項目を入力
- 1項目を入力します
- 2プロンプトをコピーします
- 3GPTのチャットに貼り付けます
- 4そのまま送ると、サムネイルの例のような画像になります
- 5人物写真1枚(任意)をプロンプトと一緒に入れると、その写真が反映されます 任意
プロンプト全文を見る 4,345文字
Generate this image now. Return one complete image directly. PHOTO RULE (this overrides any other line in this prompt, before or after it, that calls the photo required or mandatory or says to ask for it): if a photo is attached, use it exactly as the instructions below describe. If no photo is attached, never ask for one and never stop — invent a fitting fictional subject (person, pet, food, product or place, whatever this card is about) in the spirit of the card's example image, and finish the image. [User choices] Fictional person note: "【人物】". Use only without an attached person photo; this note defines the default face, hair and age. Night city: "【夜の街】". Exact option mapping: "水辺の街" = an original waterfront skyline with illuminated towers reflected in still water; "丘の町" = an original layered hillside town with tiny warm window lights; "高架鉄道の街" = an original city with an elevated rail viaduct, distant lamps and silent dark towers. Apply only the selected option. Exposure glow: "【重なりの光】". Exact option mapping: "アクアと金" = aqua shadows and warm gold city lights; "紫とコーラル" = violet shadows and coral-pink city lights; "青と銀" = deep-blue shadows and pale silver city lights. Apply only the selected option. [Person photo takes priority] If a person photo is attached, transform that exact person into this card's specified medium and scene. Preserve apparent age, gender, face shape, skin tone, actual hairstyle, hair texture and color, glasses and distinctive features. Never add glasses, a beard or a mustache absent from the photo. The fictional person's face, hair and age never replace the photographed identity. For a doll, preserve recognizable identity cues through the deliberately oversized doll eyes and small doll body. For two-ink or translucent exposure styles, translate photographed colors into the chosen ink or exposure palette while preserving structure and tonal relationships. Controls alter props, clothes and scene only. Preserve a photographed child's actual age and use age-appropriate fully covering clothing and proportions. Do not ask for a photo when none is attached. [True profile silhouette double exposure] Create an original illustrated double exposure on warm off-white paper. One large, anatomically coherent head-and-shoulders profile faces right, with the forehead, nose, lips, chin and neck contour clearly readable. A fully opaque closed-neck charcoal sweater defines the shoulder silhouette. Render the outer face softly in anime painting with a subtle visible eye and retain identity in the profile contour. Inside the head, neck and shoulder silhouette, blend the selected original night city using a translucent second exposure: city towers emerge through the hair, water or streets cross the lower neck and glowing windows fill the shoulder. Keep these buildings mostly clipped to the person's outline, with softly dissolved internal transitions rather than a hard pasted rectangle. A few translucent iridescent soap bubbles overlap the temple and extend slightly beyond the contour; tiny stars glow within the dark inner skyline. Use the selected exposure glow. The face remains readable THROUGH the city, not a person posed in front of a city and not a split-face comparison. No album title, music player, typography, real landmark trademark, brand, extra face or text. [Original and complete] Invent an original composition, character, costume and ornament details. Use only general medium, framing and atmosphere; never reproduce an existing artwork, recognizable character, commercial doll face mold or creator signature. Clothing is opaque and fully covering with a closed chest and calm nonsexual framing. No revealing clothes, cleavage, breast emphasis, underwear, upskirt angle, cigarettes, smoking, firearms or gun accessories. No readable lettering, title, logo, signature, watermark or UI. Return exactly one complete image; no comparison panels, device mockup, explanatory prose, code or questions. [Final output format] 完成した2:3の縦型画像を1枚、1024×1536ピクセルで出力してください。重要な文字は上12%と下15%に置かないでください。 This selected output format takes priority over any fixed canvas size or aspect ratio elsewhere in this template. Adapt the composition, text zones and margins to the selected canvas without stretching or cropping essential content. Device safe areas apply only when a device is selected. Never print these format instructions on the image.
結果はどうでしたか?
使い方・よくある質問
どんな絵が描けますか?
右を向く横顔の輪郭の中に、都会の窓の光や通り、星を半透明に重ね合わせます。人物と都会を前後に並べるのではなく、頭・首・肩の中に風景が染み込む多重露出(ダブル・エクスプロージャー)です。いくつかのシャボン玉が輪郭の外へ少しはみ出し、エモーショナルな人物紹介や縦長の芸術投稿に使用できます。
表紙のように始めましょう
表紙の例は、35歳男性、ダークネイビーの短いウェーブヘア、穏やかな表情 / 水辺の都市 / アクア金色です。最初はこれらの値が入っており、自分で直接入力する欄は好みの特徴に変更できます。推奨比率は2:3です。
目に見えるボタンだけを選びます
都会の夜景: 水辺の都市・丘の村・高架鉄道の都市。
重なり合う光: アクア金色・パープルコーラル・ブルー銀色。
都会の夜景は水辺の都市、丘の村、高架鉄道の都市であり、重なり合う光はアクア金色、パープルコーラル、ブルー銀色です。有名都市の特定の建物や商標の代わりに新しい都市を構成します。鼻、唇、顎のラインが都会の光に埋もれず、同じ横顔の輪郭の中に残るようにします。
写真は任意です
ご本人または使用許可を得た人物の写真1枚をプロンプトと一緒に入力すると、顔の形、年齢層、肌の色、髪型、眼鏡やヒゲの有無を活かしてこのカードの表現に変えます。写真にない眼鏡やヒゲを新しく付け足すことはありません。ボタンは衣装やシーンを変更し、実際の顔や髪の特徴は変えません。写真がなくても人物欄の仮想人物で完成し、写真を要求しません。







