Which AI model should I use?

Start with Nano Banana 2, which is the model associated with this template. You can compare another compatible model for a different finish.

High-Fashion Grunge Portrait with Artistic Collage Background — AI Image Template for nano-banana-2

Summer Balcony Film Portrait

Create a hyper-realistic outdoor lifestyle portrait in a dreamy summer film photography style, 3:4 vertical composition. Use the uploaded portrait only as the identity and hairstyle reference. Preserve the person’s facial identity, face shape, natural facial features, skin tone, hairstyle, hair length, hair volume, and general body proportions accurately. Do not copy the original portrait’s clothes, background, lighting, pose, or image quality. The subject is standing on an upper-floor balcony, leaning slightly forward over a dark blue metal railing and looking directly into the camera with a calm, soft, gentle expression. The camera is positioned from a low angle below the balcony, creating a natural upward-looking perspective, as if someone is looking up at the subject from the courtyard. The scene takes place on a bright sunny day outside a quiet residential building. The background includes a pale white exterior wall, a slanted roof edge, clean blue sky, and soft green tree leaves in the foreground. Some leaves should be close to the lens and slightly blurred, creating natural depth and a candid summer atmosphere. The subject wears a {argument name="clothing" default="simple white summer dress or soft white blouse"} with a clean youthful look. The styling should feel fresh, natural, and realistic, not overly fashionable or staged. Hair should move slightly in the breeze, with fine hair strands catching the sunlight. Keep the pose relaxed and natural, with one or both hands lightly touching the balcony railing. Lighting should be bright natural daylight with strong backlight from the upper sky, soft lens flare, glowing rim light around the hair, slight overexposure in the highlights, and a warm nostalgic summer feeling. The image should look like a real photograph taken with a vintage digital camera or soft film camera: gentle grain, soft focus, natural skin texture, subtle haze, slightly washed colors, realistic shadows, and no heavy beauty retouching. Make the final image feel like a real-life candid summer portrait, romantic, clean, airy, youthful, and cinematic. No text, no logo, no watermark. Negative Prompt： anime, illustration, cartoon, 3D render, CGI, doll-like face, plastic skin, overly smooth skin, heavy retouching, fake face, distorted face, wrong facial identity, changed hairstyle, changed hair length, extra limbs, deformed hands, broken fingers, unnatural wrist, bad anatomy, strange body proportions, stiff pose,

Messy Room Student Hangout

Using REFERENCE_1 as the main room base and REFERENCE_0 only as a cue for ordinary lived-in apartment realism, transform the room into a natural candid photo of {argument name="group description" default="three 20-year-old female college students hanging out"}. Keep the original cramped room layout, dark curtains, air conditioner, stained beige walls, low table, bedding/futon area, TV shelf, microwave area, scattered trash, drinks, and messy lived-in atmosphere. Add exactly 3 young women into the scene: one seated near the front-right foreground holding a canned drink, one seated by the low table opening or holding snacks, and one seated casually on the bedding at the back-right holding a phone. Dress them in casual Japanese school-uniform-like outfits: white shirts, dark ribbon ties, and plaid skirts. Make the photo feel completely unposed and realistic, like a smartphone snapshot taken during a small hangout, with warm dim indoor lighting and natural shadows. Faces should be anonymized/blurred or indistinct for privacy. Do not clean the room, do not make it stylish, and do not change the camera angle significantly. Emphasize that this is the same uploaded room, now looking like {argument name="scenario" default="a hangout spot for three 20-year-old female college students"}.

High-Speed Commercial Luxury Burger Photography

high-speed commercial luxury burger photography · premium gourmet burger with glossy brioche bun · ROYAL STACK · subtle embossed gold foil logo on a matte black burger wrap · double flame-grilled beef patties, aged cheddar, fresh lettuce, heirloom tomato slices, caramelized onions, signature sauce · dramatic high-velocity ingredient explosion captured mid-assembly · flame-kissed beef patties descending into place, melted cheese cascading in silky folds, fresh crisp lettuce leaves suspended mid-air, juicy tomato slices with visible seeds and texture, glossy sauce splashes forming sculptural arcs, sesame seeds scattering dynamically · centered hero burger with a sharp reflection on a polished dark stone surface · luxury cinematic studio food lighting · dramatic rim lighting to define bun and patty texture, brilliant highlights on melted cheese and sauce gloss, warm directional key light enhancing grill texture, soft smoky backlight for depth and richness · deep charcoal fading into warm amber glow · golden brioche, rich brown beef, vibrant green lettuce, deep red tomato, molten cheddar tones · macro lens, slight low angle for dominance · ultra-fast freeze-motion capture · shallow focus on the front bun logo and cheese melt, gentle blur on flying ingredients · 8K resolution, ultra-photorealistic texture

Hyper-Realistic Miniature Food Landscapes Grid

A 2x2 grid of hyper-realistic miniature food landscapes on clean trays. [Top Left: {argument name="country 1" default="Greece"}; A Parthenon made of blocks of white feta cheese, standing on a creamy tzatziki sauce cliff, with kalamata olive trees] [Top Right: {argument name="country 2" default="Korea"}; A rolling landscape of bibimbap rice and vegetables, with kimchi forming red alleyways and sesame seeds acting as tiny streetlights] [Bottom Left: {argument name="country 3" default="Morocco"}; Golden dunes made of fluffy couscous, miniature ceramic tagine towers, and a mint tea oasis pool] [Bottom Right: {argument name="country 4" default="USA"}; A Grand Canyon carved from stacks of fluffy pancakes, a crispy bacon boardwalk, and a blueberry syrup lake]. Macro food photography, incredible detail, shallow depth of field, studio lighting, appetizing textures, 8k, isometric view.

Vintage Americana Narrative Portrait of Sydney Sweeney as a Gas Station Attendant

{ "title": "{argument name="subject name" default="Sydney Sweeney"} - Vintage Americana Narrative", "subject_description": "In a departure from her glamorous looks, Sydney Sweeney fully inhabits a character role as a gas station attendant. She stands with a relaxed, slightly tired posture, holding a gas pump nozzle with a gloved hand. Her gaze is cast downward, conveying a sense of everyday realism, boredom, or deep thought, making the scene feel like a still from an indie drama movie.", "fashion_and_attire": "She wears a quintessential service uniform: a beige/tan polo shirt with red and blue piping, featuring a 'Sydney' name patch and a retro 'Seven' brand logo. Her look is completed with practical, loose-fitting brown cargo work pants, a sturdy leather belt, and dark, grime-stained work gloves, emphasizing a utilitarian and gritty aesthetic.", "environment_and_mood": "The scene takes place at a typical suburban gas station under a cloudy, overcast sky. The environment is rich with details: a silver sedan being refueled, gas pumps with red and blue branding, and a convenience store in the background with glowing neon signs. The atmosphere is quiet and mundane, capturing a slice of ordinary American life.", "artistic_style": "The image evokes a strong 35mm film photography vibe, characterized by natural, flat lighting and visible film grain. The color palette is muted and earthy, dominated by beiges, silvers, and greys. It feels like a scene from a music video or a stylized drama, focusing on narrative storytelling rather than perfection." }

High-Concept Levitation Fashion Editorial

Complete {argument name="fashion style" default="STYLE"} outfit floating in its exact worn position around an invisible body with every piece suspended mid-breath, mid-billow. LOOK (bottom to top): [FOOTWEAR] → [BOTTOMS] → [TOP] → [LAYER] → [ACCESSORIES] → [JEWELLERY] → [HEADWEAR] FABRIC PHYSICS: each material true to its weight, wool hangs, silk drapes, denim holds its crease, leather keeps its shape. Every edge lifting slightly as if caught in one silent gust. LABELS: hairline leader to floating label box. "[GARMENT]" uppercase / "[FABRIC]" italic / "[ONE DEFINING DETAIL]" LIGHTING: soft directional from upper left + warm fill from below catching linings and sole edges + cool rim outlining the silhouette. BACKGROUND: {argument name="background color" default="COLOR"} seamless, fashion-forward. TITLE: "{argument name="look name" default="LOOK NAME"}" elegant serif type, top right. SUBTITLE: "[MOOD / OCCASION]" italic. Mood: high-concept levitation editorial, the outfit exists, the person is imagination. 4K, extraordinary fabric fidelity, tack sharp.

Miu Style Academic Nerd Portrait

请基于用户上传的 1-3 张清晰个人照片，一次性生成 4 张不同的单独精修写真照片，统一为 3:4 竖构图。主题为：「{argument name="主题" default="高智 Miu 系学院少女写真"}」。 ## 人物一致性请严格保留用户本人真实身份特征，包括脸型、五官比例、眼睛、鼻子、嘴唇、肤色、年龄感、发型基础、体型和整体气质。 4 张照片里都必须清楚看起来是同一个真实女生，不要变成陌生人，不要欧美化，不要网红化，不要过度磨皮，不要 AI 假脸，不要改变人物年龄感。 ## 整体风格整体是高智感学院少女写真，不是普通校园写真。风格关键词：高智感、学院风、轻复古、松弛时髦、书卷气、微叛逆、Miu 系氛围、韩系棚拍、杂志大片感、低调但有审美。画面像一组时尚摄影工作室拍摄的学院少女杂志写真，有精致布景、统一妆造、统一色调和真实摄影质感。 ## 场景设定场景为室内复古学院风摄影棚。背景可以使用：深胡桃木墙面、黑色皮质懒人沙发、墨绿色复古地毯、落地灯、杂志、艺术书、拍立得照片、复古音箱、书堆、黑胶唱片、银色随身听、散落的时装杂志。整体空间要有轻微暗调、复古木质感和高级杂志棚拍感。 ## 服装造型服装为高智 Miu 系学院风造型。可以包括： {argument name="服装" default="黑色宽松西装外套、浅蓝色细条纹短款衬衫、白衬衫、灰色针织背心、深蓝或灰色百褶短裙"}、灰色中筒袜、黑色厚底乐福鞋、细框眼镜、简约发夹、银色戒指、细项链。服装要有学院感和轻微叛逆感，不能太乖，不能太幼稚。有一点露腰设计，但整体保持时尚、高级、聪明、克制。 ## 发型妆容发型为自然蓬松的长卷发或微卷发，带一点凌乱空气感，不要过度精致。妆容为清透高级妆：干净底妆、自然眉毛、低饱和眼影、细腻卧蚕、轻微眼线、自然睫毛、裸粉或豆沙色唇妆。人物气质要聪明、冷静、松弛、有一点不想讨好人的少女感。 ## 四张照片镜头设计请生成 4 张不同的单独照片，不要拼图，不要四宫格。 ### 第 1 张：沙发正面坐姿人物坐在黑色皮质沙发上，身体微微后靠，双腿自然弯曲或交叠，手边有杂志和书本。眼神看向镜头，表情冷静、聪明、略带距离感。构图为中远景，完整展示服装和环境。 ### 第 2 张：站姿杂志阅读人物站在木质墙面前，手拿一本艺术杂志或书本遮住下半张脸，露出眼睛和眼镜。旁边有书堆、复古音箱或落地灯。姿态自然松弛，像被摄影师抓拍到的时尚杂志片。 ### 第 3 张：近景高智感肖像人物靠近镜头，戴细框眼镜，一只手轻轻扶脸、扶眼镜或靠近嘴唇。画面为胸像或半身近景，重点表现五官、眼神、妆容和发丝质感。表情安静、理性、带一点疏离感。 ### 第 4 张：地毯坐姿 / 杂志散落人物坐在墨绿色复古地毯上，背靠木墙或沙发，腿部自然摆放，手里拿一本杂志或艺术书，地上散落时装杂志和拍立得照片。眼神可以看向镜头外，像在发呆，氛围更松弛、更电影感。 ## 摄影与画质真实摄影质感，高级棚拍光线，暖调柔光，轻微胶片颗粒，低饱和复古色调，木质棕、墨绿色、黑色、浅蓝色为主色。画面需要有空间层次、衣服质感、发丝细节、皮肤真实纹理和自然阴影。不要过曝，不要塑料皮肤，不要廉价网红风，不要浓重滤镜，不要动漫化，不要油画化。 ## 负面要求不要四宫格拼图。不要生成同一张图的重复角度。不要改变人物身份。不要变成欧美脸。不要过度瘦身。不要夸张大眼。不要多余手指、畸形手、错误腿部结构。

Basic Product Shot Prompt for Moving Parts

show the robot in a pose doing something with it's arms

New York Night Archive Diorama

Goal: Create a highly detailed physical “Landscape Archive Model” museum diorama of {argument name="city name" default="New York City"} at night, presented as an architectural archive board with a raised 3D city model integrated into a flat cartographic map. Canvas: Wide horizontal 16:9 image, photographed from an oblique overhead angle like a premium editorial product shot. The board sits on a dark surface with subtle shadows, a thick matte edge, and tactile paper/cardboard texture. Use a restrained night palette of deep navy, charcoal blue, muted brass, warm amber window lights, cream annotation lines, and dark green park areas. Layout: The entire image is one large rectangular archive plate with a thin double-line border, coordinate grid letters along the top and bottom, coordinate numbers along both sides, and faint technical map grid lines. The central area shows Manhattan as a dense raised miniature city, surrounded by darker flat-map boroughs and waterways. The 3D buildings should look like matte architectural model blocks with tiny lit windows and cast shadows. The waterways are dark blue, slightly satin, and labeled directly on the map. Main title block: Place a boxed title panel in the upper left reading exactly “NEW YORK CITY”, with smaller lines “NOCTURNAL URBAN ARCHIVE” and “NYC-NAM-2024-001”. Add tiny archive text above it such as “LANDSCAPE ARCHIVE MODEL / 地景档案模型”. Add a small top-right study label reading “EAST RIVER CORRIDOR STUDY” and “EDITION 01”. Subject details: Show Manhattan as the main raised island, packed with hundreds of small buildings and warm light points. Include a tall glowing Empire State Building near midtown, a bright cluster around Times Square, One World Trade Center near lower Manhattan, the Chrysler Building on the east side, Brooklyn Bridge crossing the East River, and a rectangular dark Central Park inset near the top-center of Manhattan. Surrounding flat-map areas should include New Jersey on the left, Queens on the right, and Brooklyn in the lower right. Counted visible map labels: Include exactly 15 prominent callouts/region labels: 1) “NEW JERSEY / HUDSON COUNTY”, 2) “HUDSON RIVER”, 3) “ONE WORLD TRADE CENTER / 1,776 ft / 541 m”, 4) “TIMES SQUARE / THEATER DISTRICT”, 5) “EMPIRE STATE BUILDING / 1,454 ft / 443 m”, 6) “CENTRAL PARK”, 7) “CHRYSLER BUILDING / 1,046 ft / 319 m”, 8) “EAST RIVER”, 9) “BROOKLYN BRIDGE / 1,595 ft / 486 m”, 10) “QUEENS / LONG ISLAND CITY”, 11) “BROOKLYN / DOWNTOWN BROOKLYN”, 12) “LEGEND”, 13) “NORTH”, 14) “SCALE 1:25,000”, 15) “ARCHIVE NOTES”. Use thin cream leader lines and small boxed annotation plates for landmark callouts. Legend and information panels: In the lower left, create one boxed legend with exactly 6 legend entries: “PRIMARY ROAD”, “SECONDARY ROAD”, “RAIL LINE”, “WATER BODY”, “PARK / GREEN SPACE”, and “MAJOR LANDMARK / BUILDING FOOTPRINT”. Below or near it, include one small north arrow compass and one scale bar labeled in miles and kilometers. In the lower right, create one archive notes box with a paragraph of tiny technical text plus exactly 4 metadata fields: “ARCHIVE CODE NYC-NAM-2024-001”, “MODEL NO. 001”, “SHEET NO. 01 / 01”, and data-source text in very small print. Visual style: Ultra-realistic miniature architectural model photography mixed with precise cartographic design, museum archive aesthetic, sharp details, physical paper grain, slightly worn board edges, amber pinprick lights, clean serif title typography, tiny monospaced technical labels, and dramatic but soft nocturnal studio lighting. Constraints: Keep the image as a single finished physical archive board, not a digital UI. Maintain exact visible landmark hierarchy and the listed label count. No people, vehicles, logos, watermark, or extra decorative text. Preserve the nighttime restrained color palette and the tactile model-map hybrid look.