back at the camera. She wears a {argument name="outfit" default="fitted gray sleeveless tank top, light-wash loose straight-leg jeans, and carries a black leather shoulder bag"}. In one shot she playfully raises her hand toward the lens, creating natural foreground motion blur; in another she crouches against a white glossy subway-tiled wall with her chin resting on her hand; in another she looks back over her shoulder while walking. The setting features a dimly lit Japanese city street with tiled walls, crosswalks, utility poles, distant traffic lights, glowing shop signs, apartment buildings, and soft streetlights. {argument name="lighting" default="Warm ambient lighting mixed with cool city lights"} creates a moody, nostalgic atmosphere. Natural skin tones, subtle reflections on the tiled wall, shallow depth of field, realistic shadows, slight digital grain, soft bokeh, authentic smartphone low-light photography, spontaneous lifestyle aesthetic, minimal color grading, quiet midnight city vibe, documentary style, ultra-realistic, 35mm equivalent lens, vertical 9:16 composition.

🖼️ Generated Images

Image 1
Image 2
Image 3

📌 Details

👉 Try it now →

No. 30: Social Media Post - Photorealistic Person with Ink-Twin Doodle

📖 Description

A creative prompt generating a photorealistic person standing beside their chaotic charcoal sketch silhouette on a minimal wall.

📝 Prompt

Use the uploaded photo as the exact identity reference. Keep the face, skin tone, hairstyle, accessories, and outfit exactly the same. Create a vertical full-body image of the real person standing beside their {argument name="twin type" default="ink-twin doodle"}. The real person should look photorealistic with a {argument name="expression" default="playful, slightly embarrassed expression"} and a natural pose. The ink twin should be a {argument name="sketch style" default="rough black charcoal sketch"} on a clean white or light gray wall, matching the person's hairstyle, outfit, and pose only as a silhouette, but with exaggerated, chaotic energy. Add a few simple doodle effects like motion lines, stars, or hearts. Use soft natural daylight with a clean minimal background. Do not change the person's appearance or outfit. Do not make the twin a real person, colored cartoon, or flat shadow. Avoid repeated poses, bad hands, extra limbs, clutter, text, or watermarks.

🖼️ Generated Images

Image 1
Image 2
Image 3
Image 4

📌 Details

👉 Try it now →

No. 31: Social Media Post - Monochrome Surreal Obsidian Monolith

📖 Description

A surreal monochrome editorial portrait with floating obsidian elements and impossible spatial distortion.

📝 Prompt

A striking monochrome editorial portrait suspended inside a massive floating {argument name="monolith material" default="obsidian"} monolith with impossible spatial distortion. The rectangular frame appears sliced into multiple layers drifting independently while remaining physically connected in impossible ways. Tiny floating dust particles catch {argument name="lighting" default="cinematic studio lighting"}. Deep matte textures, brutalist luxury aesthetic, dramatic contrast, premium fashion magazine cover style, perfectly centered composition, ultra-realistic skin pores, {argument name="lens type" default="85mm"} portrait lens, impossible dimensional illusion, surreal architecture meets fine art photography.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 32: Infographic / Edu Visual - Nested Picture-in-Picture Software UI

📖 Description

A complex prompt used to test the rendering depth and detail of GPT Image 2, featuring a software editor nested within a chat app and artwork.

📝 Prompt

Generate a 'picture-in-picture' image with visual depth. The outermost layer is a realistic {argument name="programming interface" default="VSCode programming interface"}, nested with a {argument name="app name" default="Qwen App"} chat interface. In the chat, I am sending a message saying: '{argument name="request content" default="help me generate a hand-brewed coffee poster"}'. The app replies with an exquisite coffee poster, which is also clearly displayed in the chat interface. Each UI layer must maintain realistic style and detail, with clear micro-details like time digits and button text.

🖼️ Generated Images

Image 1
Image 2

📌 Details

👉 Try it now →

No. 33: Infographic / Edu Visual - AI Model Routing Comparison Infographic

📖 Description

A square social media infographic comparing chaotic all-GPT usage with smart task-based AI model routing.

📝 Prompt

Create a square 1:1 dark futuristic tech infographic for social media comparing two AI workflow approaches. Canvas: 768x768 or similar, deep navy-to-black background with subtle dotted grid texture and a vertical split down the center. At the top, place a huge bold uppercase headline: “STOP USING GPT FOR {argument name="headline word" default="EVERYTHING"}.” The words “STOP USING GPT FOR” are white, and the final word is a left-to-right gradient from lime green to cyan-blue, with a cyan period. Use a clean heavy sans-serif font, high contrast, crisp vector-like rendering.

Layout: two side-by-side columns. Left column is labeled as the bad workflow, right column as the improved workflow. The left side has a red/pink theme with a pill label reading “THE OLD WAY,” a small subtitle “WASTE MONEY,” and a central rounded-square GPT/OpenAI-style knot icon. Around it are exactly 5 smaller rounded-square task icons connected by messy red dashed routing lines: 1 video clapper/play icon at upper center, 2 design pen-nib/Bezier icon at left, 3 microphone icon at right, 4 image/photo icon at lower left, 5 code brackets icon at lower right. The messy dashed lines loop and cross, showing chaos.

Right column has a teal/blue theme with a pill label reading “THE SMART WAY,” a small subtitle “ROUTE TO THE BEST MODEL,” and a central rounded-square robot router icon. Connect it with clean glowing solid lines to exactly 5 model cards: 1 top card with OpenAI knot icon labeled “GPT 5.6” and “DESIGN,” 2 left purple card with code brackets labeled “{argument name="coding model" default="FABLE"}” and “CODE (HARD),” 3 right blue card with clapper/play icon labeled “{argument name="video model" default="SEEDANCE 2.0"}” and “VIDEO,” 4 bottom-left gold card with image icon labeled “{argument name="image model" default="GPT 2.0"}” and “IMAGE,” 5 bottom-right blue card with microphone icon labeled “{argument name="voice model" default="HUME"}” and “VOICE.” Use rounded glassmorphism cards with neon outlines and soft glow.

Bottom callouts: under the left column, place a red outlined rounded status bar with a red X icon and text “EXPENSIVE. CHAOTIC. INEFFICIENT.” Under the right column, place a teal/green outlined rounded status bar with a green check icon and text “SMARTER. CHEAPER. BETTER RESULTS.” Keep all text legible, centered, and aligned. Use strong contrast, modern SaaS marketing style, subtle gradients, neon highlights, no extra logos, no watermark, no additional text beyond the specified labels.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 34: Infographic / Edu Visual - Footballer Then vs Now Transformation

📖 Description

A split-screen prompt that generates a nostalgic childhood portrait and a modern adult version of the same person, showing the passage of time.

📝 Prompt

Create a realistic vertical split-screen "Then vs Now" transformation featuring the same famous {argument name="athlete" default="football player"}. The composition is divided into two stacked sections. Top panel: a warm nostalgic childhood portrait set in the player's family home during their birth year (display the year in clean white text on the left, e.g. "{argument name="birth year" default="1985"}"). The child sits naturally facing the camera wearing a simple white T-shirt, soft golden sunlight streaming through a nearby window, authentic 90s/80s home interior, subtle film grain, warm Kodak color grading, emotional and cinematic. Bottom panel: the same person recreated as their present-day adult self in 2026, maintaining recognizable facial structure and identity, wearing a plain white oversized T-shirt inside a modern café with warm ambient lighting and shallow depth of field. Place a small rounded-corner reference portrait of the player in their national team jersey at the bottom-right corner. Match the pose, eye direction, framing, and expression between the child and adult versions to emphasize the passage of time. Hyper-realistic skin, natural facial evolution, consistent identity, cinematic photography, editorial quality, soft depth of field, 85mm lens, ultra-detailed, photorealistic, 8K, masterpiece.

🖼️ Generated Images

Image 1
Image 2

📌 Details

👉 Try it now →

No. 35: Infographic / Edu Visual - Japanese Pediatric Disease Infographic

📖 Description

A cute Japanese clinic flyer explaining hand-foot-and-mouth disease and herpangina for parents.

📝 Prompt

Goal: Create a friendly Japanese medical explanation infographic for parents about {argument name="topic title" default="手足口病とヘルパンギーナ"}, suitable for use in a pediatric clinic consultation room.

Canvas: Vertical portrait flyer, warm off-white paper background, soft hand-drawn watercolor style, rounded corners, pastel colors, clear black handwritten Japanese text. Add small decorative confetti marks around the title. Overall look should be cute, reassuring, and easy to understand.

Layout: Use exactly 5 stacked rounded rectangular information panels, each with a large numbered circle on the left. Panel 1 has a pink border, panel 2 blue, panel 3 yellow-orange, panel 4 green, panel 5 orange with a scalloped decorative border. Keep generous margins and make all text large and legible.

Title: At the top, write 「手足口病とヘルパンギーナ」 in large dark brown handwritten lettering with a pink wavy underline.

Panel 1, number 1, pink: Write 「手・足・口に小さな水疱、おしりにも」. Include exactly 4 medical illustrations in a row: an open palm with small red blisters, a sole of a foot with small red blisters, an open mouth/throat with red spots, and a diapered bottom/thigh area with red spots. At the bottom add a small sun icon and the note 「夏〜秋に小さい子に多い」.

Panel 2, number 2, blue: Write 「原因はコクサッキーウイルス」 and smaller text 「ありふれたかぜのウイルス」. On the right draw exactly 1 cute round blue virus mascot with tiny spikes, eyes, a smiling mouth, and small motion lines.

Panel 3, number 3, yellow-orange: Show a simple Venn diagram with exactly 2 overlapping large translucent circles: left circle pink, right circle light blue, overlap pale green. Left circle text: 「のどの奥に白い水疱→ヘルパンギーナ」. Right circle text: 「手のひら・足のうらに発疹→手足口病」. Under the circles write: 「原因ではなく『どこに出たか』でつけた病名。ヘルパンギーナでも全身に発疹が出ることがあり、厳密には区別できない」.

Panel 4, number 4, green: Write 「特効薬なし・対症療法」 and smaller text 「約1週間で治る」. Include exactly 4 supportive-care illustrations: a glass of water, a sleeping child tucked in bed, a digital thermometer showing 36.6°C, and a smiling child in a green striped shirt raising one fist.

Panel 5, number 5, orange: Headline in large orange text: 「登園の目安」. List exactly 2 numbered conditions: 「① 熱がない」 and 「② 普通にご飯が食べられる」. Add a large emphasized orange message: 「発疹が残っていても 普通の生活・登園OK」. Smaller explanatory text at the bottom: 「ウイルスは治った後も長く出続けるので、発疹が消えるまで待つ意味はありません」. On the right draw a cheerful preschool child wearing a yellow hat, blue backpack, striped shirt, blue shorts, and sneakers, running or waving toward a small school building with flowers.

Constraints: Use exactly 5 numbered panels and the exact Japanese text above. Do not add extra sections, extra medical claims, logos, watermarks, QR codes, or English translations. Keep the illustration soft, pediatric, non-scary, and clinically clear.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 36: Infographic / Edu Visual - City Aesthetic Morning Poster Collage

📖 Description

A creative prompt for generating city-themed morning posters with a fresh Japanese aesthetic, featuring culture-specific elements and a multi-grid layout for different hues.

📝 Prompt

Theme: {argument name="city characteristics" default="City characteristic cultural elements"} + Good Morning Greeting + {argument name="date" default="2026-07-24"} + Today's Quote. A total of {argument name="number of cities" default="10"} different cities, each with its own unique beautiful image. Japanese-style fresh and artistic color palette. Aspect ratio 16:9. Each image features different color logic and compositional differences, resulting in distinct hues at a glance.

🖼️ Generated Images

Image 1
Image 2
Image 3
Image 4

📌 Details

👉 Try it now →

No. 37: Infographic / Edu Visual - BIP110 Korean Infographic

📖 Description

A prompt used to test and compare the Korean text rendering capabilities of GPT Image 2 vs other models.

📝 Prompt

Create a Korean infographic about the {argument name="subject" default="BIP110 operating mechanism"}

🖼️ Generated Images

Image 1
Image 2
Image 3

📌 Details

👉 Try it now →

No. 38: Infographic / Edu Visual - Neon Jellyfish Scientific Specimen

📖 Description

A striking prompt for a futuristic scientific specimen illustration featuring a luminous neon jellyfish against a pure black background.

📝 Prompt

A {argument name="subject" default="luminous jellyfish"} suspended against a {argument name="background" default="pure black background"}, presented like a futuristic scientific specimen plate. Its translucent bell glows in {argument name="colors" default="saturated neon magenta, ultraviolet purple, electric cyan, cobalt blue, and toxic green"}, with branching vein-like structures and fine cellular textures visible inside. Long ribbon-like tentacles trail downward in elegant curves, each edge illuminated by fluorescent light. Along the left side, six clean rectangular swatches show gradients and macro texture studies derived from the jellyfish’s membranes. High-contrast ultraviolet photography, iridescent biological detail, crisp symmetry, minimal composition, deep black negative space, surreal natural-history aesthetic, intensely radiant neon color.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 39: Infographic / Edu Visual - AI Vibe Coding Evolution Map

📖 Description

A prompt to generate a detailed layout map exploring the development of AI vibe coding and the roles of different LLM models.

📝 Prompt

I need to understand the development history of the entire {argument name="topic" default="AI vibe coding"}, including the roles played by models such as {argument name="models" default="Claude, ChatGPT, Kimi, GLM, DeepSeek"} throughout this process. Generate a layout map and chart that is as detailed as possible.

🖼️ Generated Images

Image 1
Image 2

📌 Details

👉 Try it now →

No. 40: Infographic / Edu Visual - Rayleigh Scattering Infographic

📖 Description

A vertical classroom-style infographic explaining why the sky is blue and sunsets are red through Rayleigh scattering diagrams, formulas, and fact cards.

📝 Prompt

Goal: Create a tall single-page educational science infographic explaining {argument name="headline text" default="WHY THE SKY IS BLUE — AND SUNSETS ARE RED"} with the subtitle {argument name="subtitle text" default="Rayleigh scattering explained in one page"}. Use a clean flat-design science-magazine look, suitable for a classroom handout.

Canvas: Vertical 9:16 poster on an off-white background, framed by black horizontal bars at the very top and bottom. Center the white text “GPT Image 2” inside each black bar. Main infographic area has generous margins, thin navy divider lines, rounded cards, and a navy/teal/coral/yellow palette.

Layout: Use exactly 5 numbered sections, each marked by a dark navy circular badge with white numbers 1 through 5 on the left. Keep all typography geometric sans-serif, with bold uppercase navy headings and teal italic subtitle.

Section 1 — Visible Light Spectrum: Heading reads “VISIBLE LIGHT SPECTRUM”. Show one long rounded horizontal rainbow gradient bar from violet/blue at left through cyan, green, yellow, orange, and red at right. Add exactly 4 wavelength labels beneath it: “400 nm”, “500 nm”, “600 nm”, and “700 nm”, with small tick marks.

Section 2 — Sunlight Entering the Atmosphere: Heading reads “SUNLIGHT ENTERING THE ATMOSPHERE”. Draw a large stylized yellow sun on the left, Earth’s curved edge on the right, and a pale blue atmospheric band between them filled with many small blue air-molecule dots. Show exactly 4 blue horizontal light rays entering and scattering with small blue arrows, plus exactly 3 red horizontal rays passing straight through toward Earth. Include exactly 6 larger molecule/star scattering icons in the atmosphere. Add two explanatory captions below the rays: “Blue light: scattered ~5.5x more” in blue and “Red light: passes through” in red.

Section 3 — Formula and Bar Chart: Create two rounded rectangular cards side by side. Left card shows the large equation “I ∝ 1/λ⁴” and the caption “Scattering intensity is inversely proportional to the fourth power of wavelength”. Right card title reads “RELATIVE SCATTERING (450 nm vs 650 nm)”. Include a simple bar chart with exactly 2 bars: a tall blue bar labeled “450 nm” and a shorter red-orange bar labeled “650 nm”, y-axis labeled “Relative scattering”, and large text “≈ 4.4 : 1” on the right.

Section 4 — Noon vs Sunset: Make two large circular/oval diagrams side by side. Left diagram title: “NOON — short path through atmosphere”. It shows a small sun above a curved Earth horizon, a tiny black human silhouette at ground level, blue dots in the sky, and vertical red and blue rays passing through a short atmospheric path with blue scattering arrows. Right diagram title: “SUNSET — long path”. It shows a low sun near the horizon on the left, a long horizontal path through a pale blue atmosphere over curved Earth, blue light scattering away along the path, a red ray continuing to a black human silhouette at the right, and the caption “Blue is scattered away before reaching your eye”.

Section 5 — Facts: Create exactly 3 rounded fact cards in a row. Card 1 has a simple outlined Mars-like planet icon and text “Fact: Mars sunsets are blue”. Card 2 has a teal ocean wave icon and text “Fact: The ocean is blue for a different reason”. Card 3 has a purple eye icon with rays and text “Fact: Violet scatters most, but our eyes favor blue”.

Footer: Add small centered source text: “Sources: Rayleigh (1871) · Illustration for classroom use · Fig. 1 of 1”.

Visual style: Flat vector illustration, thin navy outlines, soft gradients only where needed, crisp readable labels, science textbook clarity, no photorealism except the Earth texture may be lightly detailed. Keep spacing balanced and ensure every label is legible.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 41: Infographic / Edu Visual - Dark Chinese Industry Quote Poster

📖 Description

Generates a premium vertical speaker or industry commentary poster with a cinematic portrait, bold Chinese quote typography, and corporate red accents.

📝 Prompt

Goal: Create a vertical Chinese business keynote quote poster featuring a serious industry expert portrait and bold editorial typography.

Canvas: 2:3 vertical poster, dark premium corporate style, black-to-charcoal vignette background with a soft gray halo behind the subject, high contrast, cinematic lighting.

Main subject: One centered East Asian male expert, about 35–45 years old, short black hair, round black eyeglasses, calm serious expression, looking directly at the viewer. He wears a black suit or dark blazer. Pose him leaning forward with both hands clasped under his chin, elbows implied below frame. Use realistic studio portrait photography, sharp facial detail, moody side lighting, shallow depth of field.

Layout: The portrait fills the upper two thirds of the poster. Place the text block over the lower half, aligned left, leaving the face unobstructed. Use a large white quotation mark at the lower left above the headline. Add a thin vertical red line along the left side of the main text block and small red accent lines.

Text content: Include exactly 1 oversized white opening quotation mark. Include exactly 2 small labels above the headline: a red rectangular label with white Chinese text “行业观察”, followed by a small gray label “专栏”. Include exactly 1 large bold white Chinese headline: “当增长放缓，真正的竞争才开始”. Under it, include exactly 3 insight bullet lines, each with a small white icon and red accent: 1) “需求进入存量时代，增长逻辑全面重构” with an upward chart icon, 2) “从规模扩张转向效率提升，组织能力是关键” with a person icon, 3) “技术与场景深度结合，构建可持续的竞争壁垒” with a target icon. At the bottom left, include exactly 1 author block: “张睿 资深行业分析师” and below it “专注产业研究与企业战略”.

Typography and style: Heavy condensed sans-serif Chinese headline, bright white text with subtle shadow, clean smaller gray body text, red accents in a vivid corporate red. Overall mood should feel like a high-end conference speaker poster, business magazine cover, leadership profile, or industry commentary card.

Customizable fields: Use {argument name="speaker name" default="张睿"}, {argument name="speaker title" default="资深行业分析师"}, {argument name="headline text" default="当增长放缓，真正的竞争才开始"}, {argument name="category label" default="行业观察"}, and {argument name="subtitle label" default="专栏"}.

Constraints: Keep the poster dark, minimalist, and premium. Do not add logos, watermarks, QR codes, extra people, extra bullet points, or extra decorative elements. Ensure all Chinese text is legible and correctly placed.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 42: Infographic / Edu Visual - Fair Partnership Business Infographic

📖 Description

A vertical Korean business infographic illustrating the shift from exploitative client-vendor hierarchy to equal value-based partnership.

📝 Prompt

Goal: Create a vertical Korean editorial infographic poster about business relationships, contrasting an exploitative “client as boss / vendor as subordinate” mindset with a fair partnership based on exchanging value. Use a polished GPT-image style digital illustration with clear Korean typography, warm lighting, and a split-scene narrative.

Canvas: Vertical 9:16 poster, cream paper background, high-resolution, suitable for a social media post. Main palette: navy, gold, cream, warm brown, sky blue, and business-office neutrals.

Top headline: Large bold dark navy Korean headline centered at the top: {argument name="headline text" default="돈을 주는 사람이\n무조건 갑일까?"}. Add small decorative radiating lines on both sides.

Layout: Divide the central image into two contrasting halves. Left half is dark, cramped, theatrical, and exploitative; right half is bright, airy, professional, and collaborative. A central walking businessman bridges the two worlds, moving from left to right. Bottom contains a large navy-and-gold banner statement and hashtags.

Left half, exploitative side: Show a smug king-like client on a balcony wearing a gold crown labeled “갑”, holding binoculars and fishing for free value. He sits in a dark red-brown booth with dramatic shadows. Include a speech bubble saying “아이디어 좀 더!\n전략도 더!\n자료도 더!\n견적은 나중에!” and a small hanging sign saying “간 보기\n무한 루프”. Near him, show a cup labeled “조금만 더...”. Below, depict an exhausted worker labeled “을”, hunched over and chained to a heavy black ball labeled “무급 과제\n반복 요구”. He carries the burden while standing beside a tall stack of papers labeled in three visible layers: “정보”, “지식”, “문서 용역”. Include exactly 5 small request notes on the left wall/stack area: 1) “시장 조사\n좀 해주세요!”, 2) “경쟁사 분석\n부탁해요!”, 3) “사업 계획서\n초안 부탁!”, 4) “PoC 해보고\n결과만 주세요!”, 5) “이 정도는\n서비스죠?” At the top of this left scene write: “간만 보는 게 아니라,\n공짜로 다 가져가려는 사람”, with “공짜로” emphasized in gold.

Right half, partnership side: Show a bright modern office with large windows, city skyline, blue sky, and a clean round meeting table. At the top, a balance scale diagram shows two simple human icons on a wooden seesaw: blue figure on the left and green figure on the right, balanced equally. The center support is labeled “파트너십”. Above it write: “필요한 서비스에\n타당한 값을 지불하는\n대등한 파트너”, emphasizing “대등한 파트너” in bold navy. At the meeting table, show exactly 3 professionals: one seated man holding a contract, one seated woman smiling and holding a payment card or payment symbol, and the central walking man approaching as the partner. Add speech bubbles: from the central/left professional, “필요한 가치를\n명확히 제공하겠습니다.” and from the woman, “그 가치를\n정당하게 평가하고\n지불하겠습니다.” Include a document labeled “계약서”, a payment object labeled “공정한 대가”, and a floor sign with exactly 3 checkmarked values: “신뢰”, “존중”, “지속 가능한\n성장”. Add a potted plant at lower right.

Central character: A confident Korean businessman in a navy suit walks from the dark left side into the bright right side, holding a glowing coin labeled “을” in one hand and wearing a small badge labeled “파트너”. He should look calm, empowered, and optimistic, symbolizing transition from subordinate vendor to equal partner.

Bottom banner: Large dark navy ribbon plaque with gold trim, a central star at the top, and two gold laurel branches. Main Korean statement in bold white and gold: {argument name="bottom statement" default="갑·을이 아니라,\n서로 필요한 가치를\n정당하게 교환하는 관계"}. Below the banner, include exactly 6 hashtags in dark navy: {argument name="hashtags" default="#career  #business  #bizmodel\n#cowork  #gonnector  #고넥터"}. Footer: small text at bottom left “© 2026 Gonnector” and a tiny abstract multicolor logo at bottom right.

Visual style: Semi-realistic editorial cartoon illustration, clean linework, Korean webtoon-infographic influence, cinematic lighting contrast between left and right, high readability, crisp typography, professional business storytelling. Make the text look intentionally designed and aligned, not random.

Constraints: Keep all Korean text legible and spelled as written. Use exactly the counted elements: 5 request notes, 3 paper-stack labels, 3 meeting professionals, 3 checklist values, 6 hashtags, and 2 contrasting halves. Avoid extra characters, extra hashtags, watermarks, distorted faces, or nonsensical text.

🖼️ Generated Images

Image 1
Image 2

📌 Details

👉 Try it now →

No. 43: Infographic / Edu Visual - Studio Ghibli Style Visual Reference Sheet

📖 Description

Generates a clean, Ghibli-inspired visual reference sheet for character or item design with cel shading and minimal background.

📝 Prompt

Anime visual reference sheet, {argument name="art style" default="Studio Ghibli"} art style, clean cream white background. Bold clean outlines, cel shading, pure 2D anime illustration. Title: {argument name="subject" default="CROISSANT"} — Visual Reference Sheet — {argument name="art style" default="Studio Ghibli"} Style. INGREDIENTS PANEL: {argument name="details" default="Raw dough ball"}

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 44: Infographic / Edu Visual - Titanium Smartphone Triptych

📖 Description

Creates a premium editorial comparison image of three flagship titanium smartphones with brand labels and dramatic accent lighting.

📝 Prompt

Goal: Create a premium editorial comparison triptych of three flagship titanium smartphones side by side, photographed from the rear at matching three-quarter angles, like a luxury tech magazine ad.

Canvas: Wide 16:9 horizontal composition, dark charcoal-to-black gradient studio background, subtle smoky texture, glossy reflective floor line at the bottom, dramatic rim lighting and soft bloom.

Layout: Place a huge thin uppercase headline centered at the top reading {argument name="headline text" default="TITANIUM"}. Directly below it, add the subtitle {argument name="subtitle text" default="Three brands. One metal. Zero agreement."}. Put a small black rounded rectangle badge in the upper-right corner with bold white text {argument name="badge text" default="GPT"}. Center the three phones across the lower two-thirds with equal spacing and identical visual scale.

Subject details: Show exactly 3 smartphones. Left phone: iPhone 16 Pro in Natural Titanium, warm champagne/gold body, rear Apple logo, three large camera lenses in a square camera island, warm gold accent lighting around the edges. Center phone: Samsung Galaxy S24 Ultra in Titanium Gray, dark gray rectangular slab with squared corners, rear Samsung logo, five separate rear camera/sensor circles, electric blue rim light along the right edge. Right phone: Google Pixel 9 Pro in Obsidian black, rear Google G logo, horizontal black camera bar with lenses and flash, green accent rim light along the side.

Visible labels: Include exactly 3 product label groups near the phones. Left label reads "Apple iPhone 16 Pro" on the first line and "Natural Titanium" on the second line. Center label reads "SAMSUNG" on the first line, "Galaxy S24 Ultra" on the second line, and "Titanium Gray" on the third line. Right label reads "Google" on the first line, "Pixel 9 Pro" on the second line, and "Obsidian" on the third line. Add a small creator handle centered at the bottom reading {argument name="creator handle" default="@TechWithYami"}.

Visual style: Ultra-realistic 3D product render, premium editorial lighting, metallic surfaces, soft reflections, crisp lens glass, shallow studio haze, high contrast, cinematic color accents: gold left, blue center, green right.

Constraints: Use exactly three phones and exactly three product label groups; keep all text clean, legible, and minimal; no extra devices, hands, people, charts, or clutter.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 45: Infographic / Edu Visual - Three Steps to a Happy Life Infographic

📖 Description

A warm red-orange hand-drawn Chinese infographic explaining happiness through three simple self-care, focus, and gratitude steps.

📝 Prompt

Goal: Create a clean illustrated Chinese self-improvement infographic titled {argument name="headline text" default="三步拥有幸福人生"}, presenting happiness as three executable small steps like an instruction manual.

Canvas: Wide horizontal 16:9 white background, airy margins, minimalist editorial poster layout. Use a hand-drawn red-orange marker style for all illustrations and large step numbers, with black Chinese body text. Overall feeling: warm, encouraging, simple, practical, like a WeChat article cover illustration.

Header: Center a large rough handwritten red-orange headline at the top: 「三步拥有幸福人生」, with small decorative red strokes on both sides. Under it, add a small black subtitle: 「像说明书一样，把幸福拆成可执行的小步骤」.

Layout: Three equal columns across the lower two-thirds of the canvas, connected visually by red-orange dotted arrows moving left to right. Each column has one doodle illustration above, a thin red divider line, then a step label, huge red step number, bold black title, and three short black lines of explanatory text. Use exactly 3 steps.

Step 1 column, left: Section label 「准备」. Huge red number 「01」 followed by bold title 「先照顾自己」. Body text has exactly 3 lines: 「睡够一点」, 「吃好一点，动一动」, 「把身体和情绪放回正位」. Illustration: a simple smiling person sitting on the floor beside a pillow or bed, holding a steaming mug; include a small smiling sun doodle, a heart speech bubble, and cozy rest/self-care feeling.

Step 2 column, center: Section label 「操作」. Huge red number 「02」 followed by bold title 「认真投入」. Body text has exactly 3 lines: 「每天做好一件重要的小事」, 「专注、练习、持续积累」, 「让生活慢慢长出方向感」. Illustration: a person writing in a notebook, another person reading an open book, a small child watering a potted plant with a heart on the pot; include a checklist clipboard, a clock, books, dotted motion arrows, growth arrows, and a tall sprouting plant to symbolize progress.

Step 3 column, right: Section label 「完成」. Huge red number 「03」 followed by bold title 「分享与感恩」. Body text has exactly 3 lines: 「和喜欢的人保持连接」, 「表达感谢，也庆祝小成就」, 「幸福会在分享中放大」. Illustration: two simple smiling people clinking mugs or cups, a basket of apples with a heart, a smiling sun, a heart speech bubble, and a small award ribbon with a check mark.

Visual style: Red-orange sketch lines should look slightly imperfect and textured, as if drawn with a wax crayon or marker. Text should be crisp and readable, using bold sans-serif Chinese for headings and smaller black sans-serif for descriptions. Keep the design uncluttered, balanced, friendly, and high contrast.

Constraints: Include exactly 3 columns and exactly 3 numbered steps: 01, 02, 03. Preserve the visible Chinese text exactly as specified. Do not add extra panels, photos, gradients, shadows, watermarks, logos, or additional explanatory paragraphs.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 46: Infographic / Edu Visual - Educational Manga Generation Prompt

📖 Description

A comprehensive prompt for creating structured educational or training manga with consistent character designs and professional panel layouts.

📝 Prompt

Common Character Settings + Drawing Rules: Strictly adhere to the character designs of the two protagonists.

Teacher ({argument name="teacher name" default="Midori-sensei"}): Black straight hair in a ponytail with a single thin green highlight. Wears glasses. Wearing a large, ill-fitting white lab coat over baggy gym clothes. Expressive, energetic, and mischievous but proud of being a teacher. Uses large gestures and speaks passionately with hand movements.
Student ({argument name="student name" default="Pink-chan"}): Pale pink hair, slouched posture, with a single cowlick on top of her head. Always looks sleepy with half-closed eyes. Has a laid-back vibe and slow movements. On her desk are a drawing tablet (often used as a pillow), a half-finished strawberry milk, and a rabbit plushie pen case.

Style/Finish Specs: Generate in full color (no monochrome or grayscale). Saturation should be bright like a comedy manga; ensure Midori-sensei's green highlight and Pink-chan's pale pink hair are clearly colored.
Do not display any panel numbers (1, 2, 3, etc.) inside the panels. Labels like 'Panel 1' below are for instruction only. Adhere strictly to the Japanese commercial manga reading order (right-to-left, top-to-bottom starting from top-right). Speech bubble placement should not obstruct this flow. Thick black panel borders. Large, readable Japanese text. Setting is a manga classroom with a whiteboard, desks, and drawing tablets.

[Page 1] Vertical (3:4), 6 panels arranged R-to-L, Top-to-Bottom:
Panel 1: Title panel. Large handwritten-style text: "{argument name="manga title" default="Master the Page-Turn, Master the Manga"}". Midori-sensei holds a book and exaggeratedly demonstrates turning a page. Pink-chan is leaning on her hand, half-asleep.
Panel 2: Pink-chan asks lazily: 'Page-turn...? Does just turning a page really have a name...?' with a '?' above her head.
Panel 3: Midori-sensei's glasses glint. 'Yes! From the last panel on the left page to the first on the right. This bridge is called the "page-turn," and manga artists use every bit of their skill on it!' Background has focus lines.
Panel 4: Diagram panel. A schematic on a whiteboard showing a book spread: labels for 'Hook' on the bottom-left, 'Turn = time eyes leave the paper' in the middle, and 'Rewarding image/line' on the top-right. Midori-sensei points to it with a marker.
Panel 5: Metaphor panel. Midori-sensei speaks with her hand on her heart. 'Panel pacing is like human speech. There are fast parts and slow parts. Within that, the page-turn is—a breath.' Musical rest motifs in background.
Panel 6: Pink-chan mutters: 'A breath... my whole life is like one long breath...' Midori-sensei's small bubble: 'Yours is a deep dive! (You're sleeping!)'.

[Page 2] Vertical (3:4), 7 panels:
Panel 1: Midori-sensei continues. 'Reader focus breaks during the turn. So the last panel on the left must be a "hook" or a natural scene change!' Small example illustration on the side.
Panel 2: 'Then the first panel on the right. Because of the gap, reader expectations are up. You need a great line or image. It's the "build-up" before a big scene!' Example showing a double-page spread feel.
Panel 3: Midori-sensei starts a demo, placing a book in front of Pink-chan excitedly. 'Try it! Look at this last panel... makes you want to turn it, right?'
Panel 4: Pink-chan leans in, eyes slightly wider, reaching for the page. 'Oh... true... I'm curious... about what's next...' A tiny highlight in her eye.
Panel 5: Peak of passion. Midori-sensei's coat flutters. 'Exactly!! When that curiosity stacks, you get a work where the reader can't stop turning pages! It's a gift to the reader!!' Warm heat-tone background.
Panel 6: Pink-chan is face-down on the open book, fast asleep using it as a pillow. 'Zzz...' The page is slightly folded under her cheek.
Panel 7: Midori-sensei collapses. 'Every day!! And using the book as a pillow!!' Small bubble: '...I guess the page-turning stopped.'

🖼️ Generated Images

Image 1
Image 2

📌 Details

👉 Try it now →

No. 47: Infographic / Edu Visual - Apple Design Skill Impact Matrix

📖 Description

A Japanese Apple-style comparison table for reviewing design skill requirements and implementation status across three products.

📝 Prompt

Goal: Create a polished Apple-style Japanese comparison matrix infographic showing which Apple Design Skill review items have implementation impact across three products: {argument name="product column names" default="Flow River, Orbit Canvas, Arc Day"}.

Canvas: Vertical portrait poster, 768 × 1152 px, warm off-white background with subtle paper grain and a faint mint gradient glow near the top right. Center a large rounded white table card with a soft shadow, leaving generous margins. Use a restrained Apple-like editorial style: clean grid, thin dividers, rounded status symbols, muted teal, pale yellow, dusty pink, and gray.

Header: At top left, small uppercase teal label “APPLE DESIGN SKILL · IMPLEMENTATION IMPACT”. Below it, large Japanese headline {argument name="headline text" default="スキルが効いた設計項目"}. Under the headline, add a small gray Japanese description explaining that these are Apple Design Skill items summarized by implementation impact and grouped by initial prototype, skill principles, and later correction/implementation work. At top right place a compact legend with exactly 4 status symbols: teal circle = 合格, yellow triangle = 一部, red X = 未対応, gray dash = 対象外.

Main layout: A wide table with exactly 5 columns: “スキル番”, “Apple Designレビュー項目”, and the 3 product columns named by {argument name="product column names" default="Flow River, Orbit Canvas, Arc Day"}. Use a dark charcoal header row with white text. First two columns are wider; three product columns are equal width. Align item numbers left in teal, item descriptions left in bold dark text, and status symbols centered.

Sections: Use exactly 4 grouped sections with colored band headers:
1. Teal band: “A. スキルが明確に効いた項目　実装・修正・ブラッシュアップ検証まで完了　SKILL IMPACT”. Contains exactly 17 rows: §1 Pointer-downで即時反応; §2 Pointer Events・1:1追従・Pointer Capture; §3 動作中に掴み直せる中断可能性; §4 離れる対象へのスプリング採用; §5 指の速度をスプリングへ引き継ぐ; §7 往復経路の対称性・操作元へのアンカー; §9 境界での段階的なラバーバンド抵抗; §12 半透明Materialによる階層と奥行き; §12 Surfaceサイズに応じたBlur・Shadow重量; §14 Reduced TransparencyでSolid化; §14 Prefers Contrastで境界を強化; §16.1 Purpose：目的が明確で不要機能を抑制; §16.6 Simplicity：主要機能と情報階層の明快さ; §16.7 Craft：文字・間隔・動作の意図的な精度; §16 Wayfinding：現在地・行先・退出方法; §16 Grouping & Mapping：操作と対象の近接; §17 VisualとInteractionを一体設計.
2. Pale yellow band: “B. 一部効いた・改善が必要な項目　原則は反映したが完全実装ではない”. Contains exactly 10 rows: §6 速度から開始する予測するMomentum Projection; §8 途中フレームが操作結果の方向を示す; §10 タップ余白・ドラッグ閾値・キャンセル設計; §11 フレーム品質・compositor向け更新; §14 Reduced Motionで意味的動きへ置換; §15 サイズ別Tracking・Leading・Weight階層; §16.2 Agency：選択・取り消し・失敗からの回復; §16.4 Familiarity：既知の比喩と予測可能な挙動; §16.8 Delight：余白品質から生まれる高揚感; §16 状態・完了・警告・エラーのFeedback.
3. Dusty pink band: “C. 未対応・未検証項目　スキルが示す次の改善対象”. Contains exactly 3 rows: §15 Dynamic Typeに合わせたLayout拡張; §16.5 Flexibility：状況・環境・能力への適応; §17 実利用時・実環境でのテスト.
4. Light gray band: “D. 機能特性上の対象外　未達ではなく、今回のUIに適用領域がない”. Contains exactly 2 rows: §13 音・触覚を同期／即時性／有用性で統合; §16.3 Responsibility：安全・プライバシー・透明性.

Status pattern: Populate all 32 item rows with centered symbols. Section A is mostly teal circles, with a few gray dashes in Flow River and Arc Day matching the look of partial non-applicable cases. Section B mixes teal circles, yellow triangles, and gray dashes, including one red X in the middle product column on the row for tap margin/drag threshold/cancel design. Section C is mostly red X marks, with yellow triangles in some right-side cells. Section D uses gray dashes across all three product columns. Make the symbols small, rounded, lightly tinted, and consistent with the legend.

Footer: Add a tiny gray Japanese note at bottom left beginning with “総括方針：” and a small source note at bottom right {argument name="source note" default="Source: apple-design SKILL.md §9–17"}. Keep the table crisp and readable, no decorative illustrations, no people, no logos besides the text label, no watermark.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 48: YouTube Thumbnail - Asian Digital Influencer Portrait

📖 Description

Generates hyper-realistic, consistent portraits of a fictional digital influencer in a geeky creator room with neon lighting.

📝 Prompt

Create one standalone hyper-realistic portrait per output. Generate four independent image files of the same fictional {argument name="ethnicity" default="Asian"} digital influencer, around {argument name="age" default="28"} years old, with the same face, shoulder-length black hair with subtle blue highlights and {argument name="outfit style" default="black futuristic streetwear"} across the batch.
She is broadcasting from a sophisticated, slightly geeky creator room. Chest-up portrait, direct eye contact, confident friendly expression, professional microphone, headphones, blurred dual monitors, small sci-fi collectibles and tasteful cyan, violet and magenta neon lights. Soft warm key light on her face, realistic skin pores, natural eyes, detailed hair, shallow depth of field and premium 50mm portrait photography.
Vary only her expression, head angle, subtle hand gesture and neon balance between outputs. One woman and one portrait in each image. No grid, collage, contact sheet, split screen, multiple panels, text, logos, watermark, duplicate person, anime or CGI appearance.

🖼️ Generated Images

Image 1
Image 2
Image 3
Image 4

📌 Details

👉 Try it now →

No. 49: YouTube Thumbnail - Cyberpunk Flova AI Agent Poster

📖 Description

Generates a dense cyberpunk anime promotional banner for an AI agent video-production workflow campaign.

📝 Prompt

Goal: Create a high-energy cyberpunk promotional poster for {argument name="brand name" default="Flova"}, advertising an AI agent that helps produce a sci-fi series from planning to finished video.

Canvas: Wide 16:9 YouTube-thumbnail style banner, dark futuristic Tokyo at night, packed with neon light trails, motion blur, glowing HUD panels, sparks, and cinematic contrast. Use a black, electric-blue, purple, orange, and yellow palette with intense bloom and speed-line effects.

Main layout: On the left-center, place a large rainbow gradient triangular play-button logo, followed by an enormous bold white italic wordmark “Flova” dominating the center. Across the top, add a large Japanese headline: “AIと一緒に、世界を創る時代へ。” with the “AI” portion extra-large and white, and a smaller subtitle below it: “企画から映像完成まで、すべてAI Agentがサポート!” On the top-right, add a glowing purple rounded rectangle sign reading “AI Agent” and beneath it “Create the Future with AI”.

Hero character: On the right half, show one dynamic anime-style cyberpunk female agent flying or diving forward toward the viewer above a futuristic city. She has intense golden eyes, short light-brown hair swept by motion, a glossy armored gold-and-black helmet with cat-ear-like mechanical protrusions and a small white flower emblem on the front, black tactical cyber armor, exposed mechanical details, and one gloved hand reaching dramatically toward the camera. Make her foreshortened, sharp, and cinematic, with sparks and city lights streaking behind her.

Text content: Under the logo, add a large line: “2029 IF TOKYO Episode4”, with “Episode4” in purple. Add a small yellow tag: “[ ARCHIVE 004 ]”. Add a bold central Japanese title: “複数のSUZUNE反応”, with “SUZUNE” in large yellow distressed lettering, and a smaller subtitle beneath: “地下鉄駅で発生した、謎の複数シグナルの真相とはー”. In the lower-right, add a huge yellow callout: “シリーズ制作を 最強に加速させる!”

Left feature panel: Add one glowing cyan boxed checklist titled “Flovaでできること”. It must contain exactly 6 checked items: “プロンプト作成”, “Storyboard編集”, “GPT Image 2選択”, “Seedance 2.0生成”, “修正＆再生成”, “Skills保存＆再利用”. Beneath this panel, show exactly 4 small square app icons with labels: “Project”, “Chat”, “History”, and “Skills”.

Bottom offer cards: Along the lower center, add exactly 2 neon credit cards separated by a large white multiplication symbol. The first purple card reads “新規登録で” above a huge “100” and “Free Credits”. The second blue card reads “お友達招待で” above a huge “200” and “Credits”.

Visual style: Ultra-detailed anime key visual mixed with glossy tech advertising design, bold Japanese typography, distressed cinematic title lettering, bright rim lighting, holographic UI overlays, lens flares, fast diagonal composition, and an intense action-poster feel. Keep the design dense but readable, with all listed text clearly placed and no extra logos or watermarks beyond the specified brand elements.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 50: YouTube Thumbnail - Cyber Blue Qwen Tech Review Poster

📖 Description

A high-energy vertical tech review thumbnail featuring a surprised presenter holding a glowing blue token with bold Chinese and model-name typography.

📝 Prompt

Create a dramatic vertical 4:5 tech influencer poster in a glossy cyber-blue style. A young East Asian man with short black hair, black rectangular glasses, and a surprised open-mouth expression leans toward the camera from the right side, wearing a plain black T-shirt. He holds a large glowing circular blue token close to the lens with his left hand in the lower-left foreground, making it appear oversized; the token has a transparent glassy rim, neon blue highlights, and a raised white geometric logo made of three separate block shapes on its face. His right hand points at the token from the right. Use an extreme wide-angle selfie perspective, strong depth distortion, crisp high-contrast lighting, and a dark black background filled with electric blue light streaks, lens flares, and motion lines. Add exactly 3 visible text elements: a huge 3D metallic-blue Chinese headline in the upper-left background reading {argument name="background Chinese headline" default="大力"}, a large italic white-and-blue title across the bottom reading {argument name="model title" default="Qwen3.8"}, and bold white Chinese text at the lower right reading {argument name="test label" default="实测"}. Make all typography extruded, glossy, beveled, and glowing with blue rim light. The composition should feel like a high-energy YouTube thumbnail or social media tech review announcement, ultra sharp, cinematic, slightly surreal, no extra text, no watermark.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 51: YouTube Thumbnail - Premium Men’s Skincare Thumbnail

📖 Description

Creates a dark luxury Japanese thumbnail ad featuring a confident male model, bold Japanese headline typography, and four matte-black grooming products.

📝 Prompt

Goal: Create a cinematic Japanese YouTube thumbnail-style advertisement for a men's grooming or skincare product line, aimed at men who do not know what to choose.

Canvas: 16:9 horizontal thumbnail, dark premium editorial look, high contrast, no border or watermark.

Layout: Place one serious Japanese male model on the left third, cropped from chest upward, wearing a black blazer over a black shirt. He has medium-length wavy black hair, clean-shaven face, slightly tilted head, calm confident expression, and looks directly at the viewer. Put the main headline in the center-right, large and layered over the dark background. Place the product lineup on the far right bottom on a dark stone pedestal.

Text content: Use exactly 3 text groups. Top group: a black slanted rectangular banner with small bold white Japanese text: 「どれ選べばいいか分からない男へ。」 Main group: very large white Japanese Mincho-style serif text with subtle drop shadow: 「女性100人が」 on the first line and 「ガチで選んだ」 on the second line. Highlight group: large metallic gold serif text with quotation marks: 「30代の清潔感」, followed below by large white text: 「の正解。」 Make the gold phrase the strongest focal point after the model.

Subject details: The man should feel like a polished luxury magazine cover: realistic skin texture, moody studio lighting, sharp cheekbones, mature 30s atmosphere, understated masculinity. Use {argument name="model description" default="a handsome Japanese man in his 30s with wavy black hair wearing a black blazer"}.

Product details: Show exactly 4 matte-black grooming containers on the right: 1 tall pump bottle at the far right, 1 tall squeeze tube just left of it, 1 low cylindrical jar in front, and 1 wider low cylindrical container behind the jar. All products are unlabeled, minimal, premium, and softly rim-lit.

Visual style: Dark charcoal-blue background with a diagonal spotlight beam from the upper right, subtle smoky haze around the center text, premium black-and-gold color palette, realistic commercial photography, glossy but restrained highlights, crisp typography.

Customizable headline parameters: Use {argument name="top banner text" default="どれ選べばいいか分からない男へ。"}, {argument name="main white headline" default="女性100人が\nガチで選んだ"}, {argument name="gold key phrase" default="「30代の清潔感」"}, and {argument name="closing text" default="の正解。"}.

Constraints: Keep the composition uncluttered, ensure all Japanese text is large and legible, do not add extra labels to the products, do not add logos, do not add more than one person, and keep exactly 4 visible product containers.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 52: YouTube Thumbnail - Japanese Pricing Comparison Thumbnail

📖 Description

Generates a high-impact Japanese social media thumbnail comparing a crossed-out high subscription price with a cheaper monthly plan.

📝 Prompt

Goal: Create a bold Japanese YouTube/X thumbnail about subscription pricing being too expensive, using a dramatic comparison between a crossed-out high monthly fee and a cheaper monthly fee.

Canvas: Vertical 3:4 thumbnail, 768×1024 style, optimized for mobile readability. Use a dark navy-to-deep-purple gradient background with a subtle spotlight glow behind the person. Keep all main text inside safe margins and make it extremely large, high-contrast, and legible.

Layout: At the very top, place exactly 2 hanging price tags suspended by thin strings: left tag is red, tilted slightly, with the text {argument name="old price text" default="月15,000円"} in bold white and a thick white diagonal strike-through line; right tag is neon green, tilted slightly, glowing, with the text {argument name="new price text" default="月3,000円"} in bold white. Below the tags, center a huge white headline with black shadow: {argument name="headline text" default="その課金、まだ早い"}. Under the headline, add one bright yellow rectangular banner spanning nearly the full width, with bold black text: {argument name="subheadline text" default="月3,000円で足りる21の使い方"}.

Subject details: In the lower half, show a realistic studio-cutout portrait of a smiling young Japanese woman with long black hair and bangs, wearing a beige knit sweater. She faces the camera, raises her left hand open toward the viewer in a clear “stop/wait” gesture, and holds a gold credit card in her right hand. Use natural skin tones, clean beauty lighting, and a crisp cutout edge.

Decorative elements: Add exactly 3 small floating gold yen coins with embossed yen symbols: one on the left upper-middle area, one near the lower-left edge, and one on the right-middle area. Add exactly 2 white speech/chat bubbles with three dark dots: one on the left side near the raised hand and one on the right side near the headline/shoulder area. Do not add extra coins, bubbles, icons, logos, or watermarks.

Visual style: High-impact Japanese social media thumbnail, glossy 3D accents, strong drop shadows, neon glow on the green tag, clean compositing, sharp typography, saturated colors, professional viral-cover design. Make the text accurate and not garbled.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 53: YouTube Thumbnail - Japanese AI Telop Thumbnail

📖 Description

A bold Japanese YouTube thumbnail layout promoting AI-powered automatic caption creation using Vrew and Claude Code.

📝 Prompt

Goal: Create a high-impact Japanese YouTube thumbnail about automatically generating video captions/telops with AI, featuring a dramatic comparison from Vrew to Claude Code.

Canvas: 16:9 horizontal thumbnail, 1200×675 style, optimized for YouTube. Use a dark blurred video-editing timeline interface as the full background, with purple and blue timeline tracks and small clip blocks visible but out of focus.

Layout: Put a huge bold Japanese headline across the top reading {argument name="top headline" default="AIでテロップを自動作成"}. The letters should be white with thick black outline and an additional thin white outer stroke, slightly tilted and tightly spaced for maximum impact. Place one large white speech-bubble complaint box on the left-middle with a black outline and a small pointer at the bottom right. Inside it, use bold black Japanese text for the complaint and a red emphasized final line with a yellow underline: {argument name="complaint text" default="誤字脱字多すぎるし、テロップはズレまくってるし、変なところで改行するし、そのくせにそれ以外のことは何もできないって...\nVrewマジで使えんw"}. Place two app-style logo tiles in the center-right: exactly 2 logos total. Logo 1 is a cyan-blue rounded square Vrew-like icon with a white V mark, located near the center, partially overlapped by a small orange pixelated mascot/bug shape. Logo 2 is a larger orange-red rounded square Claude-like icon with a white radial starburst, located to the upper right, with a shiny gold crown tilted on its top-right corner. Add a small white label under the orange icon reading {argument name="tool label" default="Claude Code"} in bold black text. Between the two logos, add exactly 1 curved red arrow with a white outline pointing from the blue logo toward the orange logo.

Bottom text: Fill the bottom third with one enormous Japanese conclusion phrase reading {argument name="bottom headline" default="これで全て解決"}. Make it thick rounded display lettering with a bright yellow gradient fill, heavy black outline, and glowing white outer stroke. The text should overlap the background and partly sit in front of the center graphics, creating a loud thumbnail composition.

Visual style: Japanese viral tech thumbnail, extremely bold contrast, dense composition, exaggerated outlines, drop shadows, white glow effects, saturated colors, black background atmosphere, urgent and humorous tone. Make all Japanese text crisp, legible, and correctly spelled.

Discrete elements to include: exactly 1 top headline, exactly 1 speech bubble, exactly 2 app logos, exactly 1 orange mascot/bug shape, exactly 1 red curved arrow, exactly 1 gold crown, exactly 1 Claude Code label, and exactly 1 huge bottom headline. Do not add extra logos, people, watermarks, or unrelated text.

🖼️ Generated Images

Image 1
Image 2

📌 Details

👉 Try it now →

No. 54: YouTube Thumbnail - Consistent Social Media Cover Agent Skill

📖 Description

A workflow description for an AI agent skill that generates consistent social media covers using multi-reference images, compatible with GPT-Image models.

📝 Prompt

Input an article, go through three rounds of Q&A, and it directly outputs cover prompts that can be used for image generation. No need to understand design, no need to write prompts yourself, the aspect ratio is fixed at 3:4, and facial consistency can be maintained.👇 👹 The entire workflow is as follows: 1. Skill installation and first-time configuration (save a photo of your own face + confirm the image generation model) 2. Give the article content to the agent, which automatically reads and refines it 3. Round 1: Recommend composition styles based on content (10 options to choose from) + automatically come up with candidate titles 4. Round 2: Face reference images + materials such as UI screenshots/product images 5. Round 3: Choose expressions, background tones, fonts, and font colors all at once, or leave it all to the model if you're lazy 6. Output complete prompts: 3:4 composition, safety zone, multi-reference image writing for Image 1 (face) + Image 2 (materials) are all included 7. Take it to Jimeng / Nano Banana / GPT-Image to generate images (if your agent has an image generation API configured, you can have it generate directly in the conversation) 8. Check if the titles have typos, and regenerate any parts you're unhappy with. 🧐 Tips: You must choose an image generation model that supports multiple reference images, otherwise facial consistency cannot be guaranteed. The skill has 8 built-in sets of example prompts reverse-engineered from real trending covers, and the model will automatically use them as references, pushing the image detail to the maximum.

🖼️ Generated Images

Image 1
Image 2
Image 3
Image 4

📌 Details

👉 Try it now →

No. 55: YouTube Thumbnail - Retro 2.5D Anime CRT Girl

📖 Description

A cinematic retro anime thumbnail featuring a sharp-toothed gothic girl in a VHS-styled analog electronics room.

📝 Prompt

Create a retro 2.5D anime thumbnail in a cinematic 16:9 frame, showing a close-up of {argument name="character name" default="a mischievous gothic anime girl"} leaning toward the camera in a cluttered analog electronics room. She has long straight {argument name="hair color" default="black hair"} with blunt bangs, teal-green eyes, pale skin, small blush marks, pointed ears, and a wide unsettling grin with sharp triangular teeth. She wears a black top and a thin black choker, with her face centered and dominating the composition, shoulders cropped at the bottom, direct eye contact, playful but eerie expression. The background is a dim retro tech studio with exactly two visible CRT televisions: one large CRT on the left displaying bright cyan static and one darker CRT on the lower right with a small blue glow; include shelves, cables, ceiling pipes, hanging wires, old equipment, and a high window with washed-out daylight. Use a NORINORI CORE-inspired retro 2.5D aesthetic: cel-shaded anime character over a semi-realistic grungy room, thick ink outlines, muted olive-gray shadows, teal and magenta chromatic aberration along edges, VHS scanline noise, slight fisheye wide-angle distortion, low-light atmosphere, crisp face details, gritty analog texture, 1990s cyberpunk anime mood. Keep the image text-free, no logos, no watermark, no extra characters.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 56: YouTube Thumbnail - Cute Travel Vlog Thumbnail

📖 Description

Generates a cheerful vertical travel vlog cover with a smiling backpacker, pastel sticker typography, and kawaii travel doodles for social posts or video thumbnails.

📝 Prompt

Goal: Create a bright vertical travel vlog thumbnail/collage featuring a smiling young woman traveler in a sunny outdoor alley, surrounded by cute scrapbook stickers and hand-drawn doodles.

Canvas: Vertical 3:4 social media image, high-resolution, warm daylight, shallow depth of field. Background is a charming pedestrian street or café alley with plants, terracotta umbrellas, soft bokeh, and a small chalkboard sign in the distance.

Main subject: A cheerful {argument name="character description" default="young East Asian woman with shoulder-length black hair and bangs"} stands slightly right of center, turned three-quarters toward the camera, smiling warmly. She wears a loose white T-shirt with a small nature print on the chest, light blue jeans, and a large beige backpack over one shoulder. Add a cute plush keychain hanging from the backpack. Put a thick white cutout outline around the subject, like a sticker.

Layout and text stickers: Use exactly 6 main text stickers: 1) large top-left title reading {argument name="main title" default="Travel Vlog"} in oversized rounded pastel bubble letters with a thick white border; 2) top-right stacked sticker reading {argument name="top right phrase" default="Good Vibes Only"} with a yellow heart and yellow smiley face; 3) small pink ribbon banner on the left reading {argument name="banner text" default="let's go!"}; 4) dark cloud speech bubble on the right reading "explore more" with a small pink heart; 5) bottom-left sticker reading "on the way" in playful blue and pink bubble letters with a small white flower; 6) bottom-right sticky note reading {argument name="note text" default="Collect moments not things"} with a pink tape strip and a small heart.

Decorative elements: Include exactly 3 illustrated travel icons: a cute line-art camera with a heart on the lens on the left, a folded map with a pink location pin on the lower right, and the backpack plush charm. Add multiple small white hand-drawn sparkles, arrows, hearts, squiggles, and doodle marks scattered around the subject, keeping them light and airy.

Visual style: Photorealistic lifestyle portrait blended with kawaii sticker graphics, pastel colors, glossy scrapbook aesthetic, soft white outlines, playful vlog thumbnail design, warm golden sunlight, cheerful vacation mood.

Constraints: Keep all text legible and in English, preserve the exact 6 main text stickers and 3 illustrated travel icons, avoid extra large words, avoid watermarks or logos, and make the subject the clear focal point.

🖼️ Generated Images

Image 1
Image 2
Image 3

📌 Details

👉 Try it now →

No. 57: YouTube Thumbnail - Roblox Block Tower Thumbnail

📖 Description

A colorful Japanese Roblox-style game thumbnail for a block-tower obstacle course with chibi characters, treasure collection, gacha rewards, and mobile-game UI callouts.

📝 Prompt

Goal: Create a bright square Roblox-style promotional game thumbnail for {argument name="game title" default="巨大アスレチック ブロックタワーを駆け上がれ！"}, an exciting block-tower obby where players climb a giant toy-brick tower and collect treasure chests to spin a gacha.

Canvas: Square 1:1 thumbnail, 768x768 or larger, ultra-saturated colors, high-contrast mobile-game advertising composition, thick white and black sticker outlines around every character and text element.

Layout: Put the red-and-white ROBLOX logo at the top left. Fill the background with a huge vertical tower made from colorful LEGO-like plastic studs and brick platforms, receding upward into a blue sky with clouds. Place the main Japanese headline across the upper-middle in giant layered text: a small black rounded label reading 「巨大アスレチック」 above enormous rainbow block letters reading 「ブロックタワー」, followed by bold white text with black outline reading 「を駆け上がれ！」 with yellow star icons on both sides. Under the title, add a blue banner with white text: 「宝箱を集めてガチャを回そう！」. Add two game HUD counters at the top right: exactly 2 rounded black panels, one showing a gold coin icon and 「1,234」, the other showing a treasure chest icon and 「宝箱 7/10」.

Characters and objects: Include exactly 8 main visible characters: 1 cheerful orange-haired chibi girl in a yellow martial-arts outfit running in the foreground, 1 smiling panda companion at bottom left, 1 green-haired crowned chibi girl in a green outfit on the left, 1 red-kimono chibi girl near center, 1 black-haired ponytail chibi adventurer in green at center, 1 gray-helmet chibi girl with a small round helmet to the right of center, 1 purple wolf-eared chibi boy on the right, and 1 dark ninja boy flying at the upper right holding a small black cat. Include exactly 3 small pet/mascot creatures near the right group: a tiny black cat with the ninja, a yellow chick-like mascot, and a pink bunny-like mascot. Add exactly 1 golden treasure chest in the lower center foreground and exactly 1 red-and-gold capsule gacha machine at the lower right filled with multicolored balls and topped with a gold star. Scatter a few sparkling gold coins and star effects around the scene.

Callouts and UI: Add a jagged red-yellow burst callout near the gacha machine reading 「宝箱の数だけ ガチャが回せる！」. Along the bottom edge, add exactly 4 black rounded instruction cards with orange outlines and icons: 1 chest icon card reading 「宝箱を集めて ガチャを回そう！」, 1 stopwatch icon card reading 「タイムアタックで ランキング上位を目指そう！」, 1 badge icon card reading 「バッジを集めて 図鑑をコンプリート！」, and 1 checkpoint flag icon card reading 「セーブポイントで どこでも復帰！」.

Visual style: Roblox-inspired toy-block world, glossy 3D plastic bricks, chibi anime characters with oversized heads, big expressive eyes, joyful adventurous expressions, dynamic running poses, cartoon lighting, sparkle effects, strong drop shadows, thick outlines, vivid red yellow green blue purple palette, busy but readable YouTube thumbnail composition.

Constraints: Keep all visible text in Japanese exactly as specified, make the headline the dominant focal point, use exactly 8 main characters, exactly 3 small pet mascots, exactly 2 top-right HUD counters, and exactly 4 bottom instruction cards. No photorealism, no watermark, no extra logos beyond ROBLOX.

🖼️ Generated Images

Image 1
Image 2

📌 Details

👉 Try it now →

No. 58: YouTube Thumbnail - Low-Cost AI Video Thumbnail

📖 Description

A wide Japanese tech-marketing thumbnail for an article or video about starting AI video production with a low-cost strategy.

📝 Prompt

Goal: Create a wide 21:9 Japanese article thumbnail / YouTube-style banner advertising a low-cost AI video creation strategy, with bold energetic typography and a futuristic creator-workstation theme.

Canvas: Ultra-wide horizontal banner, 1200×514 style aspect ratio, bright blue-and-white tech background with slight vignette, glossy lighting, and high contrast for readability.

Layout: Use a dynamic diagonal composition. The left two-thirds is dominated by oversized headline typography on layered white slanted panels with drop shadows. The right third shows a young male creator seen from behind at a laptop, looking at floating video-production screens. The bottom left contains a dark navy slanted caption bar with a secondary Japanese message. Add small icon circles along the lower right edge.

Text content: Main headline must read exactly: 「Low Costで」 on the top white strip, 「AI動画」 in huge blue letters below it, 「をやるなら」 in smaller dark text beside it, and 「コレ!!」 in large hot pink letters with white outline on the right. Bottom caption bar must read exactly: 「12社のCPPに参加している筆者が、今ゼロから始めるならこの戦略で行く」 with 「12社」 and 「この戦略」 emphasized in yellow and the rest in white. Add a small handwritten note in the bottom right: 「はじめてでも安心！」 with a yellow underline.

Subject details: Show {argument name="main character" default="a young Japanese male creator in a navy jacket, viewed from behind, hand on chin, facing a laptop"}. The laptop screen should show a video editing interface with timeline tracks and preview frames. Around the character, include exactly 4 floating media panels: 1 cinematic sci-fi hallway scene, 1 futuristic city skyline at sunset, 1 fantasy mountain landscape, and 1 software/dashboard screen. Add exactly 1 black-and-white movie clapperboard near the upper center, exactly 1 translucent play-button tile near the headline, and exactly 3 circular icons at the lower right: a pink piggy bank with yen symbol, a blue rising bar chart, and a checklist clipboard.

Visual style: Polished Japanese marketing thumbnail, crisp vector typography mixed with semi-realistic digital illustration, electric blue gradients, white glow, subtle circuit-board lines in the background, dotted halftone accents, energetic shadows, yellow paint-stroke highlight behind the top headline, strong outlines around text, clean professional finish.

Parameters: The main headline concept is {argument name="headline concept" default="Low Costで AI動画をやるならコレ!!"}; the bottom copy theme is {argument name="bottom message" default="12社のCPPに参加している筆者が、今ゼロから始めるならこの戦略で行く"}; the accent color for the callout word is {argument name="accent color" default="hot pink"}.

Constraints: Keep all visible text in Japanese exactly as specified, avoid misspellings, avoid extra logos or watermarks, preserve the 21:9 thumbnail readability, and make the headline occupy most of the left side.

🖼️ Generated Images

Image 1

📌 Details

👉 Try it now →

No. 59: YouTube Thumbnail - Cine

View this README on GitHub

Рекомендуемые инструменты

Попробуйте другой запрос или уберите фильтр.

Установка

npx skillfish add youmind-openlab/awesome-gpt-image-2