All search results

Goal: Create a black-and-white shoujo manga page with exactly 2 wide horizontal panels stacked vertically, framed by thick black gutters, showing a tender bedtime interaction between {argument name="character name" default="a beautiful androgynous young man"} and {argument name="animal" default="a tiny hamster"}. Canvas: Landscape manga page, approximately 16:9, high-resolution monochrome line art with clean screentone shading, delicate hair detail, expressive eyes, soft romantic atmosphere. Panel 1: A wide top panel set in an ornate canopy bed at night. Show flowing curtains tied to bedposts, frilled fabric, pillows, blankets, and a dark starry window/background behind the bed. The young man reclines in pajamas with loose, slightly messy light hair, holding both hands open near the tiny hamster. The hamster is popping upward in a cute bounce above his palms, with small motion lines and a tiny sound effect. Add exactly 1 large vertical speech bubble on the left containing {argument name="first speech bubble" default="今日はハムスターを好きにしていいよ！"}. Add exactly 1 small handwritten sound effect near the hamster containing {argument name="sound effect" default="ぽてっ"}. The young man’s face in this top panel should be partially obscured by a plain light-gray square censor block centered over the eyes and nose, while the rest of the hair, mouth, body, and hands remain visible. Panel 2: A wide bottom panel, closer and more intimate. Show the hamster sitting upright on the young man’s open palm at the left, looking alert and cute with tiny paws. The young man leans close from the right, smiling softly and gazing lovingly directly at the hamster, with long eyelashes, detailed eyes, tousled layered hair, and loose pajama collar. The key emotional instruction is that their eyes meet affectionately. Add exactly 1 vertical speech bubble on the right containing {argument name="second speech bubble" default="……言ったね。"}. Counted visible elements: exactly 2 manga panels; exactly 1 human character; exactly 1 hamster; exactly 2 speech bubbles; exactly 1 small sound effect; exactly 1 canopy bed; exactly 2 visible bedposts; exactly 1 gray censor square in the top panel only. Visual style: Elegant Japanese manga linework, romantic comedy tone, fine hatching, pale grayscale shading, crisp black panel borders, expressive close-up composition, no color, no watermark, no extra characters, no additional text.

South Park gang gets invited for a pizza party- make sure it’s retarded and gets 50 likes

なすびぃもNano Banana Proでケーキになりました！ NanoバナーナPro最強です！🍌 ◆プロンプト 参照画像をリアルなクリスマスケーキにしてください。 さらにこの画像をChatGptに投げたらレシピまで 出してくれました！👇 【難易度】 中級（丸いスポンジを成形できればOK） 🟣 材料（6〜8人分） ◆スポンジケーキ（18cm丸型・1台分） 卵 … 3個 砂糖 … 90g 薄力粉 … 90g 溶かしバター … 20g 牛乳 … 20ml バニラエッセンス … 少々 ◆生クリーム・フィリング 生クリーム … 300ml 砂糖 … 大さじ2 お好みのフルーツ … 適量（苺・バナナ・桃など） ◆ナスの外側（紫の覆い） 紫色のチョコレートフォンダン or マジパン or シュガーペースト … 約300〜400g ※市販で「パープル シュガーペースト」「フォンダン」などが買える 黒（または濃紫）の食用色素（ヘタ用） ◆デコレーション アイシング用チョコ（茶色・白） 食用色素（赤・緑・金など） 金粉（食用） 粉砂糖 キャンディケーン（小サイズ） ジンジャークッキー（小） 星型シュガーや飾り 🍆 作り方 ① スポンジケーキを焼く オーブンを170℃に予熱 ボウルで卵と砂糖をもったりするまで泡立てる 薄力粉をふるい入れ、ヘラでさっくり混ぜる 溶かしバター＋牛乳＋バニラを合わせて加え、素早く混ぜる 型に流し、170℃で30〜35分焼く 冷ましてから2〜3枚にスライス ② ナス型に成形する スポンジを重ねつつ、生クリーム＆フルーツをサンド 全部積み上げたら 包丁でナスの形に削る 丸みのある卵型に整える 頭の部分（ヘタ側）は少し細めに 外側を生クリームで薄くコーティング（「下地」） ③ 紫フォンダンで覆う 紫色のフォンダンを麺棒で薄くのばす（3〜4mm） ケーキの上にゆっくりかぶせ、形に沿わせて密着させる 余った部分を切り取る ヘタ部分を濃紫〜黒のフォンダンで作り、上に貼り付ける ④ 顔の部分を作る 画像を再現するために： 目 → チョコチップ or 丸いチョコ ほっぺ → ピンク色マジパン or 白マジパン＋赤色素 口 → 溶かしたチョコで描く ゆるかわ系の表情にして可愛さアップ。 ⑤ クリスマス飾りを再現 画像と同じイメージで： キャンディケーンを横に刺す 星型シュガーをフォンダンに貼る ヒイラギ（緑＋赤のシュガーペースト）を作って乗せる ジンジャークッキーを土台に並べる 表面に粉砂糖を薄く振り“雪”の演出 金粉を少量はらって高級感アップ ⑥ 盛り付け 木の丸板（または丸皿）に置く モミの枝やクリスマスオーナメントを飾る （食べられない飾りはケーキに直接触れないように！） 🎉 完成！ クリスマスらしさ満点の なすびぃケーキ（ナス型クリスマスデコケーキ） の完成！

nano banana proが発表されました！ というわけで 【素人が Gemini 3 / nano banana pro でシナリオ作成から4コマ漫画作成まで全部丸投げで試してみた】 の結果を公開します！ これまでの画像生成AIとはレベチです！ 必ず確認してください！ シナリオは4種類提案してもらいました まずは「温かい目で」完成した4コマ漫画をご覧ください――― （他3つの4コマ漫画はリプ欄にそれぞれあります） （本編に登場するnano banana proは実在するnano banana proとは無関係ですのでご安心を😂） これを作成するのに使用したプロンプトは以下の文章だけです 「参照画像にある男性キャラクターと女性キャラクターによる日本語の4コマ漫画を作ってください。コマ割りは参照画像を使うこと。テーマは新しく発表されたnano banana proのこととし、最後の4コマ目で面白いオチを付けてください。ただし、生成AIに疎いユーザーにも直感的にnano banana proのことが理解できるような構成としてください。これらの条件で4種類の4コマ漫画を作ってください。」 なお、あらかじめ使いたいキャラクターとコマ割りの画像を渡しています ✅すごいポイント ・曖昧な指示だけでこのレベルの作品を作れる ・日本語の崩れが非常に少ない ・キャラクターの一貫性が高いレベルで保たれている ・吹き出しや擬音表現も全てやってくれている ✅検証ポイント ・コマ割りが指定画像と同じものは4つ中1つだけだった ・日本語が一部修正しないといけない部分があった ・余分にキャラクターが描かれていたり、眼鏡がなくなったり、バナナが基盤になったりと話の流れ的には理解できるものの「そうじゃない」的な描画も一部見られた ・シナリオは可もなく不可もなくといった印象 検証ポイントはこれからプロンプトを調整していけば何とかなりそうなレベルです とにかくざっくりした曖昧なプロンプトでここまでのものを仕上げてくるところがすご過ぎです 今回はプロンプトに入れるのを忘れましたが、この男性キャラクター（私）と女性キャラクターは大学教員と学部生という設定にしたいと考えています 生成された漫画は「先輩後輩」の関係になってしまっているので、この辺りはプロンプトで十分修正できそうですね 今後の資料作成のスタンダードツールの一つになり得ますので、ぜひ皆さんも試してみてください！ 参考になったよ！と思っていただけたら「いいね＆ブックマーク」してもらえると嬉しいです😊 ――――――――――――――― 👇nano banana pro (サイズ感編) くしゃみで眼鏡はフレームアウトしたようです あと15万という数字はどこから出てきた笑

A medium shot of the 14 fluffy characters sitting squeezed together side-by-side on a worn beige fabric sofa and on the floor. They are all facing forwards, watching a vintage, wooden-boxed television set placed on a low wooden table in front of the sofa. The room is dimly lit, with warm light from a window on the left and the glow from the TV illuminating the creatures' faces and fluffy textures. The background is a cozy, slightly cluttered living room with a braided rug, a bookshelf with old books, and rustic kitchen elements in the background. The overall atmosphere is warm, cozy, and amused. 一个中景镜头，14个毛茸茸的小家伙并排挤在一张米色旧布艺沙发上和地板上。它们都面向前方，看着一台老式木箱电视机，电视机放在沙发前的一张矮木桌上。房间光线昏暗，左侧窗户透进温暖的光线，电视机的光芒照亮了小家伙们的脸庞和毛茸茸的触感。背景是一个温馨而略显凌乱的客厅，铺着编织地毯，书架上摆放着旧书，远处还有一些质朴的厨房元素。整体氛围温暖、舒适而又充满趣味。

Create 8 different initial sketches leading to this final character. 创建 8 个不同的初始草图，最终形成这个角色。

Based on this character and background, please create a character reference sheet similar to official setting materials. ・Includes three-view drawings: front view, side view, and back view ・Add variations of the character's facial expressions ・Break down and display detailed parts of the clothing and equipment ・Add a color palette ・Include a brief explanation of the worldview setting ・Overall, use an organized layout (white background, illustration style)

Create an image where the character looks more like a real and beautiful person. There should be no clear subject or specific composition, just a random, unintentional shot. The image should be slightly blurred from motion. It should not look generated by Al, but rather as if it was taken by a real person

以丁聪的风格画一幅讽刺漫画，主题是： > 今天社交网络上被追捧的所谓AI高人,不过是 Prompt Kiddie(提示词小子)。 > 整天转帖一些提示词,其实是在自动充当大模型的燃料。

could you please try to put the characters in the shoes of the little soldiers in League of Legends, imitate their perspective and watch the battle scenes of the heroes?

Please create a three-view turnaround sheet for the attached girl.

Create an ultra-detailed retro Japanese anime portrait inspired by classic 1980s cel animation and city-pop aesthetics. Depict a {argument name="subject" default="young woman with porcelain skin, expressive warm brown anime eyes, a short feathered black bob with wispy bangs, and soft coral lips"}. She wears {argument name="clothing" default="vibrant coral-red wired over-ear headphones and a relaxed white cotton button-up shirt"}. Her head is slightly turned as if listening deeply to music, with a calm, reflective expression. Illuminate the scene using dramatic golden-hour sunlight from one side balanced by cool blue ambient skylight, creating cinematic shadows and warm facial highlights. Place her against a simple gradient sky-blue background. Render with authentic vintage cel animation linework, smooth painted shading, subtle film grain, soft bloom, nostalgic color grading, and ultra-high-resolution remastered anime quality.

Create a dynamic high-detail anime illustration of {argument name="character name" default="Alice"} in a whimsical Wonderland garden, as if she is sprinting toward the viewer in panic. She is a young blonde girl with long flowing hair, bright turquoise-blue eyes, flushed cheeks, tiny tears and sweat drops, an open frightened mouth, and a huge black bow on top of her head. She wears a classic blue-and-white Alice maid-style dress: blue puff sleeves, white frilled apron, layered ruffled skirt, black neck bow, white wrist cuffs with small buttons, white thigh-high stockings, and black Mary Jane shoes. Use a dramatic low-angle close-up composition with her body foreshortened, one fist clenched near her chest and one arm thrown back, skirt and hair flying from motion. The setting is a pastel fantasy tea-party path with exactly 7 notable background/object elements: 1 large teacup and saucer in the lower left, 1 gold pocket watch/clock in the lower left foreground, 1 red heart-shaped flower or topiary on the left, 1 large pink flower in the lower right, 1 red-and-white checkered garden path, 1 prominent playing-card soldier holding an ace-of-hearts card on the left, and 1 blurred background figure with a parasol near the center. Add curled tree branches framing the top, leafy greenery, floating petals, golden chess-piece-like ornaments on the right, and soft bokeh depth. Style should be polished modern Japanese anime, cute but frantic, with clean line art, glossy highlights, soft pastel colors, cinematic motion, shallow depth of field, and a bright airy fairytale atmosphere. Keep the image vertical, full color, no captions, no watermark, no extra text.

{argument name="character name" default="Jasmina"} 参考图

Use the main features of [same as the uploaded image] as a loose reference, with a three-quarter front-angle composition, and create a greeting card. Include only one full-body person and 1–2 distinctive objects. Make it a {argument name="style" default="minimal, simple flat-color alternative comic-style illustration"}, using clean, even hand-drawn lines. Simplify the person into basic shapes, and keep the facial features minimal—dot eyes, a simple nose, and a small mouth. Give the figure slightly awkward proportions. Use solid fill colors sparingly for contrast. Keep the composition centered, leave plenty of empty space, and do not depict a background. The overall style should feel {argument name="vibe" default="deadpan, emotionally restrained, and quietly absurd"}. The humor should come from a strange sense of logic, awkward visual relationships, or treating something trivial with excessive seriousness. Avoid exaggerated slapstick. Instead, include subtle humor that comes from an observational pose or situation. To convey a dry, bureaucratic absurdity, add a small, simple handwritten-style phrase in a rough, casual placement. No shading, no texture, no fine detail, and no coffee-related elements. The text should be written in uneven handwritten lettering as: {argument name="handwritten text" default="[Insert Text]"}

{argument name="character" default="《四谷怪谈》中的阿岩"} 的 X 个人资料页面。

Create a dramatic vertical anime fantasy illustration of a young male lightning mage unleashing an ultimate spell. The character is centered in a dynamic low-angle close-up, reaching one hand toward the viewer while the other arm extends outward, surrounded by intense electric arcs. He has {argument name="hair color" default="silvery blue"} messy layered hair with windblown strands, glowing {argument name="eye color" default="electric blue"} eyes, pale skin, a serious determined expression, and a small earring. His outfit is a futuristic high-collar mage coat: glossy black inner clothing, a white outer coat with sharp lapels, dark chains and straps, blue crystal-like glowing accents, and reflective wet-looking highlights. Behind him is one enormous luminous circular magic sigil, made of concentric rings, runic markings, geometric lines, and radial symbols, glowing bright cyan-white. Count exactly 1 magic circle, 1 central character, and many branching lightning bolts radiating from his hands and the circle. The background is a stormy night sky with dark blue clouds split open by a vertical column of blinding white-blue lightning descending behind his head like a halo. Use a cool palette of deep navy, cobalt, cyan, and white, with extreme contrast, bloom, rim lighting, sparkling particles, and cinematic anime rendering. Make the image highly detailed, mystical, powerful, and energetic, with no text, no watermark, and no extra characters.

将附带的角色转换为半身国际象棋棋子。除风格、颜色和材质外，保持所有特征不变。 风格：{argument name="style" default="写实 3DCG"} 颜色：{argument name="color" default="纯象牙白 / 哑光黑"} 材质：{argument name="material" default="宝丽石"}

A cute {argument name="character description" default="miniature blonde girl with long wavy blonde hair"} sitting comfortably on a {argument name="object" default="giant football"} held between large human fingers, exaggerated playful scale contrast, dreamy surreal scene, glossy textures, vibrant colors, soft glowing sky, aesthetic Instagram-style composition, whimsical fantasy realism, hyper-detailed outfit with a {argument name="outfit" default="red top and denim shorts"}, smooth skin, digital art style, slightly exaggerated cute proportions, sharp focus with soft dreamy background.

我想要一张 {argument name="style" default="手绘风格"} 的插画，主体是 {argument name="subject" default="一位在老街拐角处穿着白裙的猫耳少女"}，画面要极其粗犷，甚至可以被解读为一幅抽象画。你能生成一张风格类似 Midjourney 的、具有油画质感的锐利数字插画吗？