GPT Image 2 提示词：14,482+ 个示例与指南

转换为 {argument name="season" default="autumn"} 的 {argument name="location" default="European street"} 场景

High-fashion studio portrait of an elegant {argument name="ethnicity" default="East Asian"} woman with wavy short dark hair wearing a {argument name="hat description" default="wide brimmed black velvet top hat decorated with intricate silver embroidery along the brim and a metallic vintage buckle on the band"} She is dressed in a sleeveless tailored dark vest with silver swirl patterns, paired with long dark navy velvet opera gloves Wearing {argument name="jewelry" default="luxurious jewelry sapphire teardrop earrings and a multi-strand pearl and sapphire necklace with an ornate iris pendant"} Dark grey textured backdrop, dramatic studio lighting cinematic, highly detailed, 8k resolution.

Generate a 16:9 horizontal bathroom design presentation image. On the left, place a partial painting reference of the character's head and golden long hair from {argument name="artwork" default="'The Birth of Venus'"}. In the middle, show a pencil sketch of a matching seashell soap holder. On the right, show the product in use on a washstand. A wide and shallow scallop-shaped white porcelain soap dish with radial texture, featuring a small Venus figure standing on the back edge with long golden hair and wearing a white classical robe that fully covers the body. In the dish is a used {argument name="main color" default="pale peach"} bar of soap with rounded edges and a few water droplets and thin soap film on the surface and inside the dish. Render a pearl-white glazed finish, subtle material inconsistencies, and realistic contact shadows, alongside a linen towel and part of a faucet. The sketch and object should be consistent, with no text, logos, or URLs.

Ultra-realistic cinematic close-up right-facing side-profile portrait of a {argument name="ethnicity" default="young South Asian man"} outdoors during {argument name="lighting context" default="warm golden-hour sunset"}. Use my uploaded face reference as the strict identity reference-match my exact face, facial proportions, beard, mustache, skin texture and hairstyle 100%, no beautification, no skin whitening, no face reshaping. Copy only the pose and composition from the pose reference. Upper chest and shoulders upward, body fully sideways to the right, head straight with chin slightly raised, eyes gently closed, relaxed lips and peaceful emotional expression. {argument name="clothing" default="Plain oversized matte-black crew-neck T-shirt"}. Minimal open sunset sky with natural peach-orange and warm amber gradient, subtle blurred horizon. Strong sunset backlight creating a dark moody silhouette; face must remain dark, not bright or front-lit. Thin warm golden rim light outlining hair, forehead, nose, lips, beard, jawline and shoulders. 85mm DSLR, f/1.8, shallow depth of field, low-key exposure, deep shadows, subtle film grain, cinematic color grading, hyper realistic 12k resolution, natural photo, 3:4 vertical portrait.

You are an information editor, diagram designer, and 3D art director. - Compare 3 visual proposals matching the content, and adopt the most intuitive option. - Explain using objects or materials specific to the subject. Use books, bamboo slips, or paper for classical literature; parts or assembly for manufacturing. - Elegant matte materials, soft lighting, and natural depth. Use 3D representations to convey sequence, relationships, and changes.

An enchanting and surreal digital art piece featuring a translucent, golden maple leaf hovering magically above the surface of calm, dark water. The leaf glows from within with a warm, ethereal light, its delicate veins clearly visible. Inside the translucent structure of the leaf, tiny, vibrant pink flowers and closed buds are embedded, appearing to bloom within its very veins. The tips of the leaf are edged with a sparkling, golden glitter that drifts into the air like magic dust. The leaf's stem extends downward, just touching the water's surface, creating concentric ripples that spread outward. Below the water, a reflection of the glowing leaf and stem is faintly visible. The background is a dreamy twilight forest with silhouetted pine trees against a soft, gradient sky of purple, orange, and blue. Several pink water lilies float on the dark water, adding to the serene and magical atmosphere. A majestic, ethereal maple leaf made of translucent, crystalline material floats delicately above a serene dark pond. The leaf is intricately detailed with glowing veins and is embedded with small, soft pink cherry blossom flowers and buds that seem to grow directly from its structure. Golden, shimmering magical dust particles swirl around the leaf, casting a warm, radiant glow. The tip of the leaf stem gently touches the water surface, creating perfect concentric ripples that reflect the light. The background features a dreamy, out-of-focus forest landscape at dusk, with hints of silhouetted trees and a soft gradient sky ranging from deep twilight blues to pale pinks. Floating pink lotus flowers rest on the calm water surface in the foreground and mid-ground. The lighting is soft, cinematic, and magical, highlighting the glassy textures and bioluminescent quality of the scene. The composition is centered, vertical, and symmetrical, evoking a sense of tranquility, mystical nature, and fairy-tale beauty, rendered with hyper-realistic digital art precision.

Premium technical infographic of {argument name="subject" default="Apple 18 pro"}.\nUse the reference image only to understand the shape and structure of the object, without copying the same photo, angle, composition, or background. Reinterpret the subject in a new professional and realistic photograph, clean and well-lit, with a suitable and more aesthetic background. Keep the object as a real photo, not an\nillustration. Add a technical blueprint-style overlay with white lines, arrows, dimensions, labels, and small diagrams of parts, materials, measurements, and functionality.\nClear, elegant, and informative composition.\nInclude a sketch box in the upper left corner with the title "[{argument name="subject" default="Apple 18 pro"}]

请为{argument name="城市名" default="城市名"}生成竖版城市宣传海报。不要套用固定模板，要先提炼这座城市最独特的文化背景、地理环境、产业发展和城市理念，再据此设计画面结构。画面必须让人一眼看出这是{argument name="城市名" default="城市名"}：选取该城市最具辨识度的历史文化符号、自然地理符号、现代地标、产业特征、生活气质和未来愿景。构图不固定，可根据城市特色自由安排前景、中景、远景和动势元素。要求体现： 历史文化：该城市的传统建筑、地域文化、民俗、历史记忆或精神象征。 当下发展：现代天际线、产业特色、交通、商业、科技、金融、港口、生态等。 城市理念：用视觉隐喻表现这座城市的精神，比如开放、创新、烟火气、国际化、山水人文、未来科技等。 海报质感：竖版 9:16，高端国潮城市宣传海报，写实数字绘景与水墨/光影融合，电影级光影，高细节，商业海报排版。 文字：城市名“{argument name="城市名" default="城市名"}”可作为书法主标题，另加一句符合城市气质的宣传语；避免大量小字乱码。 不要通用城市拼贴，不要错误地标，不要廉价旅游广告感，不要卡通风，不要水印。

添付した4枚の女性の全身画像を参照し、ファッション映像の素材となる、正方形の4パネル画像を1枚生成してください。 【完成形】 全体のアスペクト比は1:1。画面を均等な2×2に分割し、各パネルも正方形にする。各パネルに女性を1人ずつ配置し、合計4人。添付順に、1枚目＝左上、2枚目＝右上、3枚目＝左下、4枚目＝右下とする。外枠、パネル間の隙間、立体的な額縁は不要。 要素の種類を絞りながら、文字の大小、塗りと輪郭、重なりと余白に強いメリハリを持たせた、現代的なファッションキャンペーン。人物の領域はすっきりと保ち、文字の領域はアートディレクションされた豊かな構成にする。これは完成した映像素材として使用するポスター画像。仮レイアウトではなく、この静止画だけでも魅力的な完成デザインに仕上げる。4枚がそれぞれ完成したポスターとして成立し、全体でも統一感を持つこと。 【参照人物の維持：配置より優先する条件】 これはユーザーが都度用意する女性4人の全身画像に対応する共通指示書である。特定の顔、体型、衣装、髪型をあらかじめ設定しない。各パネルの人物情報は、そのパネルに対応する添付画像だけから取得する。4人の特徴を混ぜず、共通の顔や共通のモデル体型にそろえない。 各人物の顔の輪郭、目・鼻・口の形と配置、表情、年齢感、肌色、髪型、髪色を参照どおりに維持する。頭身、頭部と身体の大きさの比率、首の長さ、肩幅、胴の長さと幅、腰幅、腕と脚の長さ・太さ、手足の大きさを維持する。顔を小さくする、胴を細くする、脚を長くする、身体を縦長・横長に変形するなどの体型補正は行わない。参照人物の姿勢、顔と身体の向き、視線、腕・手・脚の位置、足の開き方、重心と接地状態をそのまま維持する。左右反転もしない。衣装・靴・アクセサリーの形、色、素材感、丈、ゆとり、着用状態、姿勢に伴う主要なしわやシルエットを引き継ぐ。ゆったりした衣装の輪郭を身体の輪郭だと解釈して体型を作り変えない。参照写真の背景、文字、枠は引き継がない。 【人物をスペースへ配置する方法】 人物と衣装を一体として扱い、縦横同じ倍率で全体を拡大縮小し、位置を移して配置する。顔、胴体、脚、衣装などの部分ごとに異なる倍率を適用しない。ポーズや体型を枠に合わせて描き直すのではなく、元の全身シルエットを保って配置を調整する。頭頂から靴底、髪、指先、衣装の裾までを含む外形全体がパネル内に収まるようにする。人物の高さはパネルの約80〜85％を基本目安とする。ただし固定条件にはしない。参照人物の腕の広がりや衣装の幅が大きい場合は、人物全体を同じ比率で縮小して収める。身体を細くしたり、手足を移動したり、裾を切ったりして収めない。4人の表示サイズは可能な範囲で整えるが、全員を同じ頭身・同じ肩幅・同じ体型にそろえない。各パネルの上端をy=0％、下端をy=100％とする、パネル内の座標で配置を判断する。人物の外形を収める上側の配置ガイドをy=7.5％、下側の配置ガイドをy=92.5％に設定する。これは構図を決めるための見えないガイドであり、完成画像に線や数値を描かない。髪・頭頂・指先・衣装・靴を含む人物全体を、必ずこの上下ガイドの内側へ配置する。ガイド間の高さはパネル高さの85％である。人物全体の外形の中心をパネルの高さ50％に合わせ、縦横同倍率で収める。横幅の制約でさらに縮小する場合は、上下中央の配置を維持する。顔や靴が画面内に見えているだけでは余白を確保したことにしない。頭上と靴底の下に、背景だけの空間がはっきり見えること。手や衣装の外側にも余白を確保し、パネル端に接触させない。頭や足だけを移動したり、身体を圧縮したりして余白を作らない。人物の姿勢や輪郭を変更しない範囲で明るさと色調をなじませ、足元に控えめで自然な接地影を付ける。立体感を作るために顔や体型を描き替えない。 【人物と文字の棲み分け】 各パネルの左側約35％をタイポグラフィの領域、右側約65％を人物の領域とする。領域を区切る線は描かない。人物は右側、文字と図形は左側に置き、顔・髪・身体・衣装・手足に重ねない。人物と文字の間には明確な余白を設ける。文字を優先して人物の身体を変形させない。収まりが難しい場合は、人物全体の等比縮小と位置調整を優先する。 【タイポグラフィの共通設計】 同じコンデンスド・サンセリフの書体ファミリーを使用し、極太の塗り文字と、太めの輪郭線だけのアウトライン文字を組み合わせる。文字の形を装飾で崩さず、大小と重なりでデザインする。使用する言葉は、左上{argument name="左上文字" default="BOLD"}、右上{argument name="右上文字" default="COOL"}、左下{argument name="左下文字" default="PURE"}、右下{argument name="右下文字" default="EDGE"}。各パネルの主見出しは一つ。主見出しは全字が読める状態にする。同じ単語のアウトライン反復を一つだけ補助要素として加える。別の単語や小さな説明文は加えない。主見出しと補助文字には明確なサイズ差をつける。補助文字は主見出しの約1.3〜1.5倍の大きさとし、淡いスレートグレーの輪郭で描く。補助文字の一部はパネル外周で意図的に見切れてよい。隣のパネルには侵入させない。文字や図形同士の重なりは左の文字領域内だけで行い、人物との間にはパネル幅の約4％を目安とした空白を残す。すべての文字は正立。極端な遠近変形、立体化、ノイズによる文字崩しは行わない。細かな説明文、数字、パネル番号、ロゴ、バーコードは追加しない。 【背景・配色】 全パネルを明るい背景にする。左上：明るいアイボリー。右上：明るいクールグレー。左下：ごく淡いブルーグレー。右下：明るいウォームグレー。4色の明度をそろえ、背景の色差は控えめにする。暗い背景、大きな黒い背景面は使わない。人物の背後は単色を基本とし、文字、柄、帯を置かない。参照人物の髪や衣装の色に合わせ、背景の明度と暖冷だけを淡色の範囲で微調整し、全身の輪郭が背景から自然に分離するようにする。白い衣装では背景をごく薄いグレー側へ調整する。黒い衣装では十分明るい背景を維持する。輪郭を分離するために参照衣装の色を変更したり、人物へ縁取り線や発光を付けたりしない。主見出しはインクブラックを基本に、バーミリオンレッドをアクセントとして使用する。アウトラインは背景から見分けられる淡いスレートグレー。細すぎて消える線にはしない。赤は全パネルで同じ色を使う。衣装の色は参照画像を優先する。 【4パネルの文字とグラフィックの構成】 図形は、赤い長方形と細い黒の直線に絞る。人物と文字の領域分離を厳守する。全パネルに同じ下線を繰り返さず、各パネルに異なる構成と重心を作る。 左上・BOLD：大きな塗り文字と、ずれた輪郭の重なり。主見出しはBO／LDの2行。黒い極太文字で、文字領域の上から中段を大きく使う。背後に同じ2行組みのアウトラインBOLDを一つ置き、左上へ少しずらす。輪郭の一部はパネル左

Research the poster regulations for presentation at the {argument name="conference name" default="2026 Neuroscience Conference"} and transform the attached paper into a poster accordingly.

A {argument name="subject" default="tiny fishing boat"} caught in a {argument name="material" default="noodle"} wave. Dinner got a little out of hand.

a {argument name="structure" default="greenhouse"} inside a {argument name="location" default="glacier"}

Transform the reference photograph into a {argument name="art style" default="delicate hand-drawn travel journal illustration"} while preserving the original composition, architecture, people, trees, grass, road, and overall perspective. Use a traditional {argument name="medium" default="colored-pencil and watercolor sketch"} aesthetic on warm, slightly aged cream paper. Keep the buildings recognizable but simplify them into expressive hand-drawn shapes, with visible pencil strokes, loose watercolor washes, subtle paper grain, imperfect outlines, and gentle cross-hatching. Preserve the peaceful rainy-day atmosphere, soft overcast sky, warm beige and muted buildings, fresh green lawn, scattered people walking with umbrellas, wet pavement, trees, benches, puddles, and distant cars. Use a muted vintage travel-sketch palette with natural imperfections and understated colors. Place the illustration in the lower portion of the page with generous cream-colored negative space around it. Add elegant {argument name="typography" default="handwritten typography"} above: “Rainy Days”, and below: “— Quiet moments —”. Minimal, nostalgic, artistic travel magazine aesthetic, analog photography transformed into a personal sketchbook memory, sophisticated and authentic, no photorealism.

你是一款互动式古代美人捏人游戏。通过8步决定人物核心特征，其余细节由AI补全。少解释，多互动，始终保存当前角色状态。【流程】①朝代 → ②身材 → ③气质 → ④发式 → ⑤服饰 → ⑥妆容 → ⑦场景 → ⑧神态 → 完成。严格按顺序，一次只展示一个项目。用户选择后立即保存并进入下一项，不询问“下一步”，不重复确认。开始时只展示①。【选择界面】每项6～10个选项。使用紧凑视觉卡：视觉示例＋编号＋名称＋一句短解析。解析突出选项特点或视觉效果，尽量控制在10字以内。2～3列，一屏显示。支持点击时优先点击；无法点击时使用编号或名称。【捏人项目】①朝代：先秦｜秦汉｜魏晋南北朝｜隋唐｜五代十国｜宋｜辽金元｜明｜清。②身材：娇小纤秀｜纤细柔婉｜自然匀称｜高挑修长｜柔婉丰润｜丰姿婀娜。③气质：清雅｜温婉｜明艳｜灵秀｜端庄｜妩媚｜清冷｜娇憨。④发式：根据朝代提供6～8种有历史依据的女性传统发式。⑤服饰：根据朝代提供6～8种有文物、绘画、考古或文献依据的女性传统服饰形制。禁止现代新中式、泛中国风、影视架空服饰。⑥妆容：根据朝代提供6～8种有历史依据的女性妆容。⑦场景：根据朝代提供6～8种符合时代建筑、生活方式和社会环境的女性生活场景。⑧神态：根据①～⑦已确定的全部设定，动态生成8种最符合当前人物、场景和情境的神态。8种神态须有明显区别，避免重复、冲突和泛化。⑧不使用固定选项池。【朝代联动】④发式、⑤服饰、⑥妆容、⑦场景必须与①朝代一致。辽金元需分别处理，不得混合三个时期。修改①朝代，只重新处理④⑤⑥⑦；②③保持不变。修改④～⑦任一项目后，检查后续项目是否与最新设定冲突，有冲突则重新处理；⑧始终根据最新①～⑦重新生成。【状态与操作】始终保存已选项目。“随机”：随机当前项目，已锁定则无效。“换一个”：重新提供当前项目选项，已锁定则无效。“锁定”：锁定当前项目，限制随机、换一个和全部随机改变该项目。“修改设定”：用户明确指定修改时，可以修改已锁定项目。“返回”：回到上一项目并立即显示该项目，重新选择后继续向后推进，其他状态保留；若后续项目与最新设定冲突，则重新处理受影响项目，并重新生成⑧神态。“全部随机”：随机所有未锁定项目，已锁定项目保持不变，从①开始；遇到已锁定项目直接保留并进入下一项。完成①～⑦后，根据最新设定重新生成⑧神态。“重新捏人”：清空全部设定，从①开始。支持直接说“换成明代”“发式换一个”“改成浅笑”等，根据语义执行。【AI自动补全】除8个捏人项目外，其余全部由AI自动完成，包括动作、手势、具体发饰、首饰、颜色、纹样、材质、鞋履、道具、环境、人物关系、构图、镜头、光影、时令、天气等。时令：春｜夏｜秋｜冬。天气：晴｜阴｜薄雾｜细雨｜雪。所有自动补全必须符合人物、朝代、服饰、发式、妆容和场景。【固定人物】成年女性；身材自然；比例协调；真实肤质。【固定摄影】手机生活抓拍 × CCD直闪；9:16竖幅；原生数码照片。摄影风格固定，不作为选择项目，不改变历史语境。【完成】完成⑧神态后，必须依次输出：【完整角色设定】①朝代：当前选择、②身材：当前选择、③气质：当前选择、④发式：当前选择、⑤服饰：当前选择、⑥妆容：当前选择、⑦场景：当前选择、⑧神态：当前选择。【最终图片提示词】完整整合8项设定，并自动补全动作、手势、发饰、首饰、服装细节、颜色、纹样、材质、鞋履、道具、环境、人物关系、时令、天气、构图、镜头和光影。保持历史一致性，并加入：手机生活抓拍 × CCD直闪；9:16竖幅；原生数码照片。最终提示词必须完整、连贯、可直接复制用于图片生成，不得只输出关键词或省略已选设定。提示词最后加入：左下签名“● DeepBlue”；“●”为纯 #0B3D91 深蓝色实心圆点，“DeepBlue”为白色自然手写字体。然后显示：① 生成图片 ② 修改设定 ③ 重新捏人。【生成】输入“1”“生成”或“出图”，立即根据最终图片提示词生成图片。【修改】输入“2”后指定项目并重新选择。修改后重新输出完整角色设定和最终图片提示词，再显示①②③。【重新捏人】输入“3”或“重新捏人”，清空角色，从①开始。【再来一个】保留8项核心设定和固定摄影。只重新演绎动作、环境、时令、天气、构图、镜头和光影。不得改变8项核心设定或固定摄影。生成新的最终图片提示词并立即生成。【最终规则】这是连续捏人游戏，不是普通问答。一次一个项目；选择后立即推进；始终保存状态；朝代变化自动联动；修改④～⑦后检查后续一致性；⑧神态始终根据最新①～⑦动态生成；摄影固定；不得要求下一步；不得重复确认。完成⑧后必须：输出完整角色设定 → 输出完整图片提示词 → 显示①②③。不得跳过完整图片提示词。点击不可用时，立即降级为编号或名称选择，不得中断流程。现在开始，只展示①朝代。

Ultra-realistic cinematic close-up portrait of a {argument name="subject" default="young adult man"} use image for face reference , laughing naturally with a wide genuine smile, head slightly tilted upward, looking just past the camera. Dramatic studio portrait photography against a completely black background. Strong {argument name="primary color" default="vivid magenta/purple"} rim light from the left side and intense {argument name="secondary color" default="cyan/teal"} light from the right, creating a striking split-light effect across the face, beard, neck, and black crewneck sweatshirt. Highly detailed skin texture, realistic pores, individual beard hairs, sharp expressive eyes, natural teeth, soft specular highlights, shallow depth of field, high contrast, moody nightclub aesthetic, professional fashion/editorial photography, 85mm lens, f/1.8, close framing from chest up, centered composition, photorealistic, HDR, ultra-detailed, 4K.

Generate a 16:9 horizontal desktop design presentation. On the left, place a painting reference of {argument name="art reference" default="Mondrian's 'Composition with Red, Blue and Yellow'"}. In the middle, show the front grid and perspective pencil sketch of a desktop storage cabinet, and on the right, show the final effect in use. The cabinet is made of ivory-white painted wood, with thick black divider strips forming an asymmetrical rectangular grid. Large red drawers, small blue drawers, small yellow drawers, and white compartments form the front. The red drawer is pulled open, containing {argument name="storage items" default="headphones and coiled cables"}; the yellow drawer is slightly pulled out, revealing an eraser. Drawers must have realistic side walls, thickness, and internal space, aligning with their respective openings. Show fine wood grain, contact shadows, and desktop wear, with natural side lighting. The sketch must match the cabinet layout, with no text, logos, or URLs.

Macro cinematic photography inside a {argument name="fruit" default="peeled tangerine"} resting on a dark stone surface. The peel folds outward like petals, forming a cave. Overhead, the citrus segments arch into a translucent orange dome, while the white pith reads like pale plaster. {argument name="occupants" default="Three figures, each about two centimeters tall"}, inhabit the cave: one lies on a citrus segment as if it were a bed; one climbs upward along the white pith ridge between two segments as if it were a staircase; one stands at the cave entrance looking out into darkness. A single tangerine seed lies on the ground, scaled like a massive millstone. Every membrane layer and every individual juice vesicle is fully resolved. A {argument name="lighting" default="single low-angle sun"} is positioned behind the fruit and is the only light source, producing true transmitted light through the citrus flesh. The orange brightness of the dome must come from light physically passing through the fruit itself, not from any artificial glow effect. Individual juice vesicles illuminate one by one in transmission, while thicker pith appears as darker veins. The cave floor is illuminated only by this transmitted light. Outside the cave entrance is completely black. No fill light. Anamorphic 2.39:1, anamorphic lens with macro adapter, f/4. Sparse defocused light points outside the cave appear as vertically oval bokeh with subtle horizontal anamorphic stretch. Deep focus, focus stacked. Kodak Vision3 500T motion picture negative, tungsten white balance, warm saturated transmitted orange highlights with deep cyan shadows. Black Pro-Mist 1/4. Strong transmitted-light edges along the thinnest parts of the fruit show visible red halation. Overall exposure reduced by one stop. The darkness outside the cave remains truly black. Fine film grain, more visible in the shadows. No digital sharpening, no HDR, no orange-and-teal grading, no lens-flare effects, no artificial glow, no CGI plastic texture.

输出该 {argument name="character" default="character"} 的 Vocaloid MV 的各种剪辑画面，以 3x3 网格形式呈现，比例为 16:9。

This image presents a serene four-panel photo collage featuring a {argument name="subject description" default="young woman with long, dark wavy hair and soft bangs"}, dressed in a {argument name="clothing" default="light, sheer garment"}. In the top-left panel, she faces forward with a gentle, warm smile, her eyes engaging the camera directly. The top-right panel captures her glancing back over her shoulder against a background dappled with soft, abstract light patterns. In the bottom-left panel, she is depicted in a peaceful moment with her eyes gently closed, highlighting a calm and contemplative mood. Finally, the bottom-right panel shows her looking thoughtfully toward the side with a soft expression, completing a cohesive visual narrative centered on grace, natural beauty, and tranquility.

Create a refined editorial {argument name="location atmosphere" default="European"} travel-art composition based on a reference photograph. The image is divided vertically into two parts: the upper section is a realistic cinematic travel photograph, while the lower section transforms the exact same scene into a delicate {argument name="watercolor style" default="hand-painted watercolor illustration"}. Upper section: authentic candid travel photography, natural daylight, soft shadows, subtle film grain, realistic textures, documentary-style composition, people naturally walking through the scene, beautiful architectural details, slightly muted elegant colors, high-end travel magazine photography. Lower section: a minimalist handmade watercolor painting of the exact same scene, preserving the recognizable composition, architecture, people, poses, perspective and major visual elements from the photograph. Loose translucent watercolor washes, delicate ink details, visible paper texture, soft edges, imperfect brushwork, subtle pigment bleeding, airy negative space, understated pastel tones, artistic but realistic. Leave generous warm ivory/off-white textured paper space surrounding the watercolor illustration. Add a small elegant {argument name="caption" default="handwritten caption"} near the bottom, such as “summer days” or “a quiet afternoon”, with a thin minimalist horizontal line underneath. Overall aesthetic: luxury travel journal, fine-art watercolor postcard, contemporary editorial design, nostalgic European summer, understated elegance, tactile handmade paper, sophisticated and serene. Portrait orientation, clean composition, premium art direction, no clutter, no borders, natural proportions, highly detailed photograph transitioning into an airy watercolor illustration.

请将我上传的每一张照片分别制作成一张独立的高级设计海报，不多图拼接，每张照片单独输出。整体采用 3:4 竖版构图，上下两个区域高度严格 1:1，各占画面 50%。 上半部分保留原始照片，保持主体身份、结构、姿态、真实质感、自然光影和原有色彩氛围，仅进行轻微高级调色，使其具有艺术杂志与展览图像质感。为适配画幅，可自然扩展环境背景，但不得拉伸、扭曲或改变主体。 下半部分只提取照片中最具识别性的主体、轮廓、结构、姿态与叙事关系，重构为 手绘涂鸦式摄影拼贴 / Hand-drawn Doodle Photo Collage。不要完整复制照片，不要保留全部对象和背景，而是删去无关细节，只选取最能代表原图主题与视觉记忆点的少量照片碎片，通过裁切、缩放、重组与留白重新表达，使人一眼识别它与上方照片之间的对应关系。 下半部分需重新做美术判断。哪怕原图构图差、背景乱、主体小，也要主动通过删减、重组、裁切、尺度变化和留白把它救成一张成立的作品，真正赋予模型重新导演画面的权力。 构图采用小尺度拼贴群组 + 大片空场的方法。下半部分只保留一组较小的照片拼贴单元，像被安放在白纸上的一簇视觉笔记，可偏心、贴边、悬置或局部裁切；整体不铺满，不做大场景复刻。留白不是空背景，而是画面的一部分，要与照片碎片、手绘线条、符号和文字共同形成呼吸感、空间感、停顿感与非对称平衡。宁可少，也不要满。 画面语言采用摄影拼贴 + 手绘涂鸦 + 平面版式设计的混合媒介方式。照片碎片可按不规则网格、错位模块或松散编排组织；边缘可带有粗糙、随手画出的黑色手绘边框。可加入少量自由手绘的太阳、星星、笑脸、括号、箭头、杯子、线条、符号或涂鸦式注记，增强 scrapbook / zine / editorial collage 的私人记录感与杂志感，但必须克制，不可喧宾夺主。 背景保持干净白底或极浅暖白底，大面积空白，像速写本、剪贴簿或独立杂志页面。整体气质轻松、日常、聪明、松弛，但版式要精致、平衡、耐看。 配色从上方照片中提取 2–4 种最具辨识度、最有情绪价值的颜色，用于下半部分照片碎片、手绘元素和少量点缀，使整体色彩统一、柔和、自然，不杂乱、不脏灰。 文字只作极少量编辑性介入，不限制语种。可根据主体、地点、动作、情绪或隐喻生成少量字词或短句，像手帐、独立杂志或 zine 中的随手注记一样，轻巧地分布在留白区域，与照片碎片和涂鸦共同形成精致图文关系。

A {argument name="subject" default="face"} with a lifetime in it. No polished skin, no studio backdrop. Just a {argument name="setting" default="rooftop radio"} before sunrise.

Referencing this character, create a 2D animation sprite sheet for a game. The content is "{argument name="action" default="fill in action"}". Represent one continuous action across a total of 16 frames in a 4x4 grid. [Sprite Sheet Specifications] - Square canvas - 4 columns x 4 rows, total 16 frames - All 16 cells are exactly the same size - Ensure at least 10px margins on top, bottom, left, and right of each cell - No borders, grid lines, numbers, text, symbols, or UI required - Background is a single solid white color unified across all frames - Arrange frames in chronological order from top-left to right, and top row to bottom row. [Most Important: Fixed Size and Position] - Unify character scale across all 16 frames - No zooming in or out - Fix the ground baseline at the same height - Ensure the character's center position does not move significantly between frames - Change poses only as needed for movement. [Most Important: Fit Entirely Within Cells] - Everything including hair, clothes, limbs, weapons, accessories, effects, afterglow, and particles must fit inside each cell - Do not exceed cell boundaries - Do not violate the 10px margin safety area - Even if the action is large, do not adjust by shrinking the character - If necessary, keep effects or arm swings moderate to fit within the cell. [Drawing Strategy] - Clear silhouette readable as a 2D game sprite - Movement that connects naturally between frames - Prioritize continuity without breaking as animation material rather than a single illustration - Unify detail density, lines, coloring, and shading for each frame.

Create a premium cinematic character bible sheet for {argument name="characters" default="ALAN & T-REX"}. Use uploaded character sheets as strict visual reference for both characters. Do not change either's appearance. LAYOUT: Split screen partner format. Two halves divided by a bold dramatic