프롬프트 · 창작 탐험

프롬프트 갤러리

실제 프롬프트와 생성 예시를 탐색하세요. 다음 창작 임무를 위한 영감을 찾고 전체 프롬프트를 무료로 복사하세요.

예시
10,974
모델
17
출처
1277
10,974 개의 프롬프트 예시 · 페이지 84 / 229
Example generated from “Automatic coffee machine process infographic”
GPT Image 2.6 Sunbursten

Create a detailed Infographic of the functioning and flow of an automatic coffee machine like a Jura. From bean basket, to grinding, to scale, water tank, boiler, etc. I'd like to understand technically and visually the flow.

Example generated from “Thread streetwear campaign with exact tagline”
GPT Image 2.6 Sunbursten

Give me a cool in culture ad / fashion shot for a brand called Thread. It's a hip young street brand. The ad shows a group of friends hanging out together with the tagline "Yours to Create." Make it feel like a polished campaign image for a youth streetwear audience: stylish, contemporary, energetic, and tasteful. Use clean composition, strong color direction, natural poses, and premium fashion photography cues. Render the tagline exactly once, clearly and legibly, integrated into the ad layout. No extra text, no watermarks, no unrelated logos.

Example generated from “Field and Flour bakery logo”
GPT Image 2.6 Sunbursten

Create an original, non-infringing logo for a company called Field & Flour, a local bakery. The logo should feel warm, simple, and timeless. Use clean, vector-like shapes, a strong silhouette, and balanced negative space. Favor simplicity over detail so it reads clearly at small and large sizes. Flat design, minimal strokes, no gradients unless essential. Fully transparent background. Deliver a single centered logo with generous padding, clean alpha edges, and no solid backdrop, scenery, checkerboard, or watermark.

Example generated from “Local farmers market app preview”
GPT Image 2.6 Sunbursten

Create a realistic mobile app UI mockup for a local farmers market. Show today's market with a simple header, a short list of vendors with small photos and categories, a small "Today's specials" section, and basic information for location and hours. Design it to be practical, and easy to use. White background, subtle natural accent colors, clear typography, and minimal decoration. It should look like a real, well-designed, beautiful app for a small local market. Place the UI mockup in an iPhone frame.

Example generated from “Cellular respiration classroom diagram (illustrative)”
GPT Image 2.6 Sunbursten

Create a simple biology diagram titled "Cellular Respiration at a Glance" for high school students. Show how glucose turns into energy inside a cell. Include glycolysis, the Krebs cycle, and the electron transport chain. Use arrows to connect the steps, and label the main molecules: glucose, pyruvate, ATP, NADH, FADH2, CO2, O2, and H2O. Make it look like a clean classroom handout or slide, with a white background, simple icons, clear labels, and easy-to-read text. Avoid tiny text, extra decoration, or anything that makes the diagram hard to understand.

Example generated from “Market opportunity slide with fictional figures”
GPT Image 2.6 Sunbursten

Create one pitch-deck slide titled **"Market Opportunity"** that feels like a real Series A fundraising slide from a YC-backed startup. Use a clean white background, modern sans-serif typography like Inter, and a crisp, minimal layout. The slide should include: * A TAM/SAM/SOM concentric-circle diagram in muted blues and grays * Specific, believable market sizing numbers: * **TAM:** $42B * **SAM:** $8.7B * **SOM:** $340M * A clean bar chart below showing market growth from **2021 to 2026**, with a subtle upward trend * Small footnotes: **"AGI Research, 2024"** and **"Internal analysis"** * A company logo placeholder in the bottom-right corner The design should look like it belongs in a deck that actually raised money: highly readable text, clear data hierarchy, polished spacing, and professional startup-style visual language. Avoid clip art, stock photography, gradients, shadows, decorative elements, or anything that feels generic or overdesigned.

Example generated from “Transparent shampoo product cutout (reference required)”
GPT Image 2.6 Sunbursten

Extract the product from the input image and isolate it on a fully transparent background. Output: centered product, crisp silhouette, no halos/fringing. Preserve product geometry and label legibility exactly. Add only light polishing. Do not add a solid backdrop, checkerboard, scenery, or shadow. Do not restyle the product; remove the background and preserve clean alpha transparency.

Example generated from “1969 Bethel crowd reconstruction”
GPT Image 2.6 Sunbursten

Create a realistic outdoor crowd scene in Bethel, New York on August 16, 1969. Photorealistic, period-accurate clothing, staging, and environment.

Example generated from “Preserve identity while changing clothing (references required)”
GPT Image 2.6 Sunbursten

Edit the image to dress the woman using the provided clothing images. Do not change her face, facial features, skin tone, body shape, pose, or identity in any way. Preserve her exact likeness, expression, hairstyle, and proportions. Replace only the clothing, fitting the garments naturally to her existing pose and body geometry with realistic fabric behavior. Match lighting, shadows, and color temperature to the original photo so the outfit integrates photorealistically, without looking pasted on. Do not change the background, camera angle, framing, or image quality, and do not add accessories, text, logos, or watermarks.

Example generated from “Combine woman and dog references (references required)”
GPT Image 2.6 Sunbursten

Place the dog from the second image into the setting of image 1, right next to the woman, use the same style of lighting, composition and background. Do not change anything else.

Example generated from “Place a person in a campsite scene (reference required)”
GPT Image 2.6 Sunbursten

Generate a highly realistic action scene where this person is running away from a large, realistic brown bear attacking a campsite. The image should look like a real photograph someone could have taken, not an overly enhanced or cinematic movie-poster image. She is centered in the image but looking away from the camera, wearing outdoorsy camping attire, with dirt on her face and tears in her clothing. She is clearly afraid but focused on escaping, running away from the bear as it destroys the campsite behind her. The campsite is in Yosemite National Park, with believable natural details. The time of day is dusk, with natural lighting and realistic colors. Everything should feel grounded, authentic, and unstyled, as if captured in a real moment. Avoid cinematic lighting, dramatic color grading, or stylized composition.

Example generated from “Shampoo highway billboard (reference required)”
GPT Image 2.6 Sunbursten

Create a realistic billboard mockup of the shampoo on a highway scene during sunset. Billboard text (EXACT, verbatim, no extra characters): "Fresh and clean" Typography: bold sans-serif, high contrast, centered, clean kerning. Ensure text appears once and is perfectly legible. No watermarks, no logos.

Example generated from “Introduce a watercolor forest hero”
GPT Image 2.6 Sunbursten

Create a children’s book illustration introducing a main character. Character: A young, storybook-style hero inspired by a little forest outlaw, wearing a simple green hooded tunic, soft brown boots, and a small belt pouch. The character has a kind expression, gentle eyes, and a brave but warm demeanor. Carries a small wooden bow used only for helping, never harming. Theme: The character protects and rescues small forest animals like squirrels, birds, and rabbits. Style: Children’s book illustration, hand-painted watercolor look, soft outlines, warm earthy colors, whimsical and friendly. Proportions suitable for picture books (slightly oversized head, expressive face). Constraints: - Original character (no copyrighted characters) - No text - No watermarks - Plain forest background to clearly showcase the character

Example generated from “Continue the forest hero story after snow (reference required)”
GPT Image 2.6 Sunbursten

Continue the children’s book story using the same character. Scene: The same young forest hero is gently helping a frightened squirrel out of a fallen tree after a winter storm. The character kneels beside the squirrel, offering reassurance. Character Consistency: - Same green hooded tunic - Same facial features, proportions, and color palette - Same gentle, heroic personality Style: Children’s book watercolor illustration, soft lighting, snowy forest environment, warm and comforting mood. Constraints: - Do not redesign the character - No text - No watermarks

Example generated from “Yellow Gingham Nurse Outfit Prompt”
GPT Image 2en

Cute pastel yellow and white gingham nurse outfit, sweet Lolita-inspired dress, puff sleeves, delicate white lace ruffles, frilled apron, fitted waist, fluffy layered skirt, oversized gingham bows, pearl buttons, matching yellow gingham nurse cap with white frills and tiny floral decorations, soft pastel colors, adorable elegant style, gentle smile, dynamic pose, detailed fabric textures, no red cross, no medical symbols, masterpiece, best quality.

Example generated from “Autumn Illustrated Sticker Transformation — Reference Image Required”
GPT Image 2en

Transform the uploaded photo into a charming, hand-drawn AUTUMN ILLUSTRATED STICKER. Preserve the original subject: Accurately recreate the person, pet, or group, maintaining recognizable facial features, hairstyle, clothing, colors, pose, expression, and distinctive details. Illustration style: Completely redraw the subject as polished digital character art with soft hand-painted shading, clean organic outlines, expressive features, subtle textures, and warm autumn colors. Avoid photorealism and 3D rendering. Sticker effect: Add a thick, smooth white die-cut border around the entire illustrated subject, with a subtle shadow for a realistic sticker effect. Autumn aesthetic: Incorporate tasteful seasonal details such as orange leaves, tiny pumpkins, cozy clothing, berries, acorns, or warm sparkles. Use burnt orange, terracotta, caramel, cream, and warm brown. Background: Keep the original photographic background visible behind the sticker, gently softened if necessary. Final result: A cozy, personalized, collectible autumn sticker with a clear contrast between the fully illustrated subject and the real photographic background. Do not simply apply a filter or outline to the original photo.

Example generated from “Cinematic Night Market Swordswoman”
GPT Image 2en

Ultrawide 2.2:1, photorealistic cinematic, young swordswoman turning back over shoulder in lantern-lit night market, warm lantern glow vs cold blue night. One subject. 【Composition】Three-quarter back view, left of center, face at 41% width, 38% height, 30% frame height. Right 55% background: lantern orbs receding into blur. Dark sword hilt at 24% width, low unraised. Camera shoulder height, telephoto, shallow DOF. 【Character】Young woman, oval face, soft jaw, pointed chin, warm night light on skin, satin sheen. Dark brown eyes, smoky eyeshadow, defined lashes, straight strong brows. Lips muted dark red, closed, no smile. Expression: calm, aloof, quietly alert — like a skilled swordswoman assessing her surroundings. Body walking away, head turns back over shoulder, eyes meet viewer directly with clear deep gaze, brows level. Loose black strands naturally fall across forehead and cheek, wind-swept, not damp. 【Hair/Costume】Very long black hair, half tied back half loose, natural flowing texture, strands blowing gently in night breeze, edges rimmed gold by lantern light. Plain white wandering swordsman's robe, wide sleeves, dark teal-black cross-collar inner layer, matte fine-woven cloth, white warmed to pale gold. No jewelry, no embroidery — understated elegance. Sword shows only plain dark hilt, short cord wrap. 【Pose】Torso faces away toward street depth, shoulders three-quarter back, weight shifting forward mid-step. Only head and neck rotate back, chin level, face meets lens across shoulder. Arms unemphasized, sword low behind. Turn continuous through spine and neck. 【Environment】Old-town night market: wooden shopfronts dim left, blurred signboard top center, strings of paper lanterns receding right into warm orange bokeh. Far street and lower right carry cold blue-grey shadow, wet stone sheen. No readable text. No other people. 【Lighting】All light from lanterns. Large lantern group behind right blooms warm orbs, rims hair and shoulder gold. Nearer lantern throws diagonal warm patch across left cheek and jaw, rest of face in cool blue shadow — warm and cold divide face. Background left amber-brown, right blue-grey night. Palette: lantern amber #E8A04C, night blue #33455C, shadow brown #241A14, robe white #E9DCC8, hair black #14100E, lip red #8E4A42, skin highlight #D9A37E. 【Rendering】Photorealistic cinematic, filmic grain-free: skin fine satin, hair natural flowing strands with specular edges, cloth matte weighty. Sharpness on eyes and face strands; lanterns and street dissolve into layered bokeh, air carries faint night haze. Negative: second person, drawn weapon, readable text, watermark, logo, anime, cartoon, oversaturated, plastic skin, extra limbs, centered, full-body, focused background.

Example generated from “Pumpkin Dress Halloween Prompt”
GPT Image 2ja

ハロウィンのパンプキンスカートを着た女の子。 衣装はナチュラルベージュのオフショルダーミニドレス。スカートはふんわりと丸く膨らんだパンプキン型で、細い縦溝が入っている。溝の色はハニーカラー。スカートの表面には小さなジャック・オー・ランタンの顔が 1 つ、刺繍ではなくエンボス加工で施されている。ウエストには太めのオレンジのリボン。 肩にはショート丈のナチュラルベージュのケープ。頭には帽子をかぶっていない。カラーはナチュラルベージュ、ハニー、ライトオレンジ、ナイトブルー。 全身、正面からのアングルで、パンプキン型のスカートがはっきりと見える構図。幸せそうに微笑む表情。

Example generated from “Candle Dress Halloween Girl Prompt”
GPT Image 2ja

ハロウィン用に、ろうが滴るようなドレスを着た女の子。衣装はハニーカラーのオフショルダーミニドレス。肩やスカートの裾から白いろうが垂れているような立体ディテールがあしらわれている。ろうの表面にはわずかなツヤがあり、小さな炎の模様がところどころに散りばめられている。 ウエストには細いブラックリボン。ケープはなし。頭には帽子をかぶっていない。首元には小さなキャンドルチャーム。 カラー:ハニー、ホワイト、ライトオレンジ、ナイトブルー。ろうの滴るディテールがよく見える角度からの全身ショット。静かな微笑み。

Example generated from “Giant Head Miniature Body Photo Prompt — Reference Image Required”
GPT Image 2en

Create a 1:1 square, ultra-realistic overhead photograph based on the uploaded selfie. The selfie is the sole reference for the person's identity. Preserve the same recognizable adult face, natural facial proportions, skin tone, hairstyle, original expression, visible clothing (including existing prints), and accessories. Naturally complete any unseen trousers and shoes to match the original outfit. CAMERA & ENVIRONMENT Position the camera almost directly above the person, looking vertically downward. The setting is a clean, spacious, light-colored indoor stone floor or outdoor paved surface that matches the aesthetic of the original selfie. Use large paving slabs with only 2–3 thin, widely spaced seams across the entire frame. Each slab should be approximately twice the height of the miniature full-body figure. Keep the stone texture subtle and refined, with no props, plants, or clutter. A distant wall base may appear along the top edge. COMPOSITION & PROPORTIONS Only one person stands slightly below the center of the frame, fully visible from head to toe. The entire figure occupies just 40% of the image height, leaving extensive empty floor space above the head and on both sides. Use extreme wide-angle forced perspective to create an enormous, realistic head and a miniature body. The head, from crown to chin, occupies 75% of the figure's total silhouette height. The shoulder width is only 50% of the head width. Below the head, create an extremely short, narrow torso, miniature arms, perspective-compressed short legs, and two tiny shoes placed close together. The head and body must connect seamlessly. Both arms hang naturally close to the sides. The person tilts their head upward and looks directly toward the elevated camera. Preserve realistic facial anatomy, natural skin texture, and lifelike eyes. Absolutely no cartoon styling or collage effects. LIGHTING & REALISM Use natural lighting, realistic individual hair strands, authentic fabric textures, finely detailed stone surfaces, physically accurate contact shadows, and subtle film grain. The final image must look like a genuine photograph captured with a real camera.

Example generated from “Capybara Yuzu Hot Spring Sticker”
GPT Image 2en

A cute, flat-style vector illustration of a capybara soaking in a yuzu hot spring. The capybara has a deadpan, relaxed expression with half-closed eyes and is holding a single yellow yuzu fruit in its mouth. A stack of three wobbling yuzu fruits rests on top of its head. The hot spring is filled with pale yellow water and surrounded by smooth grey stones. To the left, there is a small white drawstring pouch containing a yuzu. Wisps of steam rise from the water. The entire scene is rendered as a sticker with a thick white outline against a solid mint green background.

Example generated from “Retro Portrait: Girl with Plush Dog”
GPT Image 2en

A nostalgic, retro-style photograph of a young Asian woman sitting on a wooden chair. She has short black hair with bangs and is wearing a cream-colored floral blouse and denim shorts. A large beige plush dog toy rests on top of her head. Her expression is melancholic and distant as she looks directly at the camera, hugging her knees to her chest. The background features dark wooden louvered doors or shutters. The image has a vintage film aesthetic with visible grain, scratches, and warm, faded tones typical of Showa-era photography.

Example generated from “Cinematic Car Portrait Prompt”
GPT Image 2en

Candid lifestyle portrait of a young woman sitting in the back seat of a moving car, head tilted back against the seat with eyes gently closed, face turned toward the open window and soaking in the sunlight and breeze. Long, dark brown-black hair with wispy bangs, blowing back in the wind with loose strands flying. Soft, natural makeup, dewy skin, relaxed peaceful expression with slightly parted peach-toned lips. Wearing a plain white oversized crew-neck t-shirt and light grey sweatpants, one knee pulled up with her arms wrapped around it. Dark car interior with a black door panel and silver door handle in the foreground. Outside the window, fast-moving green trees heavily blurred by motion. Warm, bright midday sunlight streaming in, with soft highlights on her face and neck. Dreamy, carefree summer road-trip mood, Korean-style cinematic aesthetic, motion blur in the background, shallow depth of field, 50mm lens, f/2, photorealistic, ultra-detailed skin and hair texture, vertical 9:16 composition.

Example generated from “Cozy Cafe Portrait”
GPT Image 2en

Portrait of a young East Asian woman seated in a cozy café, facing the camera with a slight head tilt and a calm, soft gaze. Very long, layered, dark chestnut-brown hair with wispy curtain bangs, loose and slightly tousled, with natural highlights and strands falling over her shoulders. Dewy, flawless skin, soft natural makeup, warm peach-pink lips, subtle brown eyeliner. Wearing an oversized beige knit V-neck sweater with a soft fuzzy texture, layered delicate gold necklaces with a round medallion pendant, and small gold huggie earrings. Seated on a woven rattan café chair. Background: a large black-framed window with blurred autumn greenery, dark wooden bookshelves with warm wood shelves, framed photos and a small potted plant, all softly out of focus. Warm golden-hour sunlight, soft diffused window light, cozy autumn mood, earthy beige and brown color palette, Korean-style lifestyle editorial aesthetic, shallow depth of field, 85mm lens, f/1.8, photorealistic, ultra-detailed skin and hair texture, vertical 2:3 composition.

Example generated from “Portrait of Woman Offering Candy”
GPT Image 2en

A photorealistic portrait of a young Asian woman with short, dark hair and natural freckles on her face. She is wearing a light-colored, semi-sheer floral robe or dress with blue flower patterns over a white underlayer. A simple beige hair clip holds back the hair on one side of her head. She is seated in a wooden chair inside a sunlit room with large windows behind her that look out onto green foliage. The lighting is soft and natural, creating a warm, film-like aesthetic. She is looking directly at the camera with a gentle expression, extending her right hand forward toward the viewer to offer three small, round objects (resembling colorful candies or stones) which are slightly out of focus due to the shallow depth of field.

Example generated from “3D Caricature Portrait with Bead Texture — Reference Image Required”
GPT Image 2en

Transform the reference photo into a highly detailed, professional 3D caricature portrait. Preserve the person's recognizable facial features while giving them a creative, slightly exaggerated cartoon appearance. Create intricate textures using thousands of tiny beads, fine engraved lines, and flowing 3D filaments across the face, neck, hair, and clothing. Give the character wild, oversized, spiky orange hair made from individual curved strands, inspired by expressive modern cartoon sculptures. Add large round black glasses if suitable for the character, expressive eyes, and a distinctive facial expression. Use a sophisticated gray studio background with abstract geometric lines, circular outlines, floating dots, tiny splashes, and minimalist technical details. Apply cinematic studio lighting, realistic shadows, sharp focus, rich textures, and premium 3D rendering. Maintain the person's original outfit style and recognizable identity while adapting the entire image to this artistic aesthetic. Ultra-HD, intricate micro-details, professional digital art, sculptural depth, polished CGI, high contrast, clean composition, vertical 2:3 aspect ratio. No text, no watermark.

Example generated from “Shallow Depth of Field I2I — Reference Image Required”
GPT Image 2ja

元画像の人物、衣装、構図、画風をそのまま維持し、被写界深度の浅い立体的なフォーカス表現を適用してください。 ピントの中心は目と顔に合わせます。瞳孔、まつ毛、顔の主要な輪郭線はくっきりと保ってください。顔の焦点面から離れるにつれ、髪、肩、衣装、背景を距離に応じてなめらかにぼかし、人物の内側にも自然なピントの差を作り出します。 カメラに近い髪や肩には柔らかな前ボケを、背景には大きく溶け込むような後ボケを加えてください。背景にある点光源は、柔らかい円形のボケとして描写します。 温かみのある斜め逆光で髪や肌の輪郭を細く照らし出し、強いハイライト部分にのみ控えめなブルームと光のにじみを加えます。影の部分は落ち着いた暗さを保ち、自然と顔へ視線が引き寄せられるようなシネマティックな奥行き感を生み出してください。 画面全体を均一にぼかすことは禁止です。顔のディテールを消したりせず、元の線画や描画の質感をそのまま維持してください。

Example generated from “Showa Retro Portrait of Girl in Floral Kimono”
GPT Image 2en

A vertical portrait of a young woman with short, dark bobbed hair and bangs sitting on a brown tiled floor. She is wearing a loose, semi-sheer floral kimono-style robe in muted tones of cream, navy, and olive green. Her knees are pulled up to her chest, and she rests her chin on her clasped hands, looking directly at the camera with a melancholic expression. On her feet, she wears chunky platform sandals with ruffled white straps. A small flower clip is visible in her hair. The background features a textured white lace curtain. The image has a distinct Showa-era retro aesthetic, characterized by soft focus, warm color grading, and a nostalgic film grain texture.

Example generated from “Showa Retro Beach Portrait”
GPT Image 2en

A vertical medium-shot portrait of a young East Asian woman at the beach, styled with a nostalgic Showa-era retro film aesthetic. She is looking back over her left shoulder directly at the camera with a bright, genuine smile showing teeth. Her hair is dark brown, tied into two low braids or pigtails secured with small bands, and she wears a black hair clip on the side of her bangs. A large, wide-brimmed woven straw hat with a dark brown rim sits on her head, casting dappled shadows across her forehead and eyes. She wears a white eyelet lace top with thin straps, exposing her bare shoulders and upper back which show natural skin texture including small moles and freckles. Her right hand is raised, gently holding the brim of her hat near her cheek. The background features a sunny coastal scene with blue ocean water, white foaming waves crashing on a rocky shore, and a green forested hill in the distance under a clear blue sky. Two blurred figures are visible swimming in the water to the right. The image has a grainy, warm color palette typical of vintage 1970s or 80s Japanese idol photography.

Example generated from “Dramatic Portrait with Red Light on Eyes”
GPT Image 2en

Ultra-realistic dramatic portrait of the person ({argument name="photo" default="imported photo"}), messy hair strand over one eye, black turtleneck, centered, intense gaze. A bright and sharp horizontal red light illuminates only the eyes and reflects on the gray wall; the rest is in deep shadow. Dark, minimalist, and cinematic atmosphere.

Example generated from “Monochrome Elegant Autumn Outfit”
GPT Image 2ja

可愛い黒のギンガムチェックタイトスカート、黒のニットセーター、ベージュのブーツ、モノトーンの上品なスタイル、清潔感のあるファッションルック、柔らかなライティング、質感豊かな生地、洗練された雰囲気、傑作、最高品質

Example generated from “Photorealistic Tang Dynasty Hanfu Portrait”
GPT Image 2zh

古风女性角色,竖版 9:16,超写实摄影,85mm 人像镜头,8K 超高清。照片级真实人像:一位 20 岁的东亚年轻女子,化着中国唐代古风妆容,胸部以上的半身特写,展现面部、颈部、肩部及上半身,相机与眼睛平齐,头部向右倾斜 6 度,下巴微抬,透着一股不服输的倔强。 [眼部] 杏仁眼——标准的杏眼形状,眼尾自然拉长,内眼角圆润。上眼睑微微绷紧,下眼睑紧实,目光锐利,直视镜头,带着少女特有的倔强。浓密纤长的根根睫毛清晰自然,捕捉到来自上方的轮廓光。眼神中透着娇嗔的怒意——不是空洞地凝视,而是与观者产生互动,仿佛在抗议某种不公,又带着一丝期待,像是在等对方道歉。 [骨相结构] 面部与下颌线从颧骨到下巴过渡流畅,明暗交界柔和清晰。眼窝、鼻梁两侧和下唇下方保留自然的微弱阴影,塑造出立体的骨相结构,边缘不生硬。双唇明显前撅,下唇微微上抬,嘴角向下撇,下巴抬起,形成一副倔强的神情。皮肤质感自然,鼻翼和脸颊可见细腻毛孔,细微的绒毛在轮廓光下若隐若现,因强忍情绪,颧骨处泛起一抹红晕,额头和鼻尖带有自然的皮脂光泽。 [身形与服饰] 身材高挑纤细、体态曼妙,双肩削瘦,手臂修长,姿态优雅。身穿中国传统汉服——一套浅黄色襦裙,交领上衣采用浅黄色真丝缎面,绣有白色花卉图案。衣襟在胸前交叉,形成优雅的 V 字领口,凸显精致的锁骨与柔美的肩线。上身剪裁得体,工艺考究,丝绸面料自然垂坠,褶皱灵动飘逸,腰间系着白色丝带,打成装饰性蝴蝶结。多层半透明白纱从肩部垂落,在光线映照下营造出空灵飘逸的动态感。丝绸面料随身体姿态呈现自然褶皱,尽显女性的柔美优雅与青春活力。 [姿势] 直立站姿的半身像,重心自然落在左侧,双臂交叉抱于胸前(防御姿态),双手搭在对侧大臂上,手指微微用力,宽大的衣袖自然下垂,受力侧的肩膀放松但略带紧绷,头部微向右倾,下巴抬起。整个姿势既有年轻女孩赌气时的倔强与恼怒,又惹人怜爱。 [配饰与细节] 乌黑秀发梳成双环髻,几缕细碎散发垂落两侧,右侧插着一支金琥珀发簪,珍珠流苏垂坠而下。额头点着金色花钿,眼影为淡金色,棕色眼线细长(眼尾自然拉长),珊瑚粉色口红(哑光质地),脸颊扫着自然腮红(暗示并非真的动怒),双唇紧撅(明显突出),眉头微蹙(增添几分怒意)。 [光影] 左上方射入的黄金时刻侧光(色温 3500K)精准勾勒出面部、颈部和手臂的曲线,在颧骨和鼻梁处留下温暖的高光。头顶的发丝轮廓光营造出光晕效果。自然的光线衰减增强了画面纵深感,丝绸面料呈现方向性反光,曲面处高光明亮,层叠的褶皱间阴影深邃,半透明的薄纱层散发出空灵的光泽。皮肤质感极其逼真,毛孔清晰可见,带有轻微瑕疵,毫无塑料感。背景为虚化的中国传统建筑或园林景致,光斑柔和,暖色调与人物光影相呼应。宽高比 9:16,高分辨率,专业摄影风格。

Example generated from “Mediterranean Garden Portrait”
GPT Image 2zh

午后,地中海湖畔花园。阳光从高处斜洒而下。远处湖面湛蓝静谧,群山薄雾缭绕。浅色别墅与修长的柏树错落散布于湖畔。前景为欧式石砌露台。白色大理石栏杆、雕花立柱,大型花盆沿步道依次排开。盛开的纯白与浅紫色花朵,从拱门、墙面和花器中自然垂落。 一位年轻女子伫立在花园露台中央。她身着一袭浅紫与乳白渐变的轻薄透视长裙。层层半透明薄纱被微风轻轻托起,裙摆自然舒展。她微微侧身,一手轻提裙摆,另一手搭在锁骨附近。长发随风向后飘拂,发间点缀着白色花朵配饰。姿态毫不刻意,仿佛只是湖畔漫步时的短暂驻足,恰好被阳光温柔定格的一瞬。 整体氛围宁静、明亮而柔和,没有强烈的戏剧张力。更像是欧洲私人湖区花园里一个暮春午后。色调以乳白、浅紫、湖蓝、淡绿为主。空气通透澄澈。花瓣、薄纱与水面泛着细腻的微光倒影。质感介于高端婚纱摄影与梦幻生活方式摄影之间。

Example generated from “Tactical Cat Interrogation Scene”
GPT Image 2en

A hyper-realistic, high-resolution studio photograph of two anthropomorphic cats in a military-themed scene against a clean white background. The standing cat is an orange tabby wearing full modern tactical gear, including a camouflage helmet with goggles, a heavy plate carrier vest, and combat boots. It holds a black assault rifle with a scope in its right paw and stands triumphantly with its left boot resting on the back of a second cat lying on the ground. The defeated cat is a grey and white shorthair, bound tightly in thick rope, wearing a green military cap with a red star emblem, and sporting exaggerated bruised eyes and a swollen nose to look battered.

Example generated from “Split-Screen Realistic and Anime Illustration — Reference Image Required”
GPT Image 2en

Transform the uploaded photograph into a beautiful split-screen, half-realistic and half-anime illustration with a cute, playful, hand-drawn aesthetic. COMPOSITION & FORMAT Vertical 3:4 aspect ratio. Create one seamless-looking image divided vertically down the center by an irregular, torn white paper edge. The left half shows the original photograph in realistic photographic detail, while the right half reimagines the exact same photograph as a polished, high-quality anime-inspired digital illustration. Both halves must align perfectly, with the same subject, pose, facial direction, hairstyle, clothing, accessories, camera angle, and background placement. The torn-paper edge should look naturally ripped, with rough white fibers and an organic, imperfect shape. LEFT HALF — ORIGINAL PHOTOGRAPH Preserve the uploaded photo as faithfully as possible. Maintain the subject's original identity, facial features, skin tone, hairstyle, expression, clothing, accessories, pose, lighting, and surroundings. Keep realistic photographic textures, natural shadows, and authentic colors. Add a few delicate, hand-drawn doodles around the subject without covering important facial features. RIGHT HALF — ANIME ILLUSTRATION Recreate the same scene in a sophisticated Japanese anime-inspired illustration style blended with soft Korean webtoon aesthetics. Preserve the subject's recognizable identity and original appearance. Use clean, expressive linework, delicate facial details, softly rendered skin, subtle blush, beautifully illustrated hair strands, gentle highlights, smooth shading, and refined color gradients. Keep the original outfit and accessories recognizable. Translate the background into a softly illustrated version of the original environment, preserving its composition and atmosphere. CUTE HAND-DRAWN DOODLES Decorate the illustrated half with charming, colorful doodles drawn directly over the image: - Small pink and red hearts. - Yellow and golden stars, sparkles, and flower outlines. - Tiny white or pastel-colored cartoon cats and bunnies. - Blue paper airplanes, dotted flight paths, and playful symbols. - Hand-drawn curved lines, tiny crowns, cheerful accents, and whimsical decorative marks. Use a loose, sketchbook-inspired drawing style with slightly imperfect outlines, subtle sticker-like borders, and a harmonious pastel color palette of baby blue, blush pink, butter yellow, cream, and white. Arrange the doodles naturally around the subject, following the composition and leaving the face unobstructed. ART DIRECTION Cute, dreamy, youthful, romantic, playful, and aesthetically pleasing. Combine authentic photography with premium anime fan-art illustration and scrapbook-inspired doodle art. Use delicate details, soft natural lighting, balanced colors, and a clean, professionally finished appearance. IMPORTANT RULES 1. Preserve the original person's identity and recognizable appearance. 2. Keep the left half photographic

Example generated from “Cozy Morning Illustration”
GPT Image 2en

A warm, hand-drawn illustration in a cozy watercolor style depicting a young woman waking up in bed. She has messy dark hair and is wearing an oversized white long-sleeved shirt and grey plaid pajama pants with socks. She sits on the edge of a wooden bed frame, stretching her arms high above her head with her eyes closed and a peaceful expression. The bed has rumpled white sheets, blue pillows, and a checkered pillow. An orange tabby cat is curled up asleep at the foot of the bed. To the left, there is a small wooden nightstand holding a blue alarm clock, a white mug with a flower design, and a stack of books. A trailing green plant hangs from the side of the nightstand. In the background, a window shows bright sunlight streaming in, illuminating the room. On the floor near the bed are a pair of striped slippers. At the top of the image, large red handwritten Chinese text reads "早安,慢一点也没关系" (Good morning, it's okay to be slow). Below that, smaller black text reads "醒来这件事,可以慢慢进行。" (Waking up can happen slowly). At the bottom left, small English text says "MORNING MOOD POSTER / good morning" followed by Chinese text "给今天留一个温柔开场" (Leave a gentle opening for today).

Example generated from “Realistic Wall Calendar with Portrait — Reference Image Required”
GPT Image 2en

Create a realistic wall calendar hanging on a textured concrete wall, framed in a warm wooden frame. The top half features my uploaded portrait photo in a soft cinematic style, shallow depth of field, warm bokeh lights in the background, natural skin tones, calm confident expression. The bottom half displays a clean, modern calendar layout for current date, with bold month text on the left and year on the right, neatly aligned date grid below, Sundays to Saturdays clearly labeled. Minimal beige and brown color palette, elegant typography, realistic paper texture, soft natural sunlight casting gentle shadows, premium lifestyle photography look, ultra-high resolution.

Example generated from “Showa Retro Street Portrait”
GPT Image 2en

A vertical medium-shot portrait of a young East Asian woman standing on a busy city sidewalk, captured in the style of authentic 1980s Japanese film photography. She has short dark hair with a small gold barrette clipped to one side and is tilting her head slightly toward the camera with a gentle, candid smile. Her skin shows natural texture with visible freckles across her nose and cheeks. She wears an oversized olive-green wool coat over a plaid skirt, with a thick brown and beige striped knit scarf wrapped around her neck. A thin leather strap from a shoulder bag crosses her chest. The background features a bustling street scene with parked bicycles, vintage cars, pedestrians walking away, and blurred storefront signs with Japanese text. The lighting is soft and warm, characteristic of analog film stock, with noticeable grain and a nostalgic color palette.

Example generated from “Showa Retro Portrait: Woman and Stone Statue”
GPT Image 2en

A vintage-style photograph with a nostalgic Showa-era aesthetic, featuring a young Asian woman with short black hair crouching next to an old, weathered stone komainu (lion-dog) statue. She is wearing a beige short-sleeved button-up shirt with a small brown floral pattern and dark brown shorts. Her expression is calm and slightly melancholic as she looks directly at the camera. The scene is set outdoors on gravel ground near a building wall with visible pipes in the background. The image has a warm, faded color palette typical of 1970s film photography.

Example generated from “Flower Shop and Street Couple — Two-Scene Prompt Pack”
GPT Image 2en

Create a beautiful, nostalgic hand-drawn editorial illustration combining two cozy everyday scenes in a consistent vintage sketchbook style. In the first scene, a young woman with dark brown hair in a messy bun and black glasses, wearing a black outfit, arranges colorful pink roses, coral flowers, tiny white blossoms, and lush greenery inside a charming flower shop, holding a large bouquet wrapped in brown kraft paper. Surround her with potted plants, tropical leaves, blooming flowers, and tall vintage windows. In the second scene, a young couple sits closely together on stone steps along a charming European city street. The man wears a navy baseball cap, headphones, a gray hoodie, a long black coat, blue jeans, and sneakers, while the woman wears a black coat, a soft blue scarf, cream trousers, black sneakers, and carries a brown leather shoulder bag. They share a quiet, affectionate moment surrounded by elegant old buildings, a cozy café, glowing street lamps, bicycles, leafy trees, and pedestrians. Use a harmonious palette of warm cream, olive green, mustard yellow, dusty blue, navy, coral, and soft pink. Add textured colored-pencil strokes, delicate ink outlines, subtle watercolor shading, vintage paper grain, charming hand-drawn accents, and warm natural lighting. Whimsical slice-of-life storytelling, cozy nostalgic atmosphere, artistic imperfections, highly detailed illustration, premium handmade sketchbook aesthetic, consistent art style across both scenes, vertical composition, no photorealism.

Example generated from “Black Cat Halloween Dress Anime Girl”
GPT Image 2ja

ハロウィンの黒猫ドレスを着た、可愛らしい大人の女性。 衣装は、漆黒とダークネイビーのオフショルダーミニドレス。フレアスカートの裾には、ふんわりとした黒いファーと白い肉球の刺繍があしらわれています。背中からは長い黒猫のしっぽのような飾りが優雅に伸びており、ウエストには金色の鈴がついた大きな黒いリボンが結ばれています。胸元には、エメラルド色の目が輝く黒猫のブローチ。肩にはベージュのショートケープがかかり、内側には猫のシルエットが並んでいます。 頭には、ふわふわの黒猫耳カチューシャ。耳の内側は淡いピンク色で、根元には小さな黒いリボンと金色の鈴がついています。ヘアアクセサリーとして自然になじむ、愛らしい黒猫スタイルです。片手には魚の形をしたキャンディを持ち、もう片方の手は猫の手のポーズをとっています。 背景は、満月に照らされた夜の路地裏。足元には小さな黒猫がいます。 頭からつま先までを収めた全身構図。黒猫のしっぽと肉球が見えるように、少し振り返ったポーズ。いたずらっぽく可愛い笑顔。

Example generated from “Convenience Store Photoshoot Collage via Security Mirror — Reference Image Required”
GPT Image 2en

Create an ultra-realistic 3×3 photo collage featuring the same woman from the uploaded reference image, preserving her exact facial identity, face shape, eyes, nose, lips, skin tone, and natural features across all nine frames. CONCEPT & COMPOSITION: A fun, candid convenience-store photoshoot captured from a high-angle convex security mirror. Each frame features the woman looking up toward the mirror with realistic fisheye distortion, curved mirror edges, and a wide view of the store aisles. NINE DIFFERENT SCENES: 1. Smiling and winking while holding an iced coffee, wearing a cream knit sweater. 2. Wearing a black top and reaching toward a snack shelf while holding a shopping basket. 3. Wearing a pink hoodie, making a cute pout while hugging instant noodles and colorful snacks. 4. Wearing a black-and-white striped top and laughing while holding a basket full of groceries. 5. Wearing a white long-sleeve top and blue jeans, crouching down to pick up spilled snacks from the floor. 6. Wearing a light-blue cardigan, smiling brightly while holding a strawberry cream cake beside her face. 7. Wearing a gray hoodie and beige baseball cap, making a peace sign while holding an iced drink. 8. Wearing a black sleeveless top with sunglasses on her head, examining a cup of instant noodles with a curious expression. 9. Wearing a cream knit sweater, happily hugging a large pack of toilet paper. ENVIRONMENT: A brightly illuminated modern convenience store with colorful snack shelves, refrigerated beverage displays, glossy cream-colored tiled floors, shopping baskets, and a few distant shoppers. Include realistic reflections, curved black-and-red mirror frames, and natural overhead store lighting. PHOTOGRAPHY STYLE: Ultra-photorealistic photography, overhead fisheye perspective, wide-angle lens, realistic proportions, natural skin texture, detailed hair strands, authentic expressions, crisp product packaging, balanced exposure, and candid lifestyle photography. COLLAGE LAYOUT: Perfectly aligned 3×3 grid with nine distinct vertical panels, thin white dividers, consistent image quality, and varied poses and facial expressions. Maintain the same recognizable woman throughout all nine frames. STRICT REQUIREMENTS: Preserve the reference woman's facial identity. Keep hands, fingers, and body proportions realistic. Avoid duplicated faces, distorted anatomy, blurry details, excessive beauty filters, cartoon effects, text, logos, and watermarks. Aspect Ratio: Vertical 9:16 Quality: Ultra-realistic, high detail, 8K, professional lifestyle photography.

Example generated from “Suica Penguin in Akihabara”
GPT Image 2en

A vibrant, pop-art style illustration of the Suica Penguin mascot standing in the middle of a busy Akihabara street. The penguin is anthropomorphic with black skin and white eyes, wearing a trendy yellow varsity jacket over a white t-shirt with a pink star, teal cargo pants with yellow stars, and colorful sneakers. It has large headphones around its neck and carries a shopping bag labeled 'メイド CAFE' (Maid Cafe). To the left is a green and white Yamanote line train with 'AKIHABARA AKB' on the display. The background is filled with colorful vertical signs featuring anime characters and text like '電気街' (Electric Town), 'PCパーツ' (PC Parts), 'アニメ' (Anime), and 'ゲーム' (Game). The overall aesthetic is high-contrast, saturated colors with thick outlines.