検証済みの例

プロンプトギャラリー

実際のプロンプトと生成画像を組み合わせています。結果を確認し、そのままコピーして出発点にできます。

5,541
モデル
6
出典
10
5,541 件の検証済みペア · ページ 36 / 116
Example generated from “GPT Image 2 Trending Anime Art Style Redraw”
GPT Image 2en
GPT Image 2 Trending Anime Art Style Redraw

Create a trending anime art style image from the uploaded subject. Use confident line-work with slight variation and minimal cel shading using flat shadow shapes. Use bright, saturated colors and clean graphic lighting. The style is defined by exaggerated, cartoonish character proportions featuring highly expressive, simplistic facial features that allow for immense emotional range, with highly varied stretched anatomy.Transform the environment into a slightly warped space with playful perspective distortion and simplified objects. Composition and tone should be energetic, lively, and comedic in a fully stylized, non-realistic world

Example generated from “GPT Image 2 Warm Home Appliance Product Poster”
GPT Image 2zh
GPT Image 2 Warm Home Appliance Product Poster

请生成一张高质感家电产品广告海报,主体为「{主体}」。以主体为视觉核心,自动适配其对应的生活方式场景、辅助物品、装饰元素、关键词、卖点徽章、功能图标说明与整体色彩风格。画面布局为:顶部大号主标题 + 手写感副标题 + 关键词;中部主体产品置于符合其使用逻辑的精致生活场景中;左右加入圆形卖点徽章与 4~5 个功能图标说明;底部展示产品名称标签。整体风格要求温暖治愈、柔和暖光、真实材质、现代干净排版、商业广告质感、低饱和协调配色、4K 超清,适合品牌宣传、电商海报、社交媒体视觉展示。一切元素围绕主体自动生成并服务于主体,不喧宾夺主,不杂乱,不低质。 主体:咖啡壶

Example generated from “GPT Image 2 Y2K Pop-Street Editorial Collage”
GPT Image 2en
GPT Image 2 Y2K Pop-Street Editorial Collage

Create a bold Y2K pop-street editorial collage featuring a young person as the central subject, combining playful graffiti typography, orange poster background, sticker-like graphic elements, and fashion magazine layout energy. MAIN SUBJECT AND FRAMING: Place the young person on the right side of the composition in a close-up to upper-body portrait. The face should be large and dominant, cropped from the chest upward, with the subject slightly leaning forward into the frame. The composition should feel asymmetrical, with graphic typography filling the left side and the subject anchoring the right side. Do not control or describe the hairstyle. OUTFIT DETAIL: Style the subject in a minimal black streetwear outfit. They wear a black turtleneck or high-neck top with a soft fitted silhouette, creating a clean dark shape against the bright orange background. Add a black beret or rounded cap with a small embroidered logo detail on the front, giving the look a stylish retro street-fashion feeling. Add a small colorful cheek sticker or decorative bandage on one cheek, with cute tiny graphic details, making the styling feel playful and idol-like. Keep the outfit mostly black so the blue graffiti typography and orange background stand out strongly. BEHAVIOUR AND BODY LANGUAGE: The subject’s body language should feel calm, closed-off, and slightly moody. The shoulders are relaxed but slightly rounded forward, creating a soft guarded posture. The head tilts subtly downward and to the side, giving the portrait a cool detached attitude. The subject does not need a big hand gesture in the main portrait; instead, the behaviour comes from the face angle, lowered posture, and intense sideways eye movement. The pose should feel like someone caught in a quiet bratty moment, not fully engaging with the viewer. FACIAL EXPRESSION: The expression is pouty, serious, and mildly irritated in a fashionable way. The lips are softly pushed forward into a small pout, brows slightly tense, and the eyes look sideways with a suspicious or unimpressed gaze. The mood should feel bratty, stylish, aloof, and quietly rebellious. GRAPHIC BACKGROUND: Use a saturated orange background with a large white starburst shape behind the subject’s head and shoulders. The starburst should create strong comic-book energy and make the face pop. Add hand-drawn black scribble text across the orange background, like messy diary writing or lyric notes. Include phrases such as: “EENIE MEENY MINEY MO” “4:03” “LOVE DAY” “HIDE YOUR LOVE” “BOYZ” The handwriting should look playful, imperfect, thin, and chaotic, but still visually controlled. MAIN TYPOGRAPHY: Place a large blue graffiti-style word “Your Name” across the left-center area. The letters should be chunky, rounded, irregular, and outlined in thick black, like a playful bubble graffiti tag. The typography should overlap slightly with the subject’s face area without blocking the eyes. Add pink star sparkle stickers around the face and cap area, giving a cute pop-idol accent. BOTTOM FILMSTRIP: At the bottom of the composition, add a horizontal filmstrip with four rectangular photo panels. These panels show smaller full-body and close-up poses of the same young person wearing the same black outfit. Panel pose ideas: 1. Side close-up portrait with head tilted back slightly, cheek sticker visible, eyes looking away. 2. Full-body stance with legs apart, hands near pockets or belt area, posture confident and relaxed. 3. Repeated close-up side portrait for rhythmic collage effect. 4. Repeated full-body stance, slightly different angle or crop. The filmstrip should feel like a fashion contact sheet or idol editorial preview. MOOD AND STYLE: The overall mood should be playful, bratty, nostalgic, and street-fashion inspired. It should feel like a Y2K teen magazine layout mixed with graffiti poster design, idol concept styling, and scrapbook-like pop graphics.

Example generated from “GPT-2 Comic Creation Logic Poster”
GPT Image 2en
GPT-2 Comic Creation Logic Poster

Goal: Create a vertical Chinese promotional infographic poster about unlocking comic creation logic with GPT-2, using a playful hand-drawn editorial style. Canvas: Portrait 3:4 poster, warm off-white textured paper background, soft pastel palette, slightly grainy risograph print texture, rounded friendly shapes, dark teal headline typography, coral accent text, pale green/yellow/pink/lavender section cards. Layout: Left side is a bold text-heavy headline and feature list; right side is a large illustration of an open padlock with a glowing keyhole releasing comics, sketches, speech bubbles, arrows, and diary pages. Bottom right has an open comic book, with pages and comic panels swirling upward from it into the lock area. Keep generous margins and a lively but readable composition. Text content: Use a large Chinese headline at top left: {argument name="headline text" default="漫画的\n创作逻辑"}. Under it, add smaller bold Chinese copy: {argument name="subheadline text" default="就这么水灵灵的被\nGPT-2 解锁了"}, with “GPT-2” in large coral red and the rest in dark teal/black. Add a green underline and smaller line: {argument name="tagline" default="这个思路,真是让人好生喜欢"}. Include small decorative coral sparkle marks and a hand-drawn heart near the tagline. Feature cards: Place exactly 4 rounded horizontal cards stacked vertically on the lower left, each with one circular icon on the left and bold Chinese label on the right. Card 1 is pale green with an open notebook and pencil icon, label {argument name="card one label" default="日记转"}. Card 2 is pale yellow with a lightbulb rising from an open book icon, label “知识转”. Card 3 is pale peach with a steaming mug icon containing a heart, label “鸡汤转”. Card 4 is pale lavender with a paper airplane icon, label “各种转换,\n玩的飞起”. From each of the 4 cards, draw one dotted arrow pointing right toward the flying comic materials; use matching muted arrow colors. Right-side subject details: Draw exactly 1 oversized open padlock in muted green-gray, positioned upper right, with chalk-like doodles on its body: tiny speech bubbles, comic thumbnails, and simple character sketches. Insert exactly 1 golden key into the keyhole; the key has a fountain-pen nib as its handle, symbolizing writing unlocking comics. Make the keyhole glow with warm yellow light. Flying comic materials: Show exactly 6 loose paper/comic elements floating from the open book toward the lock: 1 small portrait sketch sheet, 1 four-panel comic page, 1 single-page layout with a yellow image block, 1 two-character dialogue comic page, 1 small pink note page, and 1 larger horizontal comic strip page. Add curved motion trails, sparkles, tiny hearts, arrows, and speech bubbles around them, but keep the main count of loose sheets exactly 6. Bottom illustration: Draw exactly 1 open comic book at the lower right with visible comic panels and a cute simple character on the left page; use thin dark teal linework and pale yellow highlights. Add soft cloud-like pale green shapes along the bottom edge of the poster. Visual style: Cute Chinese social-media poster aesthetic, hand-drawn line art, rounded sans-serif Chinese typography, vintage print grain, pastel accents, clean hierarchy, whimsical educational tone. Constraints: Maintain the exact 4 feature cards and exact 6 loose flying paper/comic elements. Do not add extra major sections, extra logos, watermarks, QR codes, or English explanatory text beyond “GPT-2”.

Example generated from “GPT-Image V2 Feature Announcement”
GPT Image 2en
GPT-Image V2 Feature Announcement

Please generate an image for me, with the following description.{argument name="announcement content" default="GPT Image V2 is now fully available."}

Example generated from “GPT-Image-2 Creative Prompt List”
GPT Image 2en
GPT-Image-2 Creative Prompt List

1. Generate a sheet containing{argument name="characters" default="Mai Shiranui and Diao Chan"} 1. A game battle poster. 2. Generate a poster.{argument name="group type" default="K-pop group"} 3. Please design a stylish album cover.{argument name="work title" default="Battle Through the Heavens"} 4. Generate a core relationship diagram. Please take a screenshot of a female influencer's profile on Douyin (TikTok) for uploading.

Example generated from “GPT-Image-2 Creative Prompt List”
GPT Image 2zh
GPT-Image-2 Creative Prompt List

1、生成{argument name="角色" default="不知火舞和貂蝉"}的游戏对战海报图 2、生成一张{argument name="团体类型" default="K-pop团体"}时尚专辑封面 3、请你生成 《{argument name="作品名" default="斗破苍穹"}》 的关键人物关系图 4、帮我截一张上传图片的抖音首页的女网红图

Example generated from “GPT-Image-2 Detail Showcase”
GPT Image 2zh
GPT-Image-2 Detail Showcase

以眼部特写图片为基础,生成3:4的四屏构图超写实眼部特写,四屏按春夏秋冬上下排序。 第一屏:眼眸中带着绽粉樱色的美瞳,睫毛缀满迷你春花,脸颊散落樱瓣与黄蕊小花,粉蝶萦绕眉眼,浅金发丝轻垂,下方簇簇樱花怒放,画面中央"SPRING"白色艺术字点缀,风格细腻唯美,光影柔和,色彩粉嫩治愈,下面用书法体写着春; 第二屏:眼眸中带着着清荷色的美瞳,睫毛饰以粉莲与绿荷,脸颊挂着晶莹水珠,粉瓣、绿荷点缀其间,蜻蜓轻绕,浅金发丝若隐若现,画面中央"Summer"白色艺术字凸显,光影通透流光感,色彩清透凉爽,下面用书法体写着夏; 第三屏:眼眸中带着金黄红相间的美瞳,睫毛饰以橙红枫叶,脸颊散落金红秋叶,橙蝶翩跹眉眼间,浅金发丝隐约可见,画面中央"AUTUMN"白色艺术字醒目,光影暖金流光,色彩浓郁温暖,下面用书法笔写着秋; 第四屏:眼眸中带着雪花蓝色的美瞳,睫毛覆满冰晶雪片,脸颊散落白色雪花与红色腊梅,银白蝴蝶翩跹眉眼,浅金发丝朦胧似雪,画面中央"WINTER"白色艺术字亮眼,光影冷冽蓝白流光,色彩清透纯净,下面用书法体写着冬。 整体呈现梦幻眼眸四季交替的唯美梦幻治愈画面,微调各屏的光影强度,让画面氛围感更浓郁。

Example generated from “GPT-Image-2 Transparency Prompting Guide”
GPT Image 2ja
GPT-Image-2 Transparency Prompting Guide

これは1枚の完成された絵ではなく、単体で使う素材です isolated object fully transparent alpha no backdrop no rectangle no plinth no cast shadow

Example generated from “Graffiti Sketch AI Builder Style”
GPT Image 2en
Graffiti Sketch AI Builder Style

Expressed in a doodle sketch style [{argument name="subject" default="a powerful AI builder"} The overall visual effect is that of a quick sketch, free deformation, improvisation, and draft. Lines are casual, exaggerated, and vary in thickness, appearing slightly chaotic yet rhythmic and expressive, emphasizing generalization, exaggeration, fun, and spontaneity rather than rigorous realism or fine detail. Colors are rendered with bold, dry brushstrokes, retaining uneven application, brushstrokes, dry brush, and overlapping. Colors automatically adapt to the theme/subject, but the overall style remains graffiti, sketch, and generalization. There is no transparent watercolor wash, no delicate watercolor transitions, no paper texture, no soft mist, and no dreamlike quality. The background is predominantly white, maintaining simplicity, ease, a sense of unfinishedness, and design. A small number of auxiliary symbols, arrows, marks, circles, repeating lines, handwritten text, or other graffiti elements can be added to enhance the visual language of the sketchbook or doodle, but these should not be overly crowded or disrupt the white space and atmosphere. Image content does not need to be pre-defined;{argument name="subject" default="a powerful AI builder"} It will automatically deduce and generate the most suitable main image, action, related elements, symbols, or simplified scene. It maintains a consistent doodle/sketch style and exaggerated, generalized expression, avoiding complex realistic backgrounds and excessive detail. It naturally incorporates a unique signature.{argument name="signature" default="BlanPlan"} As part of the image, place it discreetly and clearly in the lower left corner, lower right corner, or near the title. The style should be consistent with the overall layout, like an artist's signature or design inscription; the signature font should be exquisite, restrained, and sophisticated, not too large, not disrupting the main composition, and not appearing abrupt or cheap.

Example generated from “Graffiti Sketch Style AI Builder”
GPT Image 2en
Graffiti Sketch Style AI Builder

Expressed in a doodle sketch style{argument name="subject" default="A powerful AI builder"} The style presents a visual effect reminiscent of rapid sketching, free deformation, improvisation, and drafts. Lines are casual, exaggerated, and vary in thickness, appearing slightly chaotic yet rhythmic and expressive, emphasizing generalization, exaggeration, playfulness, and spontaneity rather than rigorous realism or meticulous detail. Colors are presented in bold blocks, with a distinct dry brush feel, retaining uneven application, brushstrokes, dry brush, and layering. Colors automatically adapt.{argument name="theme" default="Powerful AI builder"} However, the overall style remains doodle-like, sketch-like, and generalized. Avoid using transparent watercolor washes, delicate watercolor transitions, paper textures, soft mists, or dreamlike effects. The background is primarily white, maintaining a simple, relaxed, unfinished, and design-oriented feel. A few auxiliary symbols, arrows, marks, circles, repeating lines, handwritten text, or other doodle elements can be added to enhance the visual language of the sketchbook or doodle, but these should not be overcrowded to avoid disrupting the subject and the atmosphere of white space. The content of the image does not need to be pre-defined;{argument name="character image" default="A powerful AI builder"} The system will automatically generate the most suitable main image, actions, related elements, symbols, or simplified scenes. The overall style should maintain a consistent doodle sketch feel and exaggerated, generalized expression, avoiding complex realistic backgrounds and excessive details. A distinctive signature, "BlanPlan," should be naturally incorporated into the image, placed discreetly but clearly, such as in the lower left corner, lower right corner, or near the title. The signature style should be consistent with the overall layout, like an artist's signature or design mark; the signature font should be refined, restrained, and sophisticated, not too large, and should not disrupt the main composition, appearing abrupt or cheap.

Example generated from “Graffiti Sketch Style Template”
GPT Image 2en
Graffiti Sketch Style Template

Expressed in a doodle sketch style{argument name="subject" default="Theme/Main Body"} The overall visual effect is one of rapid sketching, free deformation, improvisation, and draft-like drawing. The lines are casual, exaggerated, and vary in thickness, appearing slightly chaotic yet rhythmic and expressive, emphasizing generalization, exaggeration, playfulness, and spontaneity rather than rigorous realism or meticulous detail. Colors are rendered in bold blocks, exhibiting a distinct dry brush feel, retaining uneven application, brushstrokes, dry brush, and layering. The colors adapt automatically.{argument name="subject" default="Theme/Main Body"} However, the overall expression maintains a doodle-like, sketch-like, and concise feel. There are no transparent watercolor washes, no delicate watercolor transitions, no paper textures, no soft mist effects, and no dreamlike quality. The background is primarily white, maintaining a simple, relaxed, unfinished, and design-oriented feel. A few auxiliary symbols, arrows, marks, circles, repeating lines, handwritten text, or other doodle elements can be added to enhance the visual language of the sketchbook or doodle, but these should not be overcrowded to avoid disrupting the subject and the atmosphere of the white space. The content of the image does not need to be pre-defined;{argument name="subject" default="Theme/Main Body"} The system will automatically generate the most suitable main image, actions, related elements, symbols, or simplified scenes. The overall style should maintain a consistent graffiti-style sketch aesthetic with exaggerated, generalized expressions, avoiding complex realistic backgrounds and excessive details. A distinctive signature, "voxcat," should be naturally incorporated into the image, discreetly but clearly placed, such as in the lower left or right corner, or near the title. The signature style should be consistent with the overall layout, like an artist's signature or design mark; the signature font should be refined, restrained, and sophisticated, not too large, and should not disrupt the main composition or appear abrupt or cheap.

Example generated from “Graffiti Sketch Style Template”
GPT Image 2zh
Graffiti Sketch Style Template

以涂鸦速写风表现【{argument name="主体" default="主题/主体"}】,整体呈现快速勾勒、自由变形、即兴手绘与草稿式的视觉效果。线条随手、夸张、可粗细不一,略显凌乱 but 具有节奏和表现力,强调概括、夸张、趣味 and 随性,而不是严谨写实或精细刻画。 颜色采用粗糙、干刷感明显的块面表现,可保留不均匀的涂抹痕迹、刷痕、飞白与覆盖感,色彩根据【{argument name="主体" default="主题/主体"}】自动适配,但整体保持涂鸦式、速写式、概括式的表达。不要透明水彩晕染效果,不要细腻水彩过渡,不要纸纹理,不要柔和雾化,不要梦幻质感。 背景以留白为主,保持简洁、轻松、未完成感和设计感,可加入少量辅助性符号、箭头、记号、圈画、重复线、随手写的文字或其他涂鸦元素,以增强速写本或随笔式视觉语言,但不可过于拥挤,不可破坏主体和留白气质。 画面内容不需要预先写清楚,由【{argument name="主体" default="主题/主体"}】自动推演并生成最适合的主体形象、动作、相关元素、符号或简化场景,整体保持统一的涂鸦速写风 and 夸张概括的表现方式,避免复杂写实背景 and 过度铺陈。 画面中需自然加入专属签名“voxcat”,作为画面的一部分,位置低调 but 清晰,可放在左下角、右下角或标题附近,风格需与整体版式统一,像作品署名或设计落款;签名字体精致、克制、高级,不可过大,不可破坏主体构图,不可显得突兀 or 廉价。

Example generated from “Graffiti Stairwell Sweet-Goth Fashion Portrait”
GPT Image 2en
Graffiti Stairwell Sweet-Goth Fashion Portrait

Create a high-fashion editorial full-body portrait of {argument name="character description" default="a young East Asian woman with long voluminous dark brown wavy hair, sweet-cool mature aura, pale skin, and soft but intense eye contact"} standing in an abandoned concrete stairwell or underpass covered with dense graffiti. She poses confidently with legs spread wide, one hand lifting a lock of hair near her ear and the other holding a glossy black chain shoulder bag low at her side. Outfit has exactly 7 visible fashion pieces/accessories: 1) fitted black V-neck short-sleeve knit top, 2) cream-white chiffon high-low irregular ruffle skirt with black polka dots and sheer layered hem, 3) white mid-calf ribbed socks, 4) chunky black platform derby shoes, 5) glossy black chain bag with long dangling chain strap, 6) silver hoop earrings, 7) silver cross pendant necklace. The location should feel gritty, urban, and claustrophobic, with tall window panels behind her covered in black, red, and blue tags, cracked gray concrete walls, peeling paint, and a waist-high graffiti barrier in the foreground. Use a low-angle fashion-photography composition, vertical 2:3 frame, centered subject, dramatic flash lighting, cool desaturated tones, sharp details, slight wide-angle distortion, glossy highlights on the shoes and bag, and realistic skin texture. Add subtle cyberpunk interface-like overlay text in small pale gray type around the edges, including fragments such as {argument name="overlay text" default="ERROR_404, UNKNOWN, DIGITAL_DECAY, DISCONNECT, FEEL NOTHING"}, but keep it faint and secondary. Overall mood: rebellious, sweet-goth, street-style lookbook, cinematic realism, no extra people, no watermark.

Example generated from “Grain Rain Festival Poster”
GPT Image 2en
Grain Rain Festival Poster

for{argument name="solar term" default="Grain Rain"} Design a poster for the solar term, using the following style:{argument name="style" default="Feng Zikai's painting style"} .

Example generated from “Great Wall Travel Collage”
GPT Image 2en
Great Wall Travel Collage

{ "type": "Travel photo collage", "subject": "Great Wall of China", "style": "High-resolution realistic travel photography, bright daylight clarity, vivid natural colors, editorial-quality travel brochure style.", "composition": { "format": "Square puzzle", "grid": { "columns": 3, "rows": 3, "count": 8 }, "borders": "All images are bordered with thin white borders.", "image_count": 8 }, "scenes": [ { "position": "Top left wide", "description": "From an aerial view, the Great Wall winds its way through lush green mountains, against a backdrop of blue sky and scattered white clouds." }, { "position": "upper right wide area", "description": "A view taken from eye level on the stone steps of the Great Wall, extending to a watchtower, flanked by brick crenellations, with a mountain ridge visible in the distance." }, { "position": "Middle left panel", "description": "The architectural details of the stone watchtower, photographed from below and looking up, contrast with the blue sky and white clouds." }, { "position": "Middle panel", "description": "A golden sunset scene at the Great Wall, with warm orange sunlight hanging low over the silhouettes of layered mountains, the Great Wall winding its way to the watchtowers." }, { "position": "Middle right panel", "description": "The landscape, captured with a telephoto lens, shows the Great Wall winding and twisting along steep, green mountain ridges, emphasizing its dragon-like shape." }, { "position": "Bottom left panel", "description": "Looking down over a long section of the Great Wall from a high vantage point, several tourists are walking along the central path towards the watchtower." }, { "position": "Middle and lower panel", "description": "From a human perspective, a small group of tourists dressed in summer casual wear walks along the Great Wall towards several watchtowers on a lush, green hillside, their backs to the camera." }, { "position": "Bottom right panel", "description": "A panoramic view of the mountains, framed on the right by a close-up of the Great Wall and green foliage above, showcasing the layered blue-green ridges extending into the distance." } ], "environment": { "season": "summer", "vegetation": "Dense green forests", "sky": "A clear blue sky with scattered cumulus clouds; only one photo shows a warm sunset scene.", "lighting": "Mostly bright afternoon sunlight, including one sunset photo taken at the golden hour." }, "details": { "architecture": "Ancient gray stone brick walls, crenellations, stepped walkways, and multiple watchtowers", "people": "Only two panels contain clearly visible tourists, while another panel contains tiny pedestrians in the distance.", "mood": "Magnificent, adventurous, and iconic World Heritage destinations" } }

Example generated from “Greek God Riding a Lion”
GPT Image 2en
Greek God Riding a Lion

To portray me as a{argument name="persona" default="Greek gods"} riding a{argument name="mount" default="lion"} The background is located in{argument name="setting" default="African savanna"} .

Example generated from “Greek God Riding a Lion”
GPT Image 2en
Greek God Riding a Lion

make me look like a {argument name="persona" default="greek god"} riding a {argument name="mount" default="lion"} in the {argument name="setting" default="plains of africa"}.

Example generated from “Green Tea Bottle Advertisement Poster”
GPT Image 2en
Green Tea Bottle Advertisement Poster

{ "type": "Bottled green tea beverage promotional poster", "product": { "type": "Transparent PET plastic bottle containing yellow-green tea", "label": "A white label with green lettering containing the product name.{argument name=\"product name\" default=\"Seifu Tea\"} The text includes the subtitle \"Green Tea Seifucha,\" the vertical text \"Used with domestically produced tea leaves,\" and \"Fragrant and mellow, with a pleasant aftertaste.\"" }, "background": "The bottle evokes a bright, fresh, and sunny outdoor atmosphere, with dynamic water splashes surrounding it and adorned with vibrant green tea leaves.", "layout": { "sections": [ { "title": "headline", "position": "top-left", "text": "{argument name=\"main headline\" default=\"New Release\"}", "style": "Large red text with gold underline and small green leaves" }, { "title": "catchphrase", "position": "mid-left", "text": "{argument name=\"catchphrase\" default=\"Feel refreshed every day.\"}", "style": "Dark green text" }, { "title": "features", "position": "lower-left", "count": 2, "labels": [ "Made with domestically produced tea leaves", "Rich aroma, refreshing aftertaste." ], "style": "White capsule-shaped banner with green leaf icon" }, { "title": "price_badge", "position": "top-right", "text": "Limited time offer!! Special price{argument name=\"price\" default=\"128 yen\"} (tax included)", "style": "Red round sticker with white and yellow text" }, { "title": "promo_banner", "position": "bottom-left", "text": "Limited-time special price!", "style": "A slanted red ribbon with yellow and white lettering" }, { "title": "footer", "position": "bottom-edge", "text": "{argument name=\"footer text\" default=\"Available at convenience stores and supermarkets nationwide.\"}", "style": "Plain green horizontal bar with a white shopping cart icon" } ] } }

Example generated from “Grimm's Fairy Tale Woodcut Poster”
GPT Image 2zh
Grimm's Fairy Tale Woodcut Poster

请将我上传的每一张照片分别制作成一张独立的高级设计海报,不多图拼接,每张照片单独输出。整体采用3:4竖版构图,上下两个区域高度严格1:1,各占画面50%,并确保该表达方式可适配人物、动物、建筑、静物、自然场景等不同主题,而不限于城市题材。 上半部分保留原始照片,保持主体身份、动作、空间关系、真实质感、自然光影和原有色彩氛围,仅进行轻微高级摄影调色,使其具有杂志摄影与艺术出版物的质感。为适配画幅,可自然扩展天空、地面或环境背景,但不得拉伸、扭切或改变主体。 下半部分提取照片中最具识别性的主体、轮廓、姿态与叙事关系,重构为童话版画式手绘图像。不要机械描摹细节,而是将主体压缩为一两个清楚的大体块,以钝拙剪影、略微夸张的比例和少量关键边缘,保留原始对象的身份、动作、功能与情绪。画面从原图内容中提炼出一个大面积低明度或高反差的结构场,作为包裹主体的容器、路径、框架或密度层;背景像故事发生的外壳一样从原图空间与意义中生长出来,形成遮挡、裁切、吞没与局部露出的结构叙事。整体采用平面叙事透视和绘本页面式层级,可使用俯视压缩、侧向移动、正面框架、路径引导、尺度跳跃或边缘裁切组织阅读。 配色从上方照片提取,并保持明确的三层关系:大面积暗结构色负责重量与边界,适量浅色或留白负责呼吸,小面积高饱和情绪色负责读图路线与故事信号。最重要的信息仅以少量鲜明色块集中在面部、姿态、路径、器物功能点、环境标识或叙事焦点上,并始终被深色结构或浅色负形压住,让画面鲜艳但不平均。色相可随主题情绪调整,但面积比例与明度秩序保持稳定。 线条只在功能、路径、边界、纹理和识别处出现,保持稀疏、手绘、略不准的细线。所有色块保持平面化处理,同时保留干刷、颗粒、飞白、纸纹、喷点和轻微套印错位,呈现丝网印刷与粉蜡笔共同完成的手工质感,避免写实光影、复杂体积、光滑矢量边缘、3D渲染和塑料质感。 整体构图简洁、低细节、高识别,暗场包裹亮色信号,兼具可爱叙事与厚重版画感。若画面包含文字,可将文字处理为小标识、物体面板或边缘注释,数量精简,服从图形结构;字形圆钝,粗细略不均,密度低,带有自然手写感,使其像画面的一部分而不是后期贴上去的说明。整体参考童话绘本、手工版画、编辑插画与艺术出版物气质,呈现统一、鲜明、可迁移的作者化视觉语言。

Example generated from “Gritty Córdoba Music Poster”
GPT Image 2en
Gritty Córdoba Music Poster

A dramatic, vertical poster-style mixed-media portrait presents a raw urban editorial aesthetic, reminiscent of concert or personal brand posters. At the center is a middle-aged man, half-body, wearing a black T-shirt, slightly turned to the side, one arm raised, index finger pointing to the top of the image. His face is deliberately obscured by a rectangular blurred block. The poster uses deep black and tan tones, accented with distressed cream and gold, incorporating heavy grunge textures, ink splatters, overlapping scratches, torn paper strokes, dust, and weathered printing effects. A large, soft gold circular halo is placed behind his head and upper body. In the background, a collage of Córdoba's urban landmarks is created: the cathedral facade on the right, and the river, bridges, and low skyline on the left, all elements perfectly integrated into the textured poster composition. An oversized, bold, compressed serif font is added at the top, containing the following text:{argument name="headline text" default="EDU PEREYRA"} The letter "EDU" is a large, distressed gray-white letter, while "PEREYRA" is below in gold. Five smaller text groups are added around the composition, using uppercase handwritten or compressed styles: "MÚSICA PASIÓN VERDAD" in the upper left, "DESDE ADENTRO HACIA AFUERA" in the upper right, "LO QUE SE SIENTE NO NECESITA EXPLICARSE" in the middle right, "AGRADECER SEGUIR CREAR" in the middle left, and "TIERRA DE HISTORIA, CORAZÓN DE GENTE" in the bottom center. A large, expressive brush-style font word is added across the lower foreground.{argument name="city name" default="cordoba"} The poster is off-white, slightly tilted, and finished with a gold underline. It features three small, symbolic graphic embellishments: a tiny crown icon near the top right, a small starburst decoration near the bottom center, and a handwritten signature mark in the bottom right corner. The shirt should include vintage-printed lettering and badge patterns. The lighting is somber and contrasting, creating a striking contrast between the subject and the layered collage background. Overall impression: a raw, passionate, musical, spiritual, and locally proud poster with a high-end distressed print design, possessing a strong visual impact and a cinematic, handcrafted feel.

Example generated from “Gritty Evangelion Poster”
GPT Image 2en
Gritty Evangelion Poster

A retro anime poster with dramatic tension, employing a hardcore sci-fi mecha visual style. In the foreground, three young pilots stand back-to-back, with a massive purple bio-mechanical robot standing behind them. The pilot in the center is a slender boy, wearing a dark navy blue and black pilot suit with white panels on his shoulders and a glowing red circular core on his chest, facing forward with a serious expression. To his left is a pale-faced girl with an ice-blue bob haircut, wearing a white futuristic bodysuit, slightly turned to the side. To his right is a girl with long, reddish-brown hair, her hair flowing to one side, wearing a bright red pilot suit, looking resolutely ahead. Behind the three, the massive mecha head occupies the center of the composition, symmetrically distributed, with a single horn, orange-glowing eyes, sharply defined armor, and massive shoulder structures extending upwards like black wings. The background is outer space, with two celestial bodies visible: a massive cratered moon directly behind the mecha head, and a smaller planet to the right. The poster's bottom depicts a dilapidated futuristic city, its buildings crumbling, littered with rubble, sparks, and debris. At the very center of the bottom are two tiny human silhouettes running forward through the ruins, surrounded by pink energy streams extending in arcs to the left and right. The color palette uses deep indigo, black, purple, rust red, and ashen gray, with a heavy film grain, aged ink texture, weathered paper wear, paint splatters, scratches, printing damage, and a rough silkscreen poster feel. The overall composition is a complete movie poster, with dense typography around the edges: a large vertical English title "NEON GENESIS EVANGELION" on the left, next to which is smaller red vertical text "HIRANO OF EVANGELION"; near the lower left corner is a red NERV logo and the word "NERV"; a boxed label in the lower left corner reads "TOKYO-3" and "JAPAN"; a red warning box in the upper right corner reads "ANGEL ATTACK" and Japanese characters below it; and multiple lines of vertical Japanese slogans along the left and right edges. Cinematic, emotional, apocalyptic, and highly detailed, it presents a perfect combination of iconic 1990s anime poster design and modern high-end illustration quality.

Example generated from “Gritty Evangelion Unit-01 Poster”
GPT Image 2en
Gritty Evangelion Unit-01 Poster

A hardcore, vertical anime mecha poster, featuring an aged silkscreen printing style, inspired by vintage military archives and Evangelion's key visual art. The main element is {argument name="mecha unit name" default="EVANGELION: UNIT-01"} A massive side profile close-up occupies two-thirds of the right side of the composition, facing left, jaws agape, emitting a wild roar. The head is a sharply defined biomechanical structure, featuring deep purple armor, olive green trim, a black metallic internal structure, a long horn extending diagonally upwards to the left, sharp teeth, and a narrow, glowing eye. The surface is covered in scratches, chips, and weathering marks, accented with heavy, comic-book style lines. The background is a deep navy blue blueprint, filled with eight clearly visible technical diagrams, white schematics, anatomical overlays, cross-sections, labels, measurement marks, and interface graphics. A streak of vibrant red paint sweeps diagonally across the upper center and left side of the image, with additional red dripping effects on the mech's mouth area. In the lower left corner, a small, boyish figure huddled on a gray equipment case: wearing a short-sleeved white shirt, dark trousers, and white sneakers, elbows resting on his knees, head bowed, staring at a glowing device in his hands, conveying a sense of loneliness and anxiety. Add layered poster layout and warning graphics to the border: a tattered yellow warning sign in the upper right corner with Japanese warning text and "CAUTION NERV ONLY"; a long strip on the left sidebar with "01", barcode-like squares, danger icons, and red and black labels; huge, distressed white Chinese characters stacked vertically above the mech's torso; below the Chinese characters are large, spaced-out red capital words.{argument name="main title" default="ESCAPE"} Below is a small black label that reads "PILOT:"{argument name="pilot name" default="IKARI, SHINJI"} The bottom right corner features the NERV logo; the footer includes a confidential document marker and a top-secret stamp. The blueprint area contains six clearly identifiable English technical labels: "TEST TYPE," "BIOLOGICAL CONSTRAINT," "AT FIELD," "MAGI SYSTEM," "INTERNAL," and "CLASSIFIED MATERIAL." Japanese archival text blocks are added as realistic graphic textures. The color palette is limited to deep indigo, black, deep red, purple, olive green, dirty beige, and off-white. High contrast, torn paper collage details, halftone textures, ink splatters, cracked paint, and worn printing edges. A cinematic, oppressive, chaotic, collector's edition poster design—ultra-refined, sharp, and textured, rejecting a clean, modern aesthetic.

Example generated from “Gritty Prison Mugshot Portrait”
GPT Image 2en
Gritty Prison Mugshot Portrait

{ "parameters": { "aspect_ratio": "2:3", "version": "6.0", "style_type": "Realistic photography, cinematic lighting, high detail, rough texture" }, signature: “XSydneyFan" in corner Cursive style "subject_description": { "demographics": "Beautiful young woman with fair skin.", "hair": "Long, dark black hair with a few strands falling across her forehead.", "details": "Small amounts of black soot and dirt on her face, neck, and hands." }, "attire": { "outerwear": "Bright orange prison uniform (overall workwear), slightly oversized. Worn and dirty, covered in black soot stains.", "details": "Large black '000' printed on the right side of her chest.", "under_layer": "Wearing a gray crew-neck T-shirt underneath.", "accessories": "Wearing a silver ring on her finger." }, "pose_and_expression": { "stance": "Standing in the stance of a prison photo. Looking directly at the camera.", "expression": "Expressionless, serious, indifferent, and seemingly bored.", "right_hand_action": "Casually raised, fingers touching the hair behind the right ear/neck area.", "left_hand_action": "Holding a black and white clapperboard in front of the chest." }, "props": { "slate_board_content": { "main_text": "🚫 ARRESTED 🚫 For illegally Money", "date": "12-28 25-26" } }, "environment": { "setting": "A rough, dilapidated room. The walls behind are peeling, cracked, and textured, resembling an abandoned concrete building or a run-down police station.", "background_elements": [ "A height chart on the wall.", "The word 'POLCIE' is written in the upper left corner of the wall." ] } }

Example generated from “Gritty Superhero Comic Page”
GPT Image 2en
Gritty Superhero Comic Page

{ "type": "Comic book page layout", "style": "Modern American comic book illustrations, dark and hardcore atmosphere, high-contrast lighting and dynamic composition.", "header": { "location_box": "{argument name=\"location\" default=\"Hell's Kitchen, New York\"}", "title": "{argument name=\"comic title\" default=\"Daredevil: The Fearless One!\"}" }, "character": "{argument name=\"hero description\" default=\"A superhero dressed in a red demon suit, wearing horns, and with eyes that flash red light.\"}", "layout": { "panel_count": 6, "panels": [ { "position": "Top left", "scene": "The hero stood on the rooftop, overlooking the city skyline at sunset.", "text_boxes": 3, "text": [ "Some nights, the city feels like a heartbeat.", "Swift. Unstoppable. Vibrant.", "And some nights... it feels like a warning." ] }, { "position": "Top right", "scene": "A close-up of the hero's masked face, hidden in the shadows.", "text_boxes": 1, "text": [ "Tonight, both are true." ] }, { "position": "center right", "scene": "Four thugs stood in the dark, damp alley.", "graffiti": "{argument name=\"enemy faction\" default=\"Hand\"}", "text_boxes": 2, "text": [ "The Hand is at it again.", "Silent and still. Utterly patient. As if they controlled the shadows." ] }, { "position": "Center left, breaking the border", "scene": "The hero leaps forward dynamically, stretching out his hand to grasp a short stick with steel wire, against a backdrop of concentric white radar ripples.", "text_boxes": 2, "speech_bubbles": 1, "text": [ "They don't have control.", "As long as I'm still here, they can forget about it.", "I can hear you. All of you." ] }, { "position": "Bottom left", "scene": "The hero leaps toward the silhouettes of a group of sword-wielding ninjas against a crimson background.", "text_boxes": 2, "text": [ "I don't wear the mask to be a hero.", "I wear it to ensure that innocent people can return home safely." ] }, { "position": "Bottom right", "scene": "Close-up of the hero's face, with the corners of his mouth slightly upturned.", "speech_bubbles": 1, "text": [ "Let's see who survives tonight." ] } ] }, "footer": "{argument name=\"ending text\" default=\"To be continued!\"}" }

Example generated from “Gritty Tattooed Woman Mugshot”
GPT Image 2en
Gritty Tattooed Woman Mugshot

A realistic, slightly grainy, and dimly lit police photo features a young woman with messy long black hair, prominent cheekbones, and full lips. She has a small tattoo near her right eye, and her neck, chest, hands, and arms are covered in intricate mandala-style tattoos. She wears a simple black sleeveless top and holds a white rectangular ID badge with blurred text; her nails are neatly trimmed. The background is an ordinary white cement brick wall, with a height measuring scale on the right displaying numbers like 150, 160, and 170 in black template font. The overall aesthetic is rough and realistic, resembling a genuine police photo.

Example generated from “GTA 6 CJ and Lucia crossover”
GPT Image 2en
GTA 6 CJ and Lucia crossover

Generate a{argument name="game" default="GTA 6"} Game screenshots, including{argument name="character 1" default="cj"} and{argument name="character 2" default="lucia"} Together

Example generated from “GTA Anyang Concept Screenshot”
GPT Image 2en
GTA Anyang Concept Screenshot

Generate a game screenshot with the following style:{argument name="style" default="Grand Theft Auto: Vice City"} But the location is set in{argument name="location" default="Anyang, Henan"} The perspective is an overview from north to south.{argument name="landmark" default="Anyang Wenfeng Pagoda"} The visual style should have a game-like feel while remaining as realistic as possible. The time is daytime, there are pedestrians on the road, and the protagonist is standing on a car in the middle of the road, looking towards the Wenfeng Pagoda.

Example generated from “GTA Storyboard Prompt”
GPT Image 2en
GTA Storyboard Prompt

Create a 3x3 GTA 6 gameplay storyboard image showing Micheal Playing football

Example generated from “GTA V Style Crossover Cover Art”
GPT Image 2en
GTA V Style Crossover Cover Art

{ "type": "Video game cover art collage", "style": "GTA V cover art style, cel illustration, thick black panel border.", "centerpiece": { "character": "{argument name=\"main character\" default=\"Thomas Shelby in Peaky Blinders\"} He was wearing a dark suit and a white shirt, smoking a cigarette, and sporting a low-cut hairstyle.", "logo": "{argument name=\"game title\" default=\"grand theft auto V\"} The logo features a green V and a \"FIVE\" banner.", "subtitle": "{argument name=\"bottom text\" default=\"THOMAS SHELBY BIRMINGHAM. 1919.\"}" }, "layout": { "panel_count": 8, "panels": [ { "position": "Top left", "description": "There is on the hillside{argument name=\"location sign 1\" default=\"VINEWOOD\"} Signs, radio towers, palm trees" }, { "position": "Center upper left", "description": "The street sign reads{argument name=\"location sign 2\" default=\"SMALL HEATH BIRMINGHAM S 41\"} townhouse" }, { "position": "center left", "description": "A pistol, 3 bullets, and the map says 'BY ORDER OF THE PEAKY BLINDERS'." }, { "position": "Bottom left", "description": "Retro 1920s black car, illuminated headlights, 'GTA V' license plate." }, { "position": "Top right", "description": "City skyline silhouette, helicopter" }, { "position": "center right", "description": "Three men wearing baseball caps and suits walk through a smoky industrial environment." }, { "position": "Bottom right and top", "description": "A large country estate with black horses on the lawn." }, { "position": "bottom right", "description": "A man wearing a baseball cap gazes at the industrial skyline and the yellow Rockstar Games logo." } ] } }

Example generated from “GTA-Style Beach Club Gameplay Screenshot”
GPT Image 2en
GTA-Style Beach Club Gameplay Screenshot

Create a hyper-realistic screenshot of an open-world crime video game, inspired by a modern Miami beach club scene, set in a bright afternoon sun with a clear blue sky. Use a third-person perspective composition, with a seated figure in the foreground.{argument name="character description" default="A young man with short, dark hair and fair skin was wearing a plain black T-shirt and printed swim trunks."} He sits casually on the light-colored sand, his body slightly turned to one side, as if the player's perspective has stopped beside him. Positioning him slightly off-center on the left side of the screen, occupying a large proportion, his posture is natural and relaxed. Behind him, a high-end beach club is depicted, with three white pavilions with flowing curtains clearly visible on the beach, planted with several tall palm trees. To the left is turquoise water, and to the right is a row of Art Deco hotels with soft-toned exteriors and neon decorations. The beach is filled with 12 people in swimwear in the background: some are standing and chatting, some are walking along the shore, and two are sitting at a table on the right enjoying a meal. The scene includes white casual furniture and parasols, creating a sophisticated social party atmosphere. A realistic game HUD interface is added: in the lower left corner is a sign {argument name="map label" default="GPS route"} The small square map displays weapon and control icons in the bottom right corner and the amount in the top right corner.{argument name="money amount" default="$45,670"} The money counter. The overall look is similar to screenshots from the next-gen game *Grand Theft Auto VI*, with a cinematic feel and a distinct in-game texture. It boasts rich detail, realistic shadows, vibrant color gradations, and a lively coastal atmosphere, while also possessing {argument name="city setting" default="Vice City"} The subtle irony of luxurious beaches.

Example generated from “GTA-Style Dialogue Screenshot”
GPT Image 2en
GTA-Style Dialogue Screenshot

{ "type": "Video game screenshots", "style": "{argument name=\"art style\" default=\"Grand Theft Auto VI: Aesthetics, Realistic 3D Graphics\"}", "setting": "A balcony overlooking the coastal city at sunset, with palm trees, skyscrapers, and warm lights.", "characters": [ { "role": "NPC", "description": "{argument name=\"npc description\" default=\"Omni-Man is a muscular, middle-aged man with a beard, graying sideburns, and wearing a red and white superhero suit.\"}", "position": "Center left, facing the camera" }, { "role": "Players", "description": "A man wearing a dark baseball cap backwards and a light gray T-shirt", "position": "Right foreground, facing away from the camera" } ], "ui_elements": { "type": "Dialogue Menu", "position": "Bottom Center", "speaker_name": "{argument name=\"speaker name\" default=\"OMNI-MAN\"}", "dialogue_text": "{argument name=\"npc dialogue\" default=\"This planet is not your responsibility to protect. The rule of the Viltrum is inevitable.\"}", "choices_count": 3, "choices": [ "1. {argument name=\"choice 1\" default=\"You can forget about taking over anything.\"}", "2. What exactly do you want from me?", "3. I don't care about your politics." ], "highlight": "Option 1 has a semi-transparent purple background bar." } }

Example generated from “GTA-Style Dialogue Screenshot”
GPT Image 2en
GTA-Style Dialogue Screenshot

{ "type": "video game screenshot", "style": "{argument name=\"art style\" default=\"Grand Theft Auto VI aesthetic, realistic 3D graphics\"}", "setting": "balcony overlooking a coastal city at sunset, palm trees, skyscrapers, warm lighting", "characters": [ { "role": "NPC", "description": "{argument name=\"npc description\" default=\"Omni-Man, muscular older man with a mustache and grey temples, wearing a red and white superhero suit\"}", "position": "center-left, facing camera" }, { "role": "Player", "description": "man wearing a backwards dark baseball cap and light grey t-shirt", "position": "right foreground, back to camera" } ], "ui_elements": { "type": "dialogue menu", "position": "bottom center", "speaker_name": "{argument name=\"speaker name\" default=\"OMNI-MAN\"}", "dialogue_text": "{argument name=\"npc dialogue\" default=\"This planet isn't yours to protect. Viltrumite rule is inevitable.\"}", "choices_count": 3, "choices": [ "1. {argument name=\"choice 1\" default=\"You're not taking over anything.\"}", "2. What do you want from me?", "3. I don't care about your politics." ], "highlight": "Choice 1 has a translucent purple background bar" } }

Example generated from “Guadalajara 复古电影旅行海报”
GPT Image 2en
Guadalajara 复古电影旅行海报

@Crea una imagen { "style": "Cinematic Vintage Movie Poster — Guadalajara, Mexico", "target_tool": "DALL-E 3 (ChatGPT)", "prompt": "Generate a vertical portrait-format movie poster image, taller than wide in a 2:3 aspect ratio. The image is a cinematic vintage travel movie poster for Guadalajara, Mexico, rendered with the visual texture of an aged large-format film poster: heavy 35mm film grain throughout especially in the shadow areas, slightly faded and warm-shifted color tones as if printed on aged matte paper stock, a subtle halftone dot pattern visible in the midtones, and a very slight ink bleed at high-contrast edges giving it an authentic vintage printed poster feel. Foreground: a single dark silhouette of a lone mariachi musician standing still at the center-bottom of the frame, rendered as a pure clean dark silhouette with no facial features visible — traditional wide-brim charro sombrero, fitted traje de charro suit outline, holding a guitarrón — casting a long warm shadow across the honey-colored cantera stone paving of Plaza de la Liberación below, with colorful papel picado banners in red, orange, green and yellow cut tissue paper strung in loose diagonal lines overhead from building to building, swaying slightly, framing the upper composition, no people other than the single silhouetted figure, no vehicles, no modern objects. Midground: the grand honey-amber cantera stone neoclassical facade of the Teatro Degollado rising directly behind the silhouette, its ornate columned portico and triangular pediment warmly lit by the low golden-hour sun hitting from the left, long dramatic shadows stretching across the stone paving, the warm amber volcanic stone glowing intensely in the golden light. Background: the twin neo-Gothic spires of the Catedral Metropolitana de Guadalajara rising tall into the upper frame against a vast deep cerulean blue sky transitioning to burnt amber and deep orange near the horizon, a single scattered cloud catching violet and gold light from below, the cathedral facade in warm honey stone matching the Teatro Degollado's palette. Color grade: saturated warm amber and golden honey tones dominating the stone architecture, deep cobalt blue in the upper sky, rich burnt orange near the horizon, faded warm sepia in the shadow areas consistent with a vintage printed poster. At the very top of the image, centered above the spires, render the single word GUADALAJARA in bold condensed uppercase display serif letters in warm cream-gold with a faint dark drop shadow, leaving clear sky negative space for the title. No modern buildings, no cars, no utility wires, no people other than the single dark silhouette visible anywhere in the scene.", "target": "🎯 Target: DALL-E 3 (ChatGPT) — 💡 Foreground/midground/background separation places Teatro Degollado and the Cathedral in distinct spatial layers, the mariachi silhouette is specified as a featureless outline to eliminate aberration risk, and vintage print texture is described visually rather than as a style label." }

Example generated from “Guangdong Super League Invitation Poster”
GPT Image 2zh
Guangdong Super League Invitation Poster

广东省城市足球超级联赛(粤超)邀请函海报设计,比例 9:16。S 型流动构图,以发光足球和动态能量流贯穿画面,沿动线融合广州塔、深圳平安金融中心、珠海渔女雕像、岭南建筑、佛山武术剪影、中山文化符号、潮汕英歌舞与清远山水。现代国潮高级海报风格,中国红主视觉,青蓝辅助,金色高光,带完整中文排版与电影级光影。

Example generated from “Guangzhou City Promotional Poster”
GPT Image 2en
Guangzhou City Promotional Poster

A picture that is full of festive atmosphere for the Spring Festival while maintaining an elegant style.{argument name="year" default="2026"} The city's promotional poster for the year features a double exposure and an S-shaped composition. In the lower right corner against a pure white textured background, a small figure in traditional Chinese clothing waves a long red ribbon. The ribbon dances in the air, showcasing the smooth texture of silk, and magically transforms into magnificent mountains and rivers as it floats upwards to the left. Overlaid within this "river" is a hand-drawn image.{argument name="city name" default="Guangzhou"} A city map, featuring mountains, ocean, and rivers. Its Chinese-style design is both striking and magnificent.{argument name="landmarks" default="Guangzhou Tower, Zhujiang New Town architectural complex, Pearl River, ancient buildings, cruise ships, Baiyun Mountain"} The scene is shrouded in mist, creating an ethereal atmosphere. The colors and details are rich, while the ample use of white space lends it a refined feel. The lower left corner displays "SPRING 2026" and a vertical banner, symbolizing "A Millennium Commercial Capital, Charming Guangzhou." The typography is beautiful and clear, with a 9:16 aspect ratio.

Example generated from “Guangzhou City Promotional Poster”
GPT Image 2zh
Guangzhou City Promotional Poster

一张充满{argument name="氛围" default="新春喜庆"}氛围但不失高雅格调的 {argument name="年份" default="2026"} 城市宣传海报。双重曝光,构图延续了S型的流动感;在纯白的纹理背景右下角,一个身穿中国传统服饰的微缩人物正在挥舞着一条长长的红色丝绸舞带,这条红绸在空中舞动,不仅展现出丝绸的柔顺质感,更在向左上方飘动的过程中,奇幻地变形成了一条壮丽的山脉河流。在这条“河流”中,叠加了一个有山有海河的广州城市手绘图,国潮,景色尽在眼底,壮阔雄伟,令人震撼。广州的地标建筑(广州塔,珠江新城建筑群,珠江, 广州城里古建筑,游轮,白云山)。云雾环绕,仙气缥缈,色彩丰富,结构复杂,细节丰富,但因为大面积的留白,画面依然显得清新脱俗,左下角排版着“SPRING 2026”和竖排的宣传语,整体寓意“{argument name="宣传语" default="千年商都,魅力广州"}”。文字排版优美,大方,字迹清晰完整,尺寸9:16。

Example generated from “Guangzhou Paper-Cut City Poster”
GPT Image 2zh
Guangzhou Paper-Cut City Poster

以珠江新城现代都市景观为灵感的剪纸艺术,通过精巧的镂空手法在一整幅纸上,立体刻画广州塔、东西双塔等地标建筑与繁华城景。 所有建筑与元素均以流畅的线条与结构相连,无孤立部分,构成一幅完整的都市画卷。 画面采用金属箔或光泽纸材质,表面带有细腻的明暗光泽,在光照下呈现柔和的高光与阴影,仿佛被城市灯光轻轻照亮。 背景以虚化的珠江新城天际线为衬,点缀隐约可见的花城广场与树木轮廓,整体透出现代浪漫的氛围。 作品中巧妙融入轻盈的蒲公英绒毛或星光般的动态光点,象征梦想与活力在这座新城中飘散飞扬。整体呈现8K超高清视觉,细节丰富,真实而富有艺术感染力。

Example generated from “Gupta Palace Environment Reference Sheet”
GPT Image 2en
Gupta Palace Environment Reference Sheet

Goal: Create a production-grade environment reference sheet for a {argument name="historical setting" default="Royal Gupta Empire palace complex, 5th century CE"}, designed as a cinematic storyboard and worldbuilding asset for GPT-image generation. Canvas: Wide 16:9 reference-board layout on a dark charcoal background, dense but clean, with thin white divider lines, uppercase white technical labels, small annotation callouts, and a realistic architectural concept-art style. The overall title across the top reads: “PRODUCTION GRADE ENVIRONMENT REFERENCE - | ROYAL GUPTA EMPIRE GUPTA EMPIRE PALACE COMPLEX”, with “5TH CENTURY CE” aligned at the top right. Main composition: Place a large central aerial three-quarter view of a grand Gupta-era palace complex occupying the middle of the sheet. The complex is made of red sandstone and cream stone, with symmetrical courtyards, high enclosing walls, arched gateways, colonnaded halls, carved balconies, flat terraces, small domed pavilions, lotus pools, geometric garden paths, fountains, mango trees, flowering shrubs, and warm golden-hour sunlight. Add fine white callout lines labeling architectural and landscape details such as carved columns, throne platform, mango gardens, marble seating, and sacred lotus ponds. Left column sections: Include exactly 3 sections. Section 1 is “PALACE ENTRANCE”, showing a frontal red sandstone gate with two tower-like chhatri pavilions, a central pointed arch, two stone guardian statues, red-and-gold hanging banners, and relief carvings beneath it. Label exactly 3 entrance detail thumbnails below it: “Stone guardians”, “Banners”, and “Relief carvings”. Section 2 is “ROYAL GARDENS”, showing a formal garden with rectangular water channels, fountains, clipped lawns, trees, peacocks, and palace colonnades in the background. Section 3 is “MATERIAL REFERENCE”, showing exactly 8 material swatches labeled: Red sandstone, Cream sandstone, Polished granite, Marble inlays, Carved teak wood, Bronze fittings, Copper elements, and Painted plaster mural pigments and gold leaf. Top and right sections: Include exactly 5 smaller architectural reference panels around the central image. Panel 1: “ROYAL AUDIENCE HALL”, an interior hall with carved stone columns, warm shadows, elevated audience platform, carved columns, and throne platform labels. Panel 2: “QUEEN’S COURTYARD”, a garden courtyard with colonnaded palace walls, flower beds, central fountain, marble paths, and lotus ponds. Panel 3: “MATERIAL REFERENCE”, another grid of exactly 8 swatches with the same labels: Red sandstone, Cream sandstone, Polished granite, Marble inlays, Carved teak wood, Bronze fittings, Copper elements, and Painted plaster mural pigments and gold leaf. Panel 4: “PALACE BALCONY SYSTEM”, showing carved projecting balconies with stone railings and ornate supports. Panel 5: “SACRED TEMPLE ZONE”, showing small Gupta-style shrines with domes, red stone, trees, and a courtyard. Bottom row sections: Include exactly 3 sections. Section 1: “LIGHTING REFERENCE”, with exactly 4 cinematic lighting thumbnails labeled Dawn, Midday, Sunset, and Moonlit Night. Dawn should be pale and misty, midday bright and clear, sunset orange and dramatic, moonlit night blue with palace silhouettes. Section 2: “COLOR PALETTE”, with exactly 8 color chips labeled Sandstone Red, Warm Ivory, Lotus Pink, Deep Saffron, Bronze Brown, Peacock Blue, Banyan Green, and Royal Crimson. Section 3: “CULTURAL DETAIL”, with exactly 9 illustrated cultural elements labeled Royal elephants, Attendants, Sacred cows, Oil lamps, Incense burners, Flower garlands, Palm-leaf manuscripts, Bronze vessels, and Silk banners. Atmosphere note: Add a small paragraph near the sacred temple panel describing warm Indian climate lighting, visible sunbeams in shaded courtyards, lotus pools, shisham/rosewood and neem trees, monsoon-season atmosphere, incense smoke, buffalo or sacred animals, rich bronze and gold ornamentation, birds, and subtle reflections. Visual style: Ultra-detailed realistic environment design sheet, authentic ancient Indian Gupta architecture, red sandstone carvings, cream sandstone highlights, polished stone, carved teak, bronze and copper details, painted plaster with gold leaf, volumetric god rays, warm golden-hour ambience, crisp labels, cinematic consistency across camera angles. Constraints: Keep the sheet information-dense but readable, with exactly the counted panels, material swatches, lighting thumbnails, color chips, cultural detail objects, and entrance detail thumbnails listed above. Avoid modern buildings, modern people, plastic materials, neon colors, sci-fi elements, watermarking, or random extra labels. Use the custom palette emphasis of {argument name="dominant material color" default="red sandstone"}, {argument name="secondary material color" default="warm ivory cream sandstone"}, {argument name="lighting mood" default="golden-hour volumetric sunlight"}, and {argument name="main environment feature" default="symmetrical palace courtyards with lotus pools"}.

Example generated from “Haaland Futuristic Football Poster”
GPT Image 2en
Haaland Futuristic Football Poster

Goal: Create a vertical modern football superstar collectible poster for {argument name="player name" default="埃尔林·哈兰德"}, showing an ultra-realistic striker charging toward the camera in a dramatic stadium action scene, with a futuristic sports-data archive interface around him. Canvas: Tall portrait poster, about 9:16 ratio. Dark blue, icy steel, and gold color palette. High contrast cinematic lighting, rain mist, flying turf, dust, sparks, motion blur, and a packed stadium roof in the background. Main subject: A powerful blond male footballer in a sky-blue jersey, white shorts, and pale blue socks, sprinting and kicking forward from the center of the poster. Use an extreme low-angle perspective: his boot and the football are closest to the viewer, large and motion-blurred in the foreground, while his torso fills the center. The face should be covered by a centered square blurred censor block, while hair, body, uniform, and pose remain visible. Emphasize muscular arms, explosive forward momentum, and a “finishing machine” striker vibe. Top typography: Huge distressed white Chinese headline text reading {argument name="headline text" default="埃尔林·哈兰德"}. Beneath it, a smaller gold subtitle with separators reading {argument name="subtitle text" default="北欧巨炮 · 终结机器 · 禁区统治者"}. Add thin gold horizontal accent lines on both sides. Data interface layout: Place exactly 8 transparent HUD-style stat cards around the player, with thin gold and pale-blue technical borders, tiny charts, icons, microtext, and graphs. Left column has exactly 4 cards from top to bottom: 1) 「青训起点」 with a small player path diagram, 2) 「萨尔茨堡爆发」 with a kicking silhouette and growth chart, 3) 「多特锋芒」 with a running player icon and graph, 4) 「曼城时期」 with a stadium icon and bar chart. Right column has exactly 4 cards from top to bottom: 1) 「进球效率」 with a target icon and bar chart, 2) 「禁区统治力」 with a goal icon and rising line graph, 3) 「冲刺与力量」 with a sprinting icon and bar chart, 4) 「纪录刷新者」 with a trophy icon and data chart. Bottom timeline: Add a thin career timeline stretching across the lower poster with exactly 6 small footballer silhouette milestones and tiny year labels, connected by gold dots and a fine line. Include faint blue equalizer-style bars behind the timeline. Bottom title plate: At the very bottom, add a dark futuristic nameplate with gold trim, chevron arrows on both sides, and large gold Chinese text reading {argument name="bottom slogan" default="新生代巨星破框档案"}. Visual style: Hyper-realistic sports photography mixed with sci-fi infographic design, collectible World Cup poster energy, volumetric stadium light beams, sharp typography, gritty texture, layered depth, premium editorial composition. Constraints: Keep all text legible and in Chinese where specified. Use exactly 8 side stat cards and exactly 6 bottom timeline milestones. Do not add logos, club badges, brand marks, watermarks, or extra people. The central player must dominate the composition, with the ball breaking toward the viewer in the lower right foreground.

Example generated from “Haitian Football Poster Panorama”
GPT Image 2en
Haitian Football Poster Panorama

Créer une illustration panoramique raffinée au format paysage pour une affiche haïtienne de football intitulée **« {argument name="nom de l'affiche" default="GRENADYE 2026"} »**, intégrant **{argument name="villes" default="Jacmel, Cap-Haïtien et Port-au-Prince"}** dans une seule scène harmonieuse, avec un trophée de la Coupe du monde stylisé, pleinement intégré comme point d’ancrage central. Représenter Haïti comme une scène nationale calme, élégante, très stylisée, dans un style {argument name="style artistique" default="affiche pastel en collage de papier"}. Utiliser une composition horizontale ample, avec trois zones urbaines doucement connectées par la mer des Caraïbes, les montagnes, le ciel et des plans colorés découpés en papier. Zone gauche : Jacmel, avec architecture gingerbread historique, façades coloniales pastel, balcons en bois ornés, détails décoratifs, palmiers, culture artistique du bord de mer, accents inspirés des masques de carnaval, petits artistes, bateaux et rues côtières chaleureuses. Zone centrale : Port-au-Prince, avec quartiers en pente superposés, maisons géométriques colorées, boulevards bordés de palmiers, eau du port, arrière-plan montagneux subtil, architecture civique, petits personnages de marché, motifs d’art haïtien et une place ouverte qui ancre le trophée. Zone droite : Cap-Haïtien, avec la Citadelle Laferrière comme silhouette de forteresse sur une crête verte lointaine, le palais Sans-Souci suggéré par des arches en pierre claire, architecture coloniale côtière, baie turquoise, bateaux de pêche, palmiers et petits personnages célébrant le football. Placer au centre un trophée de la Coupe du monde reconnaissable mais stylisé, rendu comme une sculpture monumentale en collage de papier doré mat, avec formes simplifiées du globe, courbes abstraites inspirées du football, bords légèrement surélevés, contours embossés et ombres délicates. Ajouter les chiffres « 2026 » près de la base. Ne pas utiliser de logos officiels FIFA ni de logos d’équipes. Ajouter des détails subtils de célébration du football haïtien : petits personnages avec accents rouges et bleus, petits drapeaux haïtiens, ballons abstraits, rubans graphiques bleu et rouge haïtiens atténués, et une énergie festive maîtrisée au premier plan. Palette : bleu ciel doux, bleu-gris brumeux, cobalt pâle, vert sauge atténué, menthe poudrée, crème chaude, beige clair, gris pierre pâle, corail poussiéreux, pêche douce, jaune atténué, blanc cassé, turquoise fané, terracotta ensoleillée, accents bleu et rouge haïtiens, petits détails marine et charbon, plus or mat raffiné pour le trophée. L’image doit sembler faite à la main, comme du papier coloré soigneusement assemblé et de la gouache sur carton d’affiche, avec grain subtil du papier, texture imprimée mate, bords relevés, embossage délicat, ombres de papier découpé, légère rugosité de surface, silhouettes nettes, aplats géométriques propres et beaucoup d’espace négatif. Typographie en haut à gauche : « GRENADYE 2026 » en police sans-serif géométrique majuscule

Example generated from “Hand Cream Tube with Botanical Sprig”
GPT Image 2en
Hand Cream Tube with Botanical Sprig

A small matte sage-green aluminium hand cream tube lying on a clean off-white linen surface, with one fresh eucalyptus sprig laid diagonally beside it. Soft diffuse daylight from above, gentle shadows. Square 1:1 minimal natural cosmetics product photography. No brand text on the tube, no logo, no watermark. Photorealistic metal and fabric textures, magazine beauty editorial styling.

Example generated from “Hand-Drawn Annotated Food Diary Style”
GPT Image 2en
Hand-Drawn Annotated Food Diary Style

Generate a{argument name="food" default="Steak and dessert"} The photos are in the style of{argument name="style" default="English Steakhouse"} The photos should have a mobile phone shooting quality, suitable for posting on Instagram. Avoid including people in the frame. Next, observe the elements in the photo and add meaningful hand-drawn annotations to each element. [Drawing Rules] - Use fine, hand-drawn lines similar to a white brush - Present a rough, slightly uneven single-stroke style - Add lines that outline the shape of objects - Use arrows or dotted lines to guide the visual focus [Text Rules] - Handwritten English text - Short, self-talk-like comments - Set the tone to "diary-like, single-word, emotional connection" [Comment Generation Rules] - Drinks -> Taste, temperature, mood (e.g., refreshing, mild sweetness) - Food -> Texture, deliciousness (e.g., juicy, excellent) - Space -> Atmosphere (e.g., relaxing, good time) - Overall -> Single-word summary (e.g., so happy~) [Decoration] - Add steam, glitter, hearts, small emojis, etc. in moderation - Don't over-decorate, keep "white space" [Finished Product Style] - Instagram Stories style, rough magazine note style - Stylish and relaxed atmosphere

Example generated from “Hand-drawn Breakfast Journal Aesthetic Poster”
GPT Image 2zh
Hand-drawn Breakfast Journal Aesthetic Poster

围绕任意主题对象呈现轻松的手写观察图谱:大面积洁白纸面作为主要空间,主题内容被拆成若干小块实物状图形、剖面小图、串联小件、短条重复物和局部特写,分散排在纸面中上部与中段,彼此不做严整表格,而是靠近似横向阅读的松散行距、错位留白和手写短语串联,形成像味觉、触感、声音或动作被随手记录下来的亲密节奏。小图形使用主题派生的材料和颜色,保持小尺幅、圆钝外轮廓、轻微透视和手绘上色痕迹,局部保留颗粒、焦边、碎屑、纹理或剖面细节;不要让它们变成统一图标,应像绘本食物插图和手账贴纸之间的实物笔记。文字是画面骨架:使用细黑色手写假名感或童稚手写感线条,字距松、基线轻微跳动,短词围绕图形左右穿插,部分字串贴近图形边缘,部分独立漂浮在空白中,底部可放一行较小署名式说明。色彩由主题自身推导,白纸占最大面积,黑色细字承担信息,主体色保持温暖、清洁、略高明度;少量高饱和暖色或深色只用于图形的焦点、阴影 and 纹理,点状绿色、褐色或其他主题辅色作为极小面积节奏。整体保持扫描纸张的轻微柔化和自然压缩感,边缘有手绘不齐与颜料吸收,不加厚重阴影、装饰边框或现代排版感;重点是让图形和拟声手写共同制造“边看边读”的清爽童趣信息页。 主题:{argument name="主题" default="早安+问候+GOOD MORNING+城市+金句+天气+2026-08-21"}

Example generated from “Hand-drawn Chengdu Food Map”
GPT Image 2en
Hand-drawn Chengdu Food Map

A{argument name="city" default="Chengdu"} A hand-drawn city food map themed around [the theme]. The image is a simplified hand-drawn city map based on a bird's-eye view, with major roads and landmarks marked in a cute, asymmetrical hand-drawn style. Twelve exquisite small hand-drawn food illustrations are scattered throughout the map.{argument name="landmark" default="Chunxi Road Skewers"} (Steaming hot skewers of various ingredients), Kuanzhai Alley's "Three Cannons" (three glutinous rice balls flying towards a copper plate), Jianshe Road's egg pancakes (golden and crispy, being flipped), Yulin Road hot pot (a nine-compartment broth bubbling), etc. Each illustration occupies about 5% of the map area, with the shop name and recommendation in handwritten script next to it: "A place where there's still a queue at 2 AM." The map's edge is decorated with a border made of hand-drawn vines and chili peppers. A hand-drawn compass and legend are located in the lower right corner. The title in the upper left corner is {argument name="title" default="Chengdu Foodie's Guide"} "It features a rounded and cute artistic hand-drawn font, decorated with chili peppers. The overall style is a hand-drawn texture that blends watercolor and colored pencils, with warm colors (chili red, ginger yellow, and emerald green) as the main colors, in a 1:1 ratio."

Example generated from “Hand-drawn Hermes Agent Poster”
GPT Image 2en
Hand-drawn Hermes Agent Poster

Generate a hand-drawn style promotional poster for introduction.{argument name="subject" default="hermes agent"}

Example generated from “Hand-drawn Infographic Card Prompt”
GPT Image 2en
Hand-drawn Infographic Card Prompt

Create a hand-drawn style infographic card in a 9:16 portrait aspect ratio. The card should have a clear theme, a beige or off-white background with a paper texture, and an overall design that presents a simple and friendly hand-drawn aesthetic. The top of the card uses large, alternating red and black cursive fonts to highlight the title and attract visual attention. The text content is all in Chinese cursive script, and the overall layout is divided into 2 to 4 clear sections, each using a short, concise Chinese phrase to express the core message. The font maintains the smooth rhythm of cursive script, making it both easy to read and artistic. The card is embellished with simple and fun hand-drawn illustrations or icons, such as figures or symbols, to enhance visual appeal and evoke thought and resonance in the reader. The overall layout emphasizes visual balance, leaving sufficient white space to ensure the image is simple, clear, and easy to read and understand. The theme is:{argument name="theme content" default="Building an IP is a long-term, compounding process. If you consistently set up a stall every day and keep doing it, you will definitely see results, because 99% of people can't stick to it."} "

Example generated from “Hand-drawn Infographic Card Prompt”
GPT Image 2en
Hand-drawn Infographic Card Prompt

Create a 9:16 portrait-oriented hand-drawn infographic card. The card should have a clear theme, a beige or off-white paper textured background, and an overall design that presents a simple and friendly hand-drawn aesthetic. The title should be highlighted at the top of the card using a striking red and black contrasting calligraphy font to attract visual attention. All text should be in Chinese cursive script, with the overall layout divided into 2 to 4 clear sections, each expressing the core message in a concise Chinese phrase. The font should maintain the smooth rhythm of cursive script, ensuring both readability and artistic appeal. The card can be embellished with simple and fun hand-drawn illustrations or icons (such as figures or symbolic symbols) to enhance visual appeal and evoke thought and resonance in the reader. Pay attention to the visual balance of the overall layout, leaving sufficient white space to ensure the image is clean, clear, and easy to read and understand. The theme is:{argument name="theme" default="Building an IP is a long-term, compounding process; if you persist in setting up your stall every day and keep doing it, you will definitely see results, because 99% of people cannot persist."} "