GPT Image 2 Prompts

Luxury fashion advertisement, cinematic editorial portrait of a tall elegant woman wearing a dramatic two-tone belted trench coat in burnt orange and deep black, layered over a cream ribbed turtleneck sweater, one hand in the pocket, shown from mid-thigh up, centered and facing forward with windswept {argument name="hair color" default="copper red"} hair loosely tied back, face intentionally obscured by shadow or stylized cropping for a mysterious high-fashion look. The scene is framed by torn pieces of orange and dark fabric around all four edges like ripped textile layers opening onto the subject. Behind her, a stormy sky with towering glowing clouds at sunset, rich amber and bronze light, moody atmosphere, subtle flying sparks and smoky haze near the bottom. Add a luxury brand campaign aesthetic, ultra-detailed fabric texture, visible stitching, polished belt hardware, strong contrast, warm orange color grading, photorealistic lighting, premium magazine ad composition. Place a large white luxury-style horse-and-carriage emblem above bold centered serif text reading {argument name="brand name" default="HERMES"} across the chest area, clean high-end typography, vertical poster layout for a mobile-generated fashion ad.

生成一个抖音直播的截图里面是一个穿着{argument name="服饰" default="中国传统服饰"}的{argument name="性别" default="男子"}在{argument name="动作" default="直播卖货"}

A side-by-side social media comparison graphic on a dark black background, showing a camera-angle transformation test for a busy restaurant interior. At the very top, large white sans-serif text reads: {argument name="headline text" default="Show me the POV from someone standing behind the bar looking out over this crowded restaurant. Change NOTHING in the scene other than the pov"}. Below that, centered on the page, are 2 vertically stacked rectangular photos with rounded corners. To the left of the top image, large white text reads "Source"; to the left of the bottom image, large white text reads "Output". The top image shows the original restaurant scene from the customer side facing the back bar: a warm, upscale, crowded restaurant at night with a massive illuminated wall of liquor bottles on shelves, wood ceiling beams, hanging globe pendant lights, bartenders and servers working, and many seated guests in the foreground and midground. The lower image shows the same restaurant with the same lighting, décor, crowd density, bottle wall, pendant lights, and overall atmosphere, but from a new viewpoint: the camera is now standing behind the bar looking outward across the crowded dining room. In the foreground of the lower image, include the bar counter surface with glassware, bottles, metal bar tools, and a glowing POS touchscreen at front left, reinforcing the behind-the-bar POV. Keep both photos photorealistic, warm amber lighting, lively evening ambiance, and maintain the sense that the lower image is the same scene with only the camera angle changed. Add subtle social-post styling with generous margins and clean layout, suitable for a tweet screenshot or AI image comparison post.

A two-panel comparison graphic on a black background demonstrating a dramatic camera-angle change in an anime-style crowded street scene. Place a large white sentence centered across the top: "{argument name="headline text" default="Move the camera POV to be at ground level in the crowd."}". On the left side, add two large white labels aligned with the panels: "Source" beside the upper panel and "Output" beside the lower panel. Create exactly 2 stacked rectangular image panels centered on the canvas. In the top panel, show a high-angle overhead view of a densely packed historical street crowd in a hand-painted anime film style, with dozens of people pressed together around horse-drawn carts and wagon wheels; include bundled luggage, hats, muted earth-tone clothing, blue and tan garments, and a busy composition where figures overlap in every direction. In the bottom panel, recreate the same type of scene but shift the camera to a low, ground-level point of view inside the crowd, looking between bodies and beside a large wagon wheel on the right edge. The foreground should feel immersive and cramped, with several bent or crouched figures close to the camera, a person in a muted purple robe on the left foreground, a kneeling or hunched figure in tan near the center bottom, and a woman in a light blue dress or coat toward the right-middle turning through the crowd while holding a small child. Keep the environment as a chaotic old-world market or transit street with horses, carts, people in brimmed hats and simple period clothing, dusty ground, and warm subdued colors. Use soft cinematic anime lighting, painterly shading, and the visual feel of a classic Studio Ghibli crowd sequence. The overall image should read as a before-and-after camera experiment, with the upper panel as the original overhead composition and the lower panel as the transformed low-angle perspective.

A hyperrealistic close-up portrait of a young Japanese woman idol, framed vertically from the shoulders up, with her head slightly tilted and looking directly into the camera. She has {argument name="hair color" default="jet black"} straight medium-length hair with full blunt bangs that partially cover her forehead and lightly frame both sides of her face. Her skin is very smooth and pale with soft even lighting, large dark brown eyes with a gentle glossy catchlight, a small natural nose, and subtly glossy pink lips parted slightly to reveal uneven front teeth, with one upper tooth visibly irregular and overlapping, creating a charming imperfect smile. Her expression is calm, soft, and innocent. She wears a delicate light blue frilled lace top with sheer ruffle details visible at the shoulders. The background is softly blurred in cool pastel tones of lavender, blue, and pink, suggesting an indoor stage or event backdrop with bokeh-like highlights. Emphasize realistic facial texture, accurate asymmetrical teeth, beauty-idol photography styling, shallow depth of field, and a clean polished Japanese portrait aesthetic.

出一个人物+{argument name="性格" default="enfp"} 的解读，类似一个人物性格属性解读的感觉，要{argument name="风格" default="二次元风格"}

Create a hyper-detailed comedic Japanese arcade fighting game screenshot styled like a versus battle scene, using a real-world photo aesthetic with game UI overlaid on top. The scene shows an intense mock battle between two groups of theme-park fans competing for the front row at an outdoor show plaza in Tokyo DisneySea. Use a wide 16:9 composition. In the background, clearly show Mediterranean Harbor and Mount Prometheus under bright daytime skies, with the waterfront and DisneySea architecture visible. In the foreground, show exactly 10 young adult people in winter casual clothing, split into 2 opposing teams of 5, physically leaning, grabbing, reaching, and shoving in a tug-of-war-like scrum over position, with exaggerated competitive body language and frozen action as if in a fighting game. Faces should be anonymized with soft blurred blocks. Add floating character labels above each person with levels and names in Japanese. The overall tone is absurdly realistic, like a real candid photo transformed into a polished arcade game battle screen. Add a full Japanese fighting-game HUD with glossy blue-versus-red interface styling. At the very top, place a center stage title bar reading "東京ディズニーシー　ミッキー広場　ショー最前列バトル" and a large timer in the middle reading "TIME 89". In the top left, add a blue team header "PLAYER1" and team name "最前列ガチ勢A". In the top right, add a red team header "RIVAL" and team name "ライバルグループB". On the left side, stack exactly 5 blue player status panels with portraits, level, Japanese class-like nicknames, HP, SP, and BURST meters. The 5 left-side labels are: "Lv.25 ガチ勢リーダー ユウキ", "Lv.24 筋肉マン タケシ", "Lv.23 眼鏡オタク シンジ", "Lv.23 開角心MAX ケント", "Lv.22 サポート要員 リョウ". On the right side, stack exactly 5 red rival status panels with the labels: "Lv.27 ライバルリーダー ダイキ", "Lv.26 パワフル代表 マサル", "Lv.24 戦略家 コウジ", "Lv.23 熱血漢 リク", "Lv.22 サポート女子 サキ". Each panel should include numeric HP and SP values and segmented BURST gauges, styled like a Japanese arcade RPG-fighter interface. Place exactly 10 in-battle nameplates above the fighters in the center scene, color-coded blue for the left team and red for the right team. The 10 labels are: "Lv.24 タケシ", "Lv.25 ユウキ", "Lv.23 シンジ", "Lv.23 ケント", "Lv.22 リョウ", "Lv.27 ダイキ", "Lv.26 マサル", "Lv.23 リク", "Lv.22 サキ", "Lv.22 ミサキ". At the lower left, add a skill menu titled "スキル" listing exactly 5 skills with SP costs: "ダッシュ突撃 SP 20", "肩押し強奪 SP 25", "荷物で場所確保 SP 15", "ロープくぐり SP 10", "本気の根性 SP 50". Beneath that, add a dark description box explaining the highlighted skill "本気の根性" with the Japanese text: "気合で相手を威圧し、どかす！ 一定時間、相手が怯みやすくなる！ （バーストゲージを大きく消費する） 効果時間：10秒". At the bottom center, add an item menu titled "アイテム" with exactly 5 item slots showing icons and counts: a water bottle "x3", a folded purple towel "x2", a blue drawstring bag "x1", a gray backpack "x1", and a boxed meal "x2". At the lower right, add a quest panel titled "クエスト" with the mission text "ショー開始までに最前列を死守しろ！" and condition text "条件：ライバルグループを全員後ろに押し戻せ！" and countdown text "ショー開始まで：02:30". Beside it, add a mini-map titled "ミッキー広場MAP" showing red and blue dots for both teams in the plaza. Along the very bottom edge, include small controller prompts in Japanese for actions such as skill use, item use, grab/push, and dash. Use dramatic, saturated lighting, crisp detail, realistic clothing folds, authentic plaza stone pavement, and a high-end Japanese game screenshot look. The image should feel like a ridiculous but believable crossover between a real Tokyo DisneySea crowd photo and a competitive arcade battle game interface.

A high-end studio fashion portrait of a {argument name="subject gender" default="woman"} in her mid-30s to early 40s with a naturally fit build, shown in a half-body to upper-thigh framing, standing in a relaxed, confident pose with both hands tucked into her pants pockets. She has long, dark chestnut-brown wavy hair parted near the center, softly cascading over her shoulders, and wears 2 small gold hoop earrings on one visible ear, a delicate gold necklace, and a thin bracelet. Her outfit is modern minimal casual streetwear in soft neutral tones: a light beige zip-front jacket worn open, a fitted white cropped tank top, and matching light beige drawstring jogger pants. Shoot at eye level with an 85mm portrait lens at f/2.8, keeping the subject tack sharp with shallow depth of field. Use professional studio lighting with 1 softbox key light from the front-left, subtle fill to soften shadows, and 1 gentle warm rim light along the hair and shoulder for separation. The background is a clean studio backdrop with a smooth taupe-to-warm-gray neutral gradient and no distractions. The image should feel highly realistic and editorial, with natural skin tones, balanced color grading, ultra-high detail, crisp fabric texture, soft natural shadows, no noise, no motion blur, no cartoon styling, and no anatomical distortions.

A 4x3 photo collage of 12 cinematic, nostalgic snapshots of a young Japanese couple in everyday life, shot like candid film photography with soft blur, muted colors, grain, bloom, and shallow depth of field. The overall mood is intimate, wistful, urban, and slightly melancholic, with a warm-and-cool mixed color palette and natural imperfect composition. Include 12 distinct photos: 1) a close nighttime portrait on a city street, one person in a scarf, face partially obscured, surrounded by glowing bokeh lights; 2) the couple sitting closely together on a train at night, leaning on each other, quiet and sleepy; 3) a rear three-quarter view of one person walking alone on a city street at night with traffic lights and storefront bokeh; 4) a rooftop or elevated outdoor portrait at dusk or early morning, one person turning back toward camera with windblown hair and a jacket; 5) a bright daytime suburban street snapshot with one person standing near a hedge, casual and slightly overexposed; 6) a very close, dimly lit selfie-like frame of the couple together indoors or at night, both faces soft and out of focus; 7) the couple seated side by side on a beach watching the sunset over the ocean, seen from behind; 8) the couple talking across a small table inside a cozy izakaya or retro restaurant with posters and warm tungsten lighting; 9) a cramped candid indoor or transit photo with one person slumped or resting, heavy motion blur and dark green tones; 10) the couple standing face to face in a narrow alley at night, surrounded by lantern light and vertical Japanese signs; 11) a quiet cropped detail shot of intertwined hands and draped clothing while sitting outdoors beside pavement; 12) a night portrait with one person against a background of tall city buildings and colorful defocused lights. Keep all 12 images borderless in a seamless grid, with slight variation in framing and exposure, as if taken over many dates and ordinary moments. Use {argument name="film style" default="moody 35mm film"}, {argument name="couple age" default="early 20s"}, {argument name="city" default="Tokyo"}, {argument name="season" default="autumn"}, and {argument name="overall mood" default="romantic nostalgia"}.

A moody 4-by-3 photo collage made of 12 candid smartphone-style snapshots of a young couple during summer nights in Tokyo, shot with a nostalgic film look, soft grain, muted colors, slight blur, low contrast, dim ambient street lighting, and intimate casual framing. The overall tone is romantic, youthful, private, and documentary-like, with a warm gray-brown palette and a slightly desaturated teal-orange night city atmosphere. The man has messy dark hair, a slim build, and wears a dark overshirt or lightweight jacket over a white T-shirt; the woman has long dark brown hair, a slim build, and wears a white sleeveless top with thin black shoulder straps from a bag. In every panel, both faces are intentionally obscured by large soft-edged blur blocks for anonymity. Include exactly 12 images arranged in a tight seamless grid: top row panel 1, an extreme close-up side profile of the man at night; panel 2, the woman taking a mirror or phone selfie while standing beside the man outdoors at night; panel 3, the couple pressed close together near a street sign with Japanese text; panel 4, the couple kissing at a busy crosswalk in the city. Middle row panel 5, a pavement shadow photo of two people, one making a peace sign; panel 6, the couple standing close on a sidewalk in an urban shopping street; panel 7, a sunset skyline over water with Tokyo Tower visible, no people; panel 8, a high-angle shot looking down on the woman and the man close together on stairs or a walkway. Bottom row panel 9, a tight intimate close-up of the couple touching faces or kissing; panel 10, the man adjusting or touching the woman's hair on a city street; panel 11, the couple riding together on a scooter or motorcycle, both wearing helmets, captured in motion blur; panel 12, the couple embracing against a pale blue sky, framed from the shoulders up. Backgrounds should include Japanese city streets, storefronts, crosswalks, signage, buildings, night traffic, and urban evening ambience. Keep the composition casual and imperfect like real memories, with varied crops, soft focus, motion blur, and authentic handheld phone photography.

{argument name="テーマ" default="実在しそうだけど絶妙におかしい魔法少女"}がでてくる架空のアニメポスター {argument name="枚数" default="4"} 種類。プロデザイナーが制作したレベルで。 アニメの企画・設定自体が「こんなのアニメ化する?」っていう、本気なのに思わず笑っちゃうシュールなアニメ。 タイトルと放映情報も日本語で見える状態で。 Format {argument name="比率" default="2:3"} 画像生成モデルは duct-tape-1か duct-tape-2、3 を指定したいです。

{"type":"anime character reference sheet","subject":"single female character design board","style":{"medium":"clean polished anime illustration","presentation":"Japanese character sheet / profile board","mood":"earnest, gentle, optimistic, intelligent","rating":"SFW"},"character":{"name":"{argument name=\"character name\" default=\"高梨 ことみ\"}","reading":"たかなし ことみ","role":"female university student, 2nd year","age":"20","height":"159 cm","build":"slim curvy build with long legs","hair":{"color":"{argument name=\"hair color\" default=\"brown\"}","style":"short bob with soft volume, rounded silhouette, side-swept bangs, glossy highlights"},"eyes":{"color":"brown"},"personality":"hardworking, mentally strong, kind, polite, forward-looking"},"outfit":{"theme":"{argument name=\"outfit theme\" default=\"dark purple glossy ribbon-themed dress\"}","pieces":["short glossy dark purple puff-sleeve mini dress with corset-like fitted torso","large ribbon bow at the collar","semi-sheer black tights or glossy thigh-high styled legwear","black high heels","small handbag in the left showcase image"]},"layout":{"background":"light beige paper-like board with purple section headers and thin borders","sections":[{"title":"main visual","position":"left column","count":1,"labels":["full-body standing illustration in a nighttime urban entrance scene with warm lights and stairs behind her, one hand near chest, handbag at side"]},{"title":"キャラクターデザイン","position":"upper middle-left","count":3,"labels":["front view","side view","back view"]},{"title":"表情集","position":"upper middle-right","count":6,"labels":["gentle smile","soft neutral","slightly shy","calm closed-mouth smile","concerned or hesitant","serious attentive look"]},{"title":"基本情報","position":"bottom left","count":5,"labels":["体重","スリーサイズ","瞳線の色","髪の色","イメージカラー / モチーフ"]},{"title":"好きなこと・得意なこと","position":"bottom center-left","count":5,"labels":["読書","カフェでゆっくり過ごすこと","日記や文章を書くこと","書道","朝のランニングやストレッチ"]},{"title":"ポーズ集","position":"bottom center-right","count":3,"labels":["strap-holding pose","forward-leaning polite pose","finger-near-lips thoughtful pose"]},{"title":"プロフィール","position":"upper right","count":13,"labels":["名前","学年","年齢","身長","誕生日","血液型","所属","住まい","趣味","特技","好きなもの","苦手なもの","一人称 / 性格"]},{"title":"キャラクター設定","position":"mid-right","count":5,"labels":["daily effort toward physical improvement","aims to balance health and beauty","very polite speech and manners","kind and caring to friends","wants to use writing in future work"]},{"title":"セリフサンプル","position":"bottom right","count":4,"labels":["gentle encouraging line","slightly troubled reaction","surprised flustered line","warm thankful line"]}],"header":{"main_name":"{argument name=\"headline text\" default=\"高梨 ことみ\"}","subtitle":"努力家で芯が強い、優しく前向きな女の子","class_label":"学生（大学2年生）"}},"composition":{"canvas":"landscape, wide reference sheet","centerpiece":"formal multi-panel character design document","design_language":"professional anime setting materials with purple accents, crisp typography, neat spacing, white panels"},"rendering":{"quality":"high detail","linework":"refined clean lines","color":"rich glossy shading with strong specular highlights on clothing","face_visibility":"clear visible anime face","finish":"official-style character setting art"}}