Lumina Mascot LogoLumina
/
将输入的城市旅行照片制作成一张竖向3:4上下对比转绘海报,上半约50%保留原照片真实摄影,准确保留城市建筑、自然地形、街道、桥梁或水岸的主体、数量、透视和光线,只做轻微出版调...
建筑与空间3:4

将输入的城市旅行照片制作成一张竖向3:4上下对比转绘海报,上半约50%保留原照片真实摄影,准确保留城市建筑、自然地形、街道、桥梁或水岸的主体、数量、透视和光线,只做轻微出版调色;下半约50%把同一城市场景转译为“NESTED VISTA MONOCHROME|叠景窗格水墨构成风”。下半使用灰米纤维纸底、2至5个不同比例的细线矩形观察窗,错位嵌套并提取原照片中的不同景深层;以烟墨线描、皴擦、积墨、干湿墨痕和少量低饱和城市色呈现远近层级。不要完整照搬原取景,不要普通水墨滤镜,保留35%至55%连续留白。下半只放短英文题签“VISTA STUDY”和小字段“INK / PAPER / MEMORY”。中线清晰,不要原图/AI图角标、Logo、水印、假中文、乱码或无关地标。

GPT Image 2.5
适用于任意真实照片,不局限于海洋、鱼类或自然题材。将输入图像转译为一张具有“标本页”气质的上下分区画面。
海报与版式2:3

适用于任意真实照片,不局限于海洋、鱼类或自然题材。将输入图像转译为一张具有“标本页”气质的上下分区画面。 上半部分保留原始照片的真实摄影属性:包括主体与环境的自然纹理、反光、明暗层次、真实色彩和空间关系,使其像被直接截取或保留下来的视觉事实。不得过度滤镜化,不削弱原图的真实感。 下半部分在一张乳白或暖白色、带粗纤维质感的纸面上,以原图主体的轮廓为基础,重建为蓝灰色系的负空间剪影构图。主体的数量、大小比例、方向关系、疏密节奏和整体分布,应与原图保持呼应;但表达方式转为“留白中的轮廓占位”,让主体像被提炼成一种安静、克制的标本形态。 重点不是描绘细节,而是利用主体轮廓、空白区域和纸面呼吸感建立版式秩序。画面应保留大面积安静留白,使下半部分具有展签、图录或观察样本页般的陈列感。可加入极少量辅助图形元素,例如丝网印刷感的细小星芒、轻微透明叠色块、纤细手写说明或注记,但必须克制、稀疏,不喧宾夺主。 整体配色应根据输入照片自然适配,在统一的低饱和、轻雾感系统下协调上区与下区;其中下半部分以蓝灰、灰白、雾青等冷静色调为主。整体气质应安静、轻盈、留白充足,像“真实图像”与“纸上负空间标本”并置于同一页中。 避免:直接海报化装饰、过多图形元素、角标、信息框、厚重拼贴、过强的海洋主题暗示、写实描边插画、主体数量或方向被任意改写、下半部分过满或失去呼吸感。

GPT Image 2.5
将输入照片制作成上下对比:上半区保留真实宠物/主体及其环境;下半区把主体和一个关键环境线索转换为由许多独立方形浮雕砖组成的像素化马赛克壁面,砖块有真实厚度、釉面反光、粗糙边缘...
海报与版式3:4

将输入照片制作成上下对比:上半区保留真实宠物/主体及其环境;下半区把主体和一个关键环境线索转换为由许多独立方形浮雕砖组成的像素化马赛克壁面,砖块有真实厚度、釉面反光、粗糙边缘、逐块阴影和少量脱落空位,颜色从原照片提取,不是平面像素滤镜。让主体轮廓仍清晰可认,周围保留温暖米白墙面、散落砖块和极简排版,可写一句短观察;禁止把所有元素做成同样密度,禁止角标和虚构文字。

GPT Image 2.5
A high-fashion cinematic beauty portrait of an elegant adult East Asian woman against a...
女性美学9:16

A high-fashion cinematic beauty portrait of an elegant adult East Asian woman against a deep crimson-red studio background. She has sleek, glossy jet-black shoulder-length bob hair with soft wispy blunt bangs, natural realistic skin texture, delicate facial features, subtle contouring, dramatic smoky burgundy-brown eye makeup, defined lashes, and rich deep dark-wine burgundy lipstick with a slightly glossy finish.She wears an elegant off-shoulder black couture dress and a tiny sparkling silver stud earring. Three-quarter profile, head slightly tilted upward, confident mysterious gaze toward the camera, slightly parted lips. Soft directional studio lighting, subtle warm highlights, deep shadows, luxurious editorial beauty campaign aesthetic, sophisticated and dramatic mood, ultra-photorealistic, detailed pores and hair strands, professional fashion photography, shallow depth of field, 85mm lens, high-end beauty magazine quality, clean composition, no text, no logo, no watermark, vertical 9:16.

GPT Image 2.5
[image1]
女性美学1:2

[image1] Use The Uploaded Image Of The Woman As Strict Facial Reference And Physical Features - Keep Her Real Face Exactly As Provided, Without Alterations Or Stylization. Ensure Seamless, Ultra-realistic Integration In The Final Render. Black And White High-fashion Editorial Portrait Of The Uploaded Person, Wearing A Loose White Blouse. She Poses With One Arm Raised, Partially Covering Her Face While Holding Her Hair Up, Creating A Dramatic And Artistic Composition. Her Gaze Is Intense And Captivating, Directly Toward The Camera, Exuding A Strong, Enigmatic Aura. Background: Minimalist Plain Wall With Sharp Daylight Shadows Adding Contrast And Depth. Lighting: Harsh Natural Sunlight, High-contrast, Emphasizing Facial Contours, Cheekbones, Hair Texture, And Fabric Detail. Pose: Bold And Expressive, Arm Lifted Framing The Face To Emphasize Raw Emotion And High-fashion Editorial Style. Camera: Eye-level Close-up, Focusing On Facial Expression, Texture, And Dramatic Shadow Play. Captured As If With Canon Eos R5, 85mm F/1.8 Lens - Crisp Detail, Tonal Depth, Fine Grain. Style: Monochrome, Ultra-realistic, Cinematic, High-fashion Editorial Photography.ashion editorial photography.

Banana Pro
Create a 1970s black-and-white close-up portrait in a win...
人物与角色2:3

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

Banana Pro
Use the uploaded image as the EXACT visual reference. Rec...
草图与线稿2:3

Use the uploaded image as the EXACT visual reference. Recreate the original scene faithfully and preserve the same composition, café table, flowers, lantern, cup, folded napkin, chairs, hanging lights, historic street, architecture, mosque/minaret, lighting, camera angle, framing, colors, proportions, and overall nighttime atmosphere. Do NOT redesign, replace, add, remove, or reinterpret any major element. The result must look like the SAME original photograph, only refined into a premium cinematic travel-editorial photograph. STRICT 3:4 vertical format. Preserve the foreground exactly: the rustic wooden café table, cream-colored vase filled with delicate white flowers, vintage glowing metal lantern, small coffee cup and saucer, folded napkin, small white flower on the table, wicker café chairs, and soft blankets draped naturally over the chairs. Keep the historic Istanbul street exactly as shown, including the narrow cobblestone street, traditional stone buildings, warm shop windows, hanging string lights, distant mosque architecture and minaret, pedestrians in the background, café seating, plants, and atmospheric depth. Maintain the original nighttime mood with warm amber lantern light contrasting naturally against the cool blue evening sky. Preserve the soft bokeh, realistic reflections, natural shadows, and intimate café atmosphere. Apply only subtle cinematic color grading, refined tonal balance, realistic textures, natural contrast, soft highlights, and premium film texture. Overall aesthetic: ultra-realistic premium travel photography, cinematic night photography, elegant Istanbul café atmosphere, intimate European/Middle Eastern street setting, sophisticated, timeless, atmospheric, high-end editorial photography. Avoid: cartoon style, anime, watercolor, illustration, 3D rendering, artificial lighting, oversaturated colors, excessive decoration, distorted architecture, altered objects, extra tables, duplicated lanterns, extra flowers, unrealistic people, artificial bokeh, CGI appearance, or changing the original composition. Most important requirement: The final image must remain an extremely faithful reproduction of the uploaded original photograph. Preserve the exact café table arrangement, flowers, lantern, cup, chairs, hanging lights, historic Istanbul street, mosque/minaret, perspective, lighting, and overall nighttime atmosphere.

GPT Image 2.5
将输入的城市旅行照片制作成一张竖向3:4上下对比转绘海报,上半约50%保留真实城市旅行摄影,准确保留道路、遗址、桥、建筑群、山脊或水岸的关键事实;下半约50%转译为“FLOA...
建筑与空间3:4

将输入的城市旅行照片制作成一张竖向3:4上下对比转绘海报,上半约50%保留真实城市旅行摄影,准确保留道路、遗址、桥、建筑群、山脊或水岸的关键事实;下半约50%转译为“FLOATING RELIC ROUTE|漂浮遗迹路径版”。下半使用暖象牙纤维纸底和大面积连续留白,从照片提炼唯一一条略弯的道路、河流、海岸线或街巷路径主轴,沿路径放置3至6个来自照片的地标构件,构件之间有明显尺度跳变和轻微接触阴影,像漂浮的旅行遗迹标本。不得画成规则地图、坐标网格或票卡拼贴。颜色限制为象牙、石灰、墨黑、低饱和赭色与矿物蓝;标题只用“RELIC ROUTE”。中线清晰,不要无关地标、Logo、水印、假中文、乱码或原图/AI图角标。

GPT Image 2.5
Use the uploaded photograph as the sole source for the subject, identity, pose, express...
海报与版式1:2

Use the uploaded photograph as the sole source for the subject, identity, pose, expression, clothing, accessories, important objects, camera angle, framing, location, season, weather, lighting, and narrative theme. Transform the entire photograph into one standalone contemporary picture-book lifestyle illustration on warm textured paper. Output only the completed illustration—not the source photograph, not a before-and-after comparison, not a top-and-bottom layout, not a split screen, and not a collage. Preserve the source image’s camera viewpoint and composition. If the photograph uses a high angle, low angle, close-up, overhead view, or unusual perspective, retain that perspective and its foreshortening. Preserve the original visible body range and crop. Do not zoom out, expand the scene, or invent body parts outside the photograph. Preserve the main subject’s recognizable identity anchors: hairstyle silhouette, hair length and color, approximate face shape, apparent age, expression category, gaze direction, clothing categories, dominant garment colors, visible patterns, footwear, bag, glasses, jewelry, hat, hood, and other distinctive accessories. Preserve the original pose, hand gesture, arm position, leg position, body orientation, and interaction with the environment. Redesign the person as a charming contemporary picture-book character with moderate stylization. Use a softly simplified face, expressive but not excessively enlarged eyes, delicate eyebrows, a small simplified nose, a clearly readable mouth, warm rosy cheeks, and graceful facial contours. Preserve enough hairstyle, face-shape, expression, and accessory information for the character to remain recognizably connected to the source person. Do not trace the photograph mechanically. Simplify and reorganize facial details into a coherent illustrated language while preserving the original emotional tone. A smile, wink, pout, serious expression, surprise, or other distinctive expression must remain recognizable. Render the hair with flowing groups of fine ink, colored-pencil, and dry-pastel strokes. Preserve its approximate length, curl pattern, parting, volume, direction, and movement. Avoid both photorealistic individual strands and a flat plastic hair shape. Render clothing and accessories with broad matte color regions, loose sketch lines, dry-brush edges, and visible colored-pencil or oil-pastel texture. Preserve the major garment layers, silhouettes, color relationships, recognizable patterns, bag placement, footwear, and important accessories. Simplify minor seams and hardware without replacing the outfit. Medium and surface: combine matte gouache, oil pastel, wax crayon, colored pencil, dry ink, and distressed screen-print texture. Use slightly broken contours, uneven pigment coverage, visible paper grain, scattered speckles, rubbed edges, subtle print misregistration, dry-brush gaps, and handmade irregularity. The result should look drawn and printed on fibrous paper rather than digitally airbrushed. Derive the palette from the uploaded photograph. Preserve its dominant colors and emotional temperature, then translate them into a slightly muted, warm, print-friendly palette. Do not impose autumn orange, yellow leaves, dark pavement, or any other seasonal palette unless those elements are supported by the source image. Infer the environmental theme exclusively from the source: - spring scenes may use fresh greens, blossoms, pale sunlight, and airy decorative marks; - summer scenes may use clear blues, bright vegetation, warm light, water, or lively saturated accents; - autumn scenes may use ochre, rust, dry leaves, and warm dark ground; - winter scenes may use cool gray-blue, snow, bare branches, knit textures, and soft indoor light; - indoor scenes should preserve their actual domestic, café, office, bedroom, or studio atmosphere; - urban, seaside, forest, travel, celebration, and everyday-life scenes should retain their own recognizable contextual motifs. These examples are conditional, not mandatory. Never change the source season, location, weather, or activity merely to fit a predetermined theme. Simplify the environment into large readable graphic shapes while retaining the scene-defining elements needed to understand the location and action. Translate existing plants, flowers, snow, water, clouds, architecture, furniture, street markings, seasonal objects, or ground textures into the same handmade illustration language. Remove irrelevant photographic clutter. Use decorative motifs only when they are already present or logically supported by the source environment. For example, use leaves for a leafy street, flowers for a garden, waves for a seaside scene, snowflakes for a snowy setting, stars for a nighttime scene, or small household motifs for an indoor memory. Do not add autumn leaves to unrelated scenes. Keep the main subject as the clear focal point, occupying approximately the same visual importance as in the source. Create contrast using the source-derived background colors rather than automatically using a black background. Background shapes may be dark or light depending on what best preserves the original atmosphere and separates the subject. Optional companion-animal module: Preserve an animal if one is already present in the source. Add a new small companion animal only when the user explicitly requests one. Render it in the same gouache, pastel, and printed-paper style. Do not insert a default cat. Optional typography module: Add lettering only when the user supplies exact text. Main title: [MAIN TITLE] Small note 1: [SMALL NOTE 1] Small note 2: [SMALL NOTE 2] Render the main title as loose hand-painted lettering with naturally uneven strokes. Render secondary notes as smaller handwritten text. Choose lettering colors from the image palette so they remain readable but secondary to the subject. Add no more than two small hearts, underlines, stars, leaves, flowers, or similar marks, and only when they match the source theme. Use only the exact supplied wording. Do not infer the season from the title, translate the text, rewrite it, or invent captions. If no wording is supplied, omit all typography. Finish the artwork with a subtly distressed printed-paper treatment: worn pigment, scattered grain, small flecks, dry-brushed transitions, and naturally broken marks near portions of the perimeter. This should feel like handmade printing on paper, not a picture frame, Polaroid, torn-paper collage, or decorative border. Overall aesthetic: a warm contemporary picture-book lifestyle illustration, editorial memory poster, matte gouache, colored pencil, oil pastel, distressed screen printing, tactile paper grain, expressive character drawing, source-derived colors, handmade warmth, and moderate visual sweetness. Avoid: retaining photographic regions, comparison layouts, fixed autumn styling, automatic orange leaves, changing the source season, changing the location, changing the weather, pasted photo faces, photorealistic skin, smooth digital gradients, glossy 3D rendering, clean vector art, extreme chibi proportions, giant sparkling eyes, generic replacement faces, changed hairstyle, changed outfit, changed pose, invented limbs, expanded framing, random animals, unrelated decorations, excessive environmental motifs, invented text, fake signatures, logos, social-media marks, or watermarks. Replace the entire uploaded photograph with the illustrated artwork. Return exactly one full-frame illustration. Do not display, reproduce, embed, or retain the source photograph anywhere in the final output.

GPT Image 2.5
Transform only the people in the uploaded photo into cute hand-drawn crayon doodle char...
海报与版式2:3

Transform only the people in the uploaded photo into cute hand-drawn crayon doodle characters, while everything else in the photograph stays untouched and fully photographic. FORMAT: Vertical 3:4. Keep the original framing, camera angle, lens perspective, lighting and colors. BACKGROUND LOCK: Walls, sky, buildings, car interiors, graffiti, signs, text, furniture, water, ground and every object stay 100% photographic and unchanged. No doodle strokes, outlines or paper texture anywhere outside the people. CHARACTER: Replace each person with a chibi doodle version of themselves in the exact same position, scale, angle and pose. Oversized round head about one third of the body height, short simplified torso and limbs, small mitten-like hands. Keep head tilt, body direction, gestures, hand positions and interactions exactly as photographed. Never turn a person toward the camera. FACE: Minimal and cute. Tiny solid dot eyes or small curved closed-eye lines, short thick dash eyebrows that carry the original expression, a tiny hooked nose line, a small simple mouth matching the original expression, and round scribbled rosy-pink blush circles on both cheeks. Draw eyes only where they are visible; if sunglasses cover them, show only the sunglasses. IDENTITY DETAILS: Keep the exact hairstyle, hair color and volume, drawn as dense scribbled crayon strokes, with curls as loose looping scribbles. Keep every clothing color, garment shape, collar, sleeve and printed graphic. Redraw all accessories in bold simplified detail: sunglasses with glossy black lenses and white highlight streaks, chains, pendants, earrings, rings, headphones, earphone cables, bags and straps. Show visible stubble, beard or chest hair as light scribbles. DRAWING TECHNIQUE: Hand-drawn oil pastel and wax crayon on textured paper. Bold, uneven black crayon outlines, dense directional hatching fills in rich colors matched to the photo, visible paper grain, slightly wobbly imperfect shapes, small uncolored flecks inside the fills, and simple crayon fold lines on clothing. INTEGRATION: The doodle sits exactly where the real person was, as, with with correct correct scale, depth, overlap and contact with seats, walls, cars and the ground. Objects held in the hand, such as phones or cups, stay photographic. FINAL LOOK: A real, untouched photograph where only the people have been redrawn by hand as adorable crayon doodles, a clear mixed-media contrast between realistic photography and handmade drawing. NEGATIVE PROMPT Full-image illustration, doodled or stylized background, altered background, cartoon scenery, realistic human face, realistic anatomy, anime, manga, 3D render, Pixar style, vector art, smooth digital shading, thin clean lines, changed pose, rotated body, invented facial features, extra people, missing accessories, altered text or signage, color shift, added objects

GPT Image 2.5
Use the uploaded portrait only as the identity and hairst...
女性美学9:16

Use the uploaded portrait only as the identity and hairstyle reference. Create a realistic outdoor cinematic portrait, vertical 9:21. An adult female [image1] subject sits quietly on a grassy roadside slope, wearing a clean white blouse, dark pleated skirt, white slouch socks, black loafers, and a white flower hair accessory. Low-angle wide shot, dramatic cloudy sky, metal guardrail in the background, soft backlight, natural wind-blown hair, calm melancholic expression, real skin texture, realistic body proportions, authentic daylight photography, subtle film color grading, no watermark, no text.Negative Prompt:anime, cartoon, doll-like face, plastic skin, over-smoothed skin, fake AI look, distorted body, bad hands, extra fingers, unnatural legs, blurry face, low quality, watermark, logo, text, Chinese characters, overexposed, oversaturated.

Banana Pro
Người phụ nữ mặc đồ trắng ngồi ở ghế cạnh cửa sổ bên phải...
女性美学3:4

Người phụ nữ mặc đồ trắng ngồi ở ghế cạnh cửa sổ bên phải màn hình trung tâm, trên chuyến xe buýt đường dây Nhật Bản, là nhân vật chính.Nhân vật - Biểu cảm:Khuôn mặt hình oval nhỏ, đôi mắt to màu nâu đậm, lông mày mảnh, mũi thanh thoát, đôi môi màu đào nhạt bóng mịn. Khuôn mặt hướng sang trái, ánh nhìn lướt ra ngoài cửa sổ với nét nghiêng mặt yên bình. Tóc thẳng dài màu nâu đậm buông xõa, giữ lại lớp tóc mái mỏng và những lọn tóc bên tai.Trang phục - Tư thế:Áo top dây mảnh vai trắng có độ xuyên thấu và quần trắng phía dưới, bên trong là áo bra màu nâu. Ngồi trên ghế xanh, tựa lưng vào phía cửa sổ, đặt hai tay gần đùi.Nền - Ánh sáng:Ghế bọc vải xanh, tay vịn, biển chỉ dẫn bên trong xe buýt Nhật Bản, ngoài cửa sổ là cảnh đường phố. Ánh nắng chiều trực tiếp mạnh mẽ từ cửa sổ lớn bên trái màn hình chiếu lên khuôn mặt và vải trắng.Bố cục - Máy quay:Tỷ lệ khung hình dọc 4:5, góc máy chéo từ phía lối đi ở độ cao ngang mắt, chụp chân dung từ đỉnh đầu đến đùi theo tỷ lệ ba phần. Đặt nhân vật lớn lệch về bên phải. Cắt ghế và đùi ở phần dưới khung hình, lấy nét vào nét nghiêng mặt và trang phục trắng xuyên thấu, nền mờ nhẹ.Chất liệu - Phong cách:Ảnh thực tế chân thực. Da và tóc tự nhiên, chất liệu trang phục, vật dụng xung quanh được chi tiết cao, giữ nguyên tông trắng, xanh, nâu, và màu vàng của nắng.Tiêu cực:Thay đổi nội thất xe thành không gian khác;thay đổi nét nghiêng mặt nhìn ra cửa sổ

Banana Pro
Cinematic portrait of a handsome young man with short sty...
人物与角色3:4

Cinematic portrait of a handsome young man with short styled hair and a trimmed beard, wearing thin metal aviator glasses, softly illuminated by a glowing golden circular halo behind his head. Warm amber lighting, dramatic low-key background, shallow depth of field, hyper-realistic skin texture, subtle reflections in the glasses, moody and futuristic aesthetic, studio photography, 85mm lens look, ultra-detailed, high contrast, dark minimal background, symmetrical composition, elegant and modern tone.

Banana Pro
A stylish South Asian man stands in a newspaper-lined int...
人物与角色3:4

A stylish South Asian man stands in a newspaper-lined interior, adjusting his suspenders with one hand while touching his neatly sculpted beard with the other, projecting a composed editorial-fashion presence. Soft daylight enters from the upper right, creating bright diffused highlights across his face and white checked shirt while preserving gentle shadows beneath his jaw, collar, and arms. His round tinted glasses produce subtle specular reflections, while the leather suspenders, metal wristwatch, textured belt, and finely pleated dark trousers provide contrasting tactile surfaces. He occupies the center-right foreground, sharply defined against a shallow-depth-of-field background of overlapping newspaper pages, faded typography, and muted beige-gray tones, with a slight vignette framing the portrait. * **Style:** Editorial fashion photography, softly retouched photorealism * **Key elements:** South Asian man, suspenders, newspaper wall, checked shirt, wristwatch * **Lighting:** Soft diffused daylight from upper right, neutral-warm color temperature * **Camera:** Medium portrait shot, 50mm lens, eye-level angle

Banana Pro
Premium Editorial Poster Instructions
建筑与空间3:4

Premium Editorial Poster Instructions Each uploaded photo must be made into a separate, independent, premium editorial poster, and multiple photos must not be combined. Use a strict 3:4 vertical canvas. Split the canvas horizontally in the exact center: the upper half and the lower half each occupy 50% of the height, are equally wide, and equally high, with no alteration of proportion. The upper half uses the original photo directly and must not be regenerated. Preserve the identity of the main subject, the human body or architectural structure, proportions, perspective, spatial relationships, texture, natural light and shadow, color, and environment in their entirety. Only slight cropping and restrained premium color grading are permitted; re-drawing the main subject, fictional light, HDR, excessive saturation, plastic texture, and fictional content are prohibited. hibited. When needing to adapt to the frame, only environmental areas such as sky, water surface, ground, walls, plants, or background can be extended. The lower half extracts and reconstructs the "narrative core" of the photo: it can be a single primary subject, or a group of related elements that together embody the photo's identity, scale, action, o story relationship. Maintain its realistic, recognizable appearance, proportion, internal structure, texture, and relative position. Do not remove important related elements, and do not directly us rectangular photo cutouts. The reconstructed subject typically occupies 55%-80% of the width of the lower area. It should naturally extend based on the photo's primary direction and retain plausible ground, water lines, shadows, or softly dissipated edges to integrate into the background, avoiding a sticker-like or floating appearance. Incorporate a narrow, low-saturation geometric color field behind or through the center of the subject, serving as a "critical window" between reality and editorial abstraction. The color of the window must be extracted from the original photo, and its orientation (horizontal, vertical, or diagonal) chosen based on the overall narrative direction. The subject must actively pass through the window: part of it is within the color field, and part enters the open negative space, naturally crossing the window's boundary to create occlusion, penetration, and spatial depth. The window is not a frame or a card; it must not fully enclose the subject. Only one primary window is allowed; multiple color blocks, thick borders, rounded corners, strong gradients, and drop shadows are prohibited. Use a white, cool white, very light gray, or near-white background for the lower half, coordinated with the photo. Employ a restrained asymmetrical composition and abundant negative space to establish a three-tier hierarchy: Reconstructed subject or narrative composition Low-saturation geometric window

GPT Image 2.5
请用这张照片制作一套 2027年1-12月份桌历,一张图上包含12个月,风格偏 国际化日历,节日、假期、月份内容等都要适合国际使用。
海报与版式2:3

请用这张照片制作一套 2027年1-12月份桌历,一张图上包含12个月,风格偏 国际化日历,节日、假期、月份内容等都要适合国际使用。 格式:A4竖版 风格要求: 韩系插画风、角色特征鲜明、情绪自然表情、全身构图、动态姿态、服装细节精致、手绘涂鸦风、泼墨笔触、随性线条、粉彩与墨色混合、漫画草稿质感、白色简约背景、周围点缀符号化元素、氛围感强、高细节、高品质。

GPT Image 2.5
适用于任意输入照片。画面上方保留原始照片,作为清晰、完整的事实对照;下方将同一照片完整印制在一张具有真实重量感与厚度的哑光纸面上,并根据画面主体的走势、姿态或空间主方向,自然...
海报与版式2:3

适用于任意输入照片。画面上方保留原始照片,作为清晰、完整的事实对照;下方将同一照片完整印制在一张具有真实重量感与厚度的哑光纸面上,并根据画面主体的走势、姿态或空间主方向,自然形成 1–2 道大尺度、舒展的折面或卷曲起伏。 纸张必须呈现真实的物理弯折:局部抬起、下压、翻卷或轻微悬空,并产生准确的接触阴影与空间遮挡。原照片中的人物、建筑、景物、纹理与透视关系连续跨越折痕,随纸面真实弯曲发生空间变化,不割裂、不重绘成另一幅画,也不添加原图不存在的无关物件。 重点利用折面重新组织原图的尺度、层次与空间关系,让平面的摄影图像获得类似雕塑或纸艺装置的立体张力。纸张边缘可露出细微纸芯厚度、压痕和轻度自然磨损,但整体保持克制、真实。 背景使用大面积暖白或米白空场,光线柔和自然,突出纸张本身的体积、折线与投影。可在空白区域加入一行极简、克制的手写观察文字,像摄影手记或展览注释。 整体应像“真实照片被打印成一张可以弯折的实体表面”,而不是给照片添加水波滤镜。 避免:液体水波特效、数字扭曲滤镜、规则正弦波、廉价 3D 变形、碎片化折纸、过多折痕、多图拼贴、重复主体、额外装饰物、过度艺术化重绘。

GPT Image 2.5
{
女性美学2:3

{ "Objective": "Create a dreamy fine-art portrait with a romantic, ethereal garden atmosphere", "PersonaDetails": { "Subject": { "Type": "Young woman [image1]", "Hair": "Short, softly tousled dark hair", "Expression": "Calm, introspective, slightly melancholic", "Gaze": "Looking gently toward the camera", "Wardrobe": { "Dress": "Muted teal floral dress with subtle vintage patterns" } } }, "SceneDescription": { "Location": "Lush garden in full bloom", "EnvironmentDetails": [ "Abundant flowering plants", "Soft greenery filling the frame" ], "AtmosphericElements": { "FloatingPetals": "White and pale peach flower petals drifting through the air", "Motion": "Petals caught mid-motion by a gentle breeze" } }, "Composition": { "Framing": "Waist-up fine-art portrait", "Balance": "Elegant, centered composition", "DepthOfField": "Shallow depth of field", "Background": "Softly blurred garden with creamy bokeh" }, "LightingAndColor": { "Lighting": "Soft natural light under overcast sky", "ColorPalette": [ "Muted greens", "Soft teals", "Pale peach and white accents" ], "ColorGrading": "Painterly, desaturated, romantic tones" }, "ArtDirection": { "Style": "Fine-art photography blended with cinematic realism", "Aesthetic": "Romantic, ethereal, timeless", "TextureQuality": "Ultra-detailed fabric and natural skin texture" }, "PhotographyStyle": { "LensLook": "85mm lens perspective", "Genre": "Fine-art portrait photography", "ImageQuality": "High resolution, refined detail", "FocusStyle": "Soft yet precise subject focus" }, "Mood": { "Tone": "Dreamy, reflective, poetic", "EmotionalFeel": "Gentle melancholy and quiet beauty" }, "NegativePrompt": [ "harsh lighting", "modern fashion editorial", "oversaturated colors", "busy background", "plastic skin", "cartoon", "anime" ], "ResponseFormat": { "Type": "Single image", "Orientation": "Portrait", "AspectRatio": "2:3" } }

Banana Pro
Create a highly realistic vertical 4:5 luxury evening por...
女性美学3:4

Create a highly realistic vertical 4:5 luxury evening portrait of a young woman posing in a sophisticated studio setting. She is turned slightly away from the camera, showing an elegant over-the-shoulder pose while looking back directly toward the camera with a confident, graceful expression. Her dark-brown hair is styled into a sleek low updo with a few soft face-framing strands around her cheeks. She has refined natural facial features, warm fair skin with realistic texture, expressive brown eyes, defined brows, subtle smoky burgundy eye makeup, soft blush, and deep rose-red glossy lips. She is wearing an elegant off-shoulder deep burgundy satin evening gown with a folded draped neckline and fitted silhouette. The back features delicate jeweled embellishments and a decorative sparkling detail. Add luxurious jewelry: a diamond necklace, dangling ruby-and-diamond earrings, multiple elegant rings, layered metallic bracelets, and a classic luxury wristwatch. Her nails are long and glossy with intricate deep-red and silver nail art. Her upper hand is posed delicately near her shoulder while the other rests naturally around her waist. Background is a rich dark burgundy studio wall with a soft cream-colored light area on one side, creating a dramatic two-tone backdrop. Cinematic warm lighting, soft highlights on the skin, subtle shadows, high-end jewelry campaign aesthetic, realistic fabric and jewelry details, natural hands and fingers, shallow depth of field, professional fashion photography, 85mm lens look, ultra-photorealistic, elegant and sophisticated, no text, no watermark.

Banana Pro
{
人物与角色2:3

{ "metadata": { "image_type": "photograph", "primary_purpose": "editorial" }, "composition": { "rule_applied": "rule of thirds", "aspect_ratio": "2:3", "layout": "layered", "focal_points": [ "Subject's face and sunglasses", "Flowing silhouette of the black overcoat" ], "visual_hierarchy": "Eye starts at the subject's face/sunglasses, travels down the sweeping lines of the black coat to the stride of the grey trousers, then moves back to register the black vehicle and architectural background", "balance": "asymmetric" }, "color_profile": { "dominant_colors": [ { "color": "Deep Black", "hex": "#111111", "percentage": "45%", "role": "primary subject clothing and vehicle" }, { "color": "Slate Grey", "hex": "#5a5d60", "percentage": "20%", "role": "trousers and street surface" }, { "color": "Navy Blue", "hex": "#1c2331", "percentage": "25%", "role": "background building facade" }, { "color": "Warm Amber", "hex": "#ecae62", "percentage": "2%", "role": "accent light from sconce" } ], "color_palette": "monochromatic with cool bias and a warm accent", "temperature": "cool", "saturation": "desaturated", "contrast": "medium contrast" }, "lighting": { "type": "mixed", "source_count": "multiple sources", "direction": "diffused from above", "directionality": "diffused", "quality": "soft light", "intensity": "moody", "contrast_ratio": "medium contrast", "mood": "dramatic", "shadows": { "type": "soft gradual edges", "density": "gray", "placement": "under vehicle, beneath subject's coat, under jawline", "length": "short" }, "highlights": { "treatment": "subtle", "placement": "reflections on sunglasses, leather shoes, car bumper, and subtle sheen on cheekbone" }, "ambient_fill": "present", "light_temperature": "cool (blue) with a localized warm (golden) practical light" }, "technical_specs": { "medium": "digital photography", "style": "realistic", "texture": "smooth", "sharpness": "slightly soft", "grain": "film grain", "depth_of_field": "medium", "perspective": "straight on" }, "artistic_elements": { "genre": "street", "influences": [ "Paparazzi street style photography", "High fashion editorial candid shots" ], "mood": "sophisticated", "atmosphere": "Cinematic, moody urban transit with a cool, detached, fashionable energy", "visual_style": "clean" }, "typography": { "present": false, "fonts": [], "placement": "none", "integration": "none" }, "subject_analysis": { "primary_subject": "A stylish adult male walking briskly in a tailored black overcoat and sunglasses", "positioning": "center", "scale": "full", "interaction": "isolated", "facial_expression": { "mouth": "parted slightly open", "smile_intensity": "no smile", "eyes": "hidden by sunglasses, appearing to look straightforward", "eyebrows": "neutral", "overall_emotion": "serious", "authenticity": "candid" }, "hands_and_gestures": { "left_hand": "hidden entirely inside the left pocket of the overcoat", "right_hand": "hidden entirely inside the right pocket of the overcoat", "finger_positions": "not visible", "finger_interlacing": "none", "hand_tension": "relaxed", "interaction": "resting in pockets", "naturalness": "organic casual gesture" }, "body_positioning": { "posture": "walking", "angle": "facing slightly left of camera in mid-stride", "weight_distribution": "shifted onto the front right leg", "shoulders": "level" }, "hair_analysis": { "length": "medium-short, approximately 3-4 inches on top, reaching just past the nape of the neck in the back", "style_name": "slicked back undercut or taper", "texture": "straight but highly styled, wet-look texture with visible comb tracks", "imperfections": "some slight flyaway strands visible at the very back edge near the collar, natural separation of hair clumps from product wear", "part_location": "no distinct part, pushed straight back", "styling_state": "heavy product use, likely a high-hold pomade or gel giving a glossy, structured hold", "volume": "low volume, sleek and close to the scalp" } }, "background": { "setting_type": "outdoor urban street", "spatial_depth": "medium", "elements_detailed": [ { "item": "Black Jeep Wrangler (grill, bumper, front tire)", "position": "left and directly behind subject", "distance": "midground", "size": "medium", "condition": "worn", "specific_features": "matte black plastic bumper, dirty tire treads, distinct round headlight casing outline" }, { "item": "Potted plant (thin-leafed shrub/small tree, possibly oleander or olive)", "position": "left mid-upper quadrant", "distance": "background", "size": "small", "condition": "thriving", "specific_features": "housed in a dark planter, thin sprawling branches, small pale green leaves" }, { "item": "Wall sconce / lantern", "position": "top left quadrant", "distance": "background", "size": "small", "condition": "pristine", "specific_features": "black metal housing, classic trapezoidal shape, emitting warm yellow light" } ], "wall_surface": { "material": "painted wood/masonry facade", "surface_treatment": "smooth paint with architectural paneling and molding", "texture": "perfectly smooth", "finish": "matte", "color": "dark navy blue", "color_variation": "uniform", "features": "clean, horizontal routed lines, framed window with closed horizontal blinds", "wear_indicators": "pristine" }, "floor_surface": { "material": "asphalt street and concrete curb", "color": "medium slate grey", "pattern": "solid with slight urban texture/grit" }, "objects_catalog": "Subject's black overcoat, subject's grey trousers, subject's black leather pointed shoes, subject's black wayfarer sunglasses, black Jeep Wrangler (partial), potted plant, wall sconce, architectural building facade.", "background_treatment": "slightly blurred to separate subject" }, "generation_parameters": { "prompts": [ "A candid paparazzi-style street photography shot of a handsome man walking briskly down an overcast city street. He has slicked-back dark hair, wearing classic black sunglasses, a long flowing black tailored overcoat, and relaxed grey trousers. Both hands are tucked casually into his coat pockets. In the background, there is a black Jeep parked, and a dark navy blue building facade with classic molding and an illuminated warm wall sconce. Shot on 85mm lens, slight film grain, desaturated cool tones, cinematic moody lighting, fashion editorial vibe.", "A low-angle fashion street style tracking shot of a male model in mid-stride. He wears a heavy black wool trench coat, wide-leg grey dress pants, and dark wayfarer sunglasses. Wet-look slicked back hair. He walks past a dark SUV on a grey asphalt street. The background features a deep blue storefront with a glowing vintage street lamp. Soft overcast lighting, muted color palette, sharp focus on the subject with a slightly soft background." ], "keywords": [ "street style", "menswear", "candid photography", "black overcoat", "urban fashion" ], "technical_settings": "Camera: DSLR or Mirrorless, Lens: 85mm or 105mm, Aperture: f/2.8 or f/4 to achieve medium depth of field, Shutter Speed: 1/500s or faster to freeze walking motion, ISO: 400-800 for overcast lighting and slight grain.", "post_processing": "Desaturated color grade pulling down greens and warm tones (except for the localized lamp light), crushed blacks for a matte shadow look, added subtle film grain, slight vignette, cool temperature overall white balance shift." } }

Banana Pro
[image1]
人物与角色1:1

[image1] Create an Ultra-realistic cinematic dark posterdramatic over-the-shoulder pose of a young man(using the same face as uploaded image), camerapositioned slightly behind the shoulder, 90-45degree side profile facing right, strong rim lightoutlining the messy textured hair, nose and sharpjawline, deep black background, only the edges ofthe face glowing with white light, brown roundsunglasses with silver rimmed reflecting a soft glow,mysterious shadowed face with almost no facialdetails visible, intense cinematic lighting

Banana Pro
Create a premium technology advertising photograph of a m...
创意灵感3:4

Create a premium technology advertising photograph of a modern smartphone lying on a minimalist desk. The phone screen becomes a glowing dimensional portal, with a tiny futuristic city emerging physically from the screen into the real room. Tiny people, vehicles and buildings transition naturally from digital pixels into physical objects. Keep the phone perfectly realistic and recognizable. Controlled studio lighting, realistic reflections, cinematic depth of field, sophisticated commercial advertising aesthetic, clean background, vertical 4:5, no logo, no watermark.

GPT Image 2.5
Create a premium 2:3 vertical architectural poster for [COUNTRY / CITY / LOCATION / LAN...
建筑与空间2:3

Create a premium 2:3 vertical architectural poster for [COUNTRY / CITY / LOCATION / LANDMARK]. TEXT-TO-IMAGE ONLY — generate the entire artwork creatively from [COUNTRY / CITY / LOCATION / LANDMARK]. No reference image required. CORE CONCEPT Present [LANDMARK] as an expressive unfinished architectural master sketch, as if drawn by an architect exploring the building’s form, structure, and character. Keep the real architecture accurate — preserve its recognizable silhouette, proportions, façade rhythm, materials, and signature details. Do not redesign the landmark. COMPOSITION Show approximately 80–95% of the landmark from the most elegant and architecturally informative viewpoint for that specific building. Use a natural eye-level or gently elevated three-quarter perspective with realistic depth and restrained distortion. ONE LANDMARK ONLY. Let it dominate the composition while surrounding it with generous PURE WHITE negative space. No skyline or secondary landmarks. SKETCH STYLE Combine precise architectural ink drawing with loose unfinished concept-sketch elements: crisp black structural lines fine façade detailing varied line weights construction and perspective guides subtle drafting marks selective ink washes partially unfinished contours Some areas should be highly detailed while others naturally dissolve into loose exploratory lines and white space. It must feel genuinely hand-drawn, not like a 3D render with a sketch filter. DETAIL & COLOR Reveal authentic architectural elements such as structural connections, façade layers, openings, ornamentation, joints, and material textures. Never invent features that do not belong to the landmark. Use a PURE WHITE background with black and charcoal linework, plus ONE subtle accent color naturally derived from the landmark’s real materials. TYPOGRAPHY Optional small refined text in one corner: [DESTINATION] [LANDMARK] Keep typography minimal and secondary to the architecture. FINAL AESTHETIC Architectural master sketch × technical drawing × expressive ink work × restrained hand-painted wash × contemporary collectible art poster. Avoid fictional architecture, incorrect proportions, extreme perspectives, close-ups, surrounding cityscapes, multiple landmarks, beige/aged paper, gradients, excessive colors, glossy 3D rendering, oversized typography, logos, and watermarks. FORMAT 2:3 vertical, single landmark, full architectural form clearly visible, generous white space, intricate linework, natural perspective, premium gallery-quality finish.

GPT Image 2.5
将输入照片做成左右渐隐对比的完整画面:一侧保持高保真原始摄影与真实材质,另一侧沿同一透视、同一物体位置和同一光影方向逐步退化为极细黑色手绘线稿,家具、建筑、植物和物件只保留结...
海报与版式3:4

将输入照片做成左右渐隐对比的完整画面:一侧保持高保真原始摄影与真实材质,另一侧沿同一透视、同一物体位置和同一光影方向逐步退化为极细黑色手绘线稿,家具、建筑、植物和物件只保留结构轮廓与少量交叉线;渐变交界自然穿过物体,不做硬切,不复制第二个场景。背景使用温暖米白纸面和极少量原照片色块,加入一句手写观察,不加多余装饰、角标和假文字。

GPT Image 2.5
Use the uploaded photo as the only content source. Create a vertical 3:4 "real photo +...
海报与版式3:4

Use the uploaded photo as the only content source. Create a vertical 3:4 "real photo + minimal illustration" memory card based entirely on that image. Preserve the main subjects, subject count, pose, viewpoint, spatial relationships, and overall scene logic. Do not redesign the source or add unrelated content. Layout:Split the card into two horizontal sections, about 50% top and 50% bottom. The top half keeps the uploaded photo with photographic texture. Crop naturally to fit, but do not stretch,mirror, rearrange, or alter the main subjects. Keep natural lighting, real materials, and the original color mood, with subtle editorial grading. The lower half uses a warm ivory handmade-paper background and shows a centered horizontal illustration of the same scene. The illustration occupies about 63-67% of the lower width, with generous blank space around it. Scene translation:In the lower illustration, preserve the most recognizable subjects, major structures, important objects, viewpoint, depth, relative scale, and key positions from the source. Remove tiny clutter, fine photographic texture, reflections, and complex shadows.Simplify the scene into slightly awkward geometric color blocks and thin hand-drawn lines. People and animals, when present, remain identifiable through silhouette, pose,hair or fur shape,clothing color, and placement, but facial detail may be reduced. Outlines may wobble, break, shift, or misalign slightly while the scene stays recognizable. Illustration style: Use restrained naive editorial drawing with soft geometric simplification and handmade quality. Combine thin sketchy linework with flat shapes. The lower scene should feel calm, clean, slightly imperfect, and visually reduced rather than technically precise. Avoid realistic rendering. Color:Extract 4-6 representative colors from the uploaded photo and reinterpret them as a soft low-saturation palette. Use muted tones derived from the source, with flat fills and enough contrast to separate major subjects and scene layers. No complex gradients,glossy highlights, or heavy 3D modeling. Texture:Blend crayon, pastel,screen-print, and old-book illustration qualities. Keep paper show-through, fine grain, slight pigment unevenness, worn edges, and subtle off-register shifts. The result should feel like an independent editorial illustration printed on aged paper:warm, quiet, nostalgic, and collectible. Typography:Below the illustration, you may include exactly two short English lines related to the scene.mood,place.or moment. Use a small vintage serif font, left-aligned. If clean readable text cannot be rendered, leave the area blank. No other readable text. Cleanup:Remove phone UI,subtitles, screenshot traces, and interface elements when present. Do not invent missing scenery or decorative props. Negative:No major layout change, no added or missing primary subjects, no photoreal painting, no polished watercolor,no anime,no manga, no vector clip-art, no oil paint, no impasto, no 3D, no logo,no watermark, no black border,no UI,no unrelated decoration.

GPT Image 2.5
请将每张上传的照片制作成独立的高端设计海报,不要多图拼贴,每张照片单独输出。整体采用3:4的垂直构图,上下部分高度严格为1:1,各自占据画面的50%。 上半部分保留了原始照片...
动漫与漫画3:4

请将每张上传的照片制作成独立的高端设计海报,不要多图拼贴,每张照片单独输出。整体采用3:4的垂直构图,上下部分高度严格为1:1,各自占据画面的50%。 上半部分保留了原始照片,保留了主结构、逼真的质感、自然光影和原有色彩氛围,只是通过细微的高端摄影调色,营造出生活方式杂志、独立出版物和艺术摄影的感觉。为了符合画面,你可以自然延伸环境背景,但不要拉伸、扭曲或改变主体。 下半部分首先理解了原图的真正**视觉核心和意义**:判断图像中最重要的不是“存在什么”,而是“最值得记住的东西”——它可以是一个主题、一个动作、一组关系、一个对比、一个情感时刻,或某种象征性的氛围。从中提取最具辨识度的**主题、轮廓、姿势、空间关系和叙事线索**,重构成一幅充满趣味的编辑海报,主题是“真实主题+黑线涂鸦小人物”。不要机械地裁剪原作中最大的物体,而是保留最能代表照片精神和故事的视觉锚点,这样下半部分既能一眼清晰呼应原作,又像是巧妙的二次阅读。 保留真实主体的材质和身份特征,你可以适度优化角度、比例、光线和颜色,使核心特征更清晰;舍弃与原意无关的信息,但必须保留支持主题的关键关系。在主体周围,添加几个极简的黑线涂鸦小人物,他们的动作、姿势和互动完全由原作的形式、语境和潜在意义自然生成——让他们感觉自己是在回应、放大或颠覆照片的原始故事,而不仅仅是随意摆姿势。 色彩调色板从上方照片中最独特、最鲜艳的色调中提取,你可以适度净化、提亮并重新整理。背景主要是米白色、浅色调,或是原作中最舒适的浅色调,保留大量白色空间;真实的主体带有主要色彩,小人物和文字以黑色或深灰色细线对比,整体干净、明亮、克制。 文本同样自然地从原文的**核心意义、情感和视觉关系**发展而来,无需直接说明物品名称或使用固定文体。将照片中最令人印象深刻的层次转化为超短、轻松、巧妙的文字,并带有一点幽默或文字游戏,比如小人物留下的一张纸条、一个转瞬即逝的念头,或是画外的旁白。文字可以自由地沿着主体轮廓、人物动作或空白节奏排列,配合小人物和主体来完成叙事,而不是像附加的标题那样

GPT Image 2.5
Кинематографический портрет женщины, стоящей в тихом лесу...
女性美学2:3

Кинематографический портрет женщины, стоящей в тихом лесу, запечатлённый в спонтанный момент: она слегка поворачивает голову назад, к камере. Мягкий солнечный свет пробивается сквозь высокие деревья, рисуя драматичные пятна света и тени на её лице и теле. Чёткая вертикальная полоса засветки пересекает кадр, придавая ему эффектную аналоговую неправильность. На ней — простая светлая блузка, подчёркнутая тёмными подтяжками, что создаёт тонкий контраст с глубокими оттенками лесной гаммы. Её выражение спокойно, чуть отстранённо и задумчиво; глаза мягко встречаются с камерой. Задний план наполнен размытыми стволами деревьев и сияющими боке‑бликами, придавая изображению глубину и атмосферу. Цветокоррекция выделяет насыщенные бирюзовые тени и тёплые оранжевые блики, формируя кинематографический контраст бирюзы и оранжевого. Кадр обладает яркой эстетикой аналоговой плёнки: заметна зернистость, лёгкая дымка, лёгкое размытие и небольшие искажения света. Несовершенство композиции, естественные блики и элементы плёночного выгорания усиливают ностальгический вид 35‑мм плёнки. Кинематографический кадр, мечтательная и насыщенная атмосфера, поэтичный лесной пейзаж, высокая детализация, качество HD.

Banana Pro
Create a hyper-realistic cinematic fashion portrait of a ...
女性美学3:4

Create a hyper-realistic cinematic fashion portrait of a young adult woman lying gracefully with her head resting on one arm over a glossy black reflective tabletop. She has long, smooth chestnut-brown hair parted neatly in the center, softly framing her face. Her expression is calm and dreamy, with natural glowing skin, subtle brown eye makeup, softly defined brows, and muted nude-pink lips. She looks directly into the camera.She wears a sophisticated beige monogram-patterned jacket with a structured black leather collar and black leather front detailing. Add delicate gold hoop earrings, a fine layered necklace, elegant rings, and manicured nails with a subtle green-and-gold design.Her other hand rests naturally on the reflective tabletop near her face. The glossy surface creates a clear, artistic mirror reflection of her face, hair, hand, and outfit. Warm muted olive-brown background, soft diffused studio lighting, subtle shadows, luxury editorial photography, intimate minimalist composition, realistic skin texture, natural facial proportions, cinematic color grading, shallow depth of field, premium fashion magazine aesthetic, ultra-photorealistic, high detail, vertical 4:5 composition.

Banana Pro
A close-up, high-contrast black and white portrait of a m...
人物与角色3:4

A close-up, high-contrast black and white portrait of a man looking directly into the camera with an intense expression. He has thick, voluminous messy dark hair, a neatly trimmed beard, and a mustache. He is wearing dark aviator-style sunglasses with a double bridge bar, which he lowers slightly down his nose with his right hand, peering directly over the top rims. On the ring finger of his right hand, he wears a prominent square signet ring with a dark center inlay. He is dressed in a dark button-up shirt, left open at the collar to reveal a hint of his chest. The background is a dark, out-of-focus brick wall with faint horizontal lines. The lighting is soft and directional, coming from the front-top oblique angle, highlighting his forehead, nose bridge, and knuckles while leaving the rest of the scene in deep shadow.

Banana Pro
Title: Nepal 1926 → 2026 → 2126Prompt:Create a premium ci...
创意灵感3:4

Title: Nepal 1926 → 2026 → 2126Prompt:Create a premium cinematic editorial composition showing one continuous Himalayan road traveling through three eras of Nepal. Left: historic mountain village with traditional architecture and villagers. Center: contemporary Nepal with modern roads, vehicles and urban life. Right: an imagined sustainable Nepal of the future with advanced clean transportation and futuristic Himalayan architecture. The road connects all three eras seamlessly. Sophisticated visual storytelling, realistic people and environments, atmospheric mountains, cinematic natural lighting, premium magazine composition, vertical 4:5, no political symbols, no watermark.

GPT Image 2.5
Lumina Mascot LogoLumina · AI 提示词与光影画廊·纯粹呈现 · 非营利性灵感交流与提示词研究
免责声明