自分を、昔のアニメ映画のキャラにしてみない?
ChatGPTに全身の写真を1枚渡すだけ。
服も、抱えてるパンも、連れてる犬もそのまま、
水彩っぽい手描きの1枚になります。
休日の自分が、急に主人公っぽくなる笑
プロンプトはリプ欄に置いておきます。
1
777
プロンプトはこちら👇
ChatGPTに全身の写真を1枚添付して、そのまま貼るだけで使えます(GPT Image 2で作成)
Turn the person in the uploaded photo into a highly detailed, hand-drawn 2D cartoon character illustration in a charming, nostalgic animated movie style.
Character: Keep the person's hairstyle, hair color, glasses or accessories, and overall vibe, but exaggerate the proportions in a playful cartoon way: slightly oversized head, long narrow neck, expressive eyes, a small nose, and a subtle, quirky expression.
Outfit: Keep the outfit from the photo (same colors and items), redrawn in a simple, cozy cartoon way. Keep anything they are holding.
Art Style: Beautiful hand-drawn 2D animation, expressive cartoon anatomy, slightly exaggerated proportions, delicate sketchy black outlines, soft watercolor textures, subtle colored pencil shading, imperfect hand-painted details, warm muted colors, and a nostalgic illustrated storybook aesthetic.
Background: Minimal plain warm ivory textured paper background with subtle grain, no distracting elements.
Composition: Full-body vertical character portrait, character standing naturally in the center, relaxed posture, entire outfit visible, generous negative space around the character.
Lighting and Texture: Soft natural lighting, gentle shadows, matte paper texture, slightly imperfect traditional illustration finish.
Aspect Ratio: 9:16 portrait.
Quality: Extremely detailed character design, polished traditional 2D animation illustration, consistent anatomy, beautiful facial expression, no photorealism, no 3D rendering, no text, no watermark.
754
【旅先の部屋の隠しカメラ、AIに探させた】
海外のエンジニアが、民泊のWi-Fiで
Claude Codeに「つながってる機器」を一覧させた。
防犯カメラ専門メーカーの機器が1台。
本人いわく、正体はベッドの上の火災報知器。
確認は2分。プロンプトはリプ欄に置いておきます。
1
234
プロンプトはこちら👇
Claude Codeを開いて、そのまま貼るだけで使えます
I'm a guest on this Wi-Fi, a hotel room or a rental, not my own place. Help me check the room is private. Look only at the network I'm on, and only list what's there. Don't log in to anything and don't open any video.
List every device you can see: what kind it is, who makes it, and whether it keeps sending data to somewhere outside the building. Point out anything that looks like a camera or a microphone, tell me how sure you are, and roughly where in the room it probably is.
If you find something, tell me not to touch it and help me write a message to the host and to support. If the network keeps guests apart and you can't see other devices, say so, and walk me through the flashlight check: lights off, phone torch slowly across smoke detectors, clocks, chargers and anything facing the bed, watching for a lens glint.
54
【旅先の部屋の隠しカメラ、AIに探させた】
海外のエンジニアが、民泊のWi-Fiで
Claude Codeに「つながってる機器」を一覧させた。
防犯カメラ専門メーカーの機器が1台。
本人いわく、正体はベッドの上の火災報知器。
確認は2分。プロンプトはリプ欄に置いておきます。
224
ChatGPTが、自分のことを何て覚えてるか見たことある?
海外の研究でメモリ2,050件を調べたら、
96%は本人が頼んでいないのに保存されていた。
半分は、性格や悩みについてのメモ。
設定→パーソナライズ→「メモリの概要」で見られます。
ちょっとドキッとするかも笑
101
【人型ロボの家事代行、定期便に】
米Tau Roboticsの人型ロボ。
トイレ掃除から床拭きまで、1体1時間30ドル。
定期で予約できるようにもなった。
ただ公式いわく「人とAIで操作」。
難しいところは、人が遠隔で動かすらしい。
ロボの中の人、ちょっと気になる笑
148
【生まれつき見えない人にも、視覚を】
Neuralinkの「Blindsight」。
カメラの映像を、脳に直接送る。
マスクいわく「技術的には完成。あとは承認待ち」。
ただ、人での結果はまだ公表されていない。
最初は粗い映像から、らしい。
最初に何を見たいか、考えちゃう。
122
昔の写真、8Kにしてみない?
海外のクリエイターが、ChatGPTで
写真を8Kまで引き伸ばす手順を公開。
写真を9枚に切って、写っている物を
理解したうえで描き直すのがミソ。
ただし、1枚10分かかる笑
リプ欄にスキル(ChatGPT/Codex用)を置いておきます。
1
265
プロンプトはこちら👇
下の英文をまるごと、ChatGPT(Work)かCodexに貼ってスキルとして登録 → 写真をアップするだけ。
2回仕上げ(おすすめ)か3回かを聞かれるので答えると、8Kで書き出してくれます。
---
name: flowers-upscale
description: Photo to 8K; 2/3-pass contextual AI crop enhancement and registered blending.
---
INPUT S=uploaded photo; missing→request. Unspecified→ask "2 passes (recommended) or 3? 8K default; another resolution?" Await choice. N=2|3; L=specified longest edge else8192; preserve aspect. Discover available AI image-editing+raster-processing capabilities; missing→report requirement. Use environment-native tools/paths; create helpers as needed. Preserve S; separate outputs. Execute end-to-end after choice.
E(C): inspect; AI-edit inputs=[S=context,C=target], maximum practical supported resolution; retain actual output dimensions. Prompt=Q+only relevant material constraints. Concurrent independent calls where supported; persist outputs+source-coordinate boxes+prompts immediately.
P1: S→3×3 cores; pad each side20% core dimension, clip to S→9 overlapping C→E→register/blend→M1; resize assembled M1 to L.
P2: M1→4–8 padded salient ROIs(face/hair/hands/objects/textiles as present)→E→register/blend→M2. Exclude low-information regions.
N=3: M2→4–8 tighter focal ROIs(individual eyes/lips/nose/fingers/material details as present)→E→register/blend→M3. Keep homologous features consistent. Every E receives S, never crop alone.
Q="1=original: identity/anatomy/color/light authority. 2=target: return exact crop/framing/geometry. Reconstruct plausible photographic detail; preserve expression, pose, contours, clothing, genuine imperfections, focus falloff. Optical clarity; natural edge transitions; spatially varied texture. Repair inherited artifacts. Skin: irregular pores/fine creases, quiet intervals. Hair: cohesive groups, selective fibers, natural sparse fringe. Iris: source color, irregular branching fibers, coherent pupil, restrained reflections. Textiles: original weave direction/spacing/motifs. Avoid invented structures/marks, beautification, relighting, halos, ringing, embossed/crosshatched/repeated texture, synthetic grain, blanket sharpening."
ASSEMBLE: map recorded boxes→master; global similarity registration first; bounded smooth local correction only with reliable correspondence, never distort rigid geometry/repeating patterns. Unreliable→retain prior pixels. Match broad exposure/color without transferring old fine texture. Normalized overlap/multiband blend; feather15–25% border→alpha0 at interior patch boundaries. Preserve native enhanced crops. Before next pass: inspect full image+100% focal/overlap crops; repair doubling/seams/drift/texture mismatch. ≤2 targeted retries/defect; rejected/failed→retain prior content+disclose.
EXPORT: M_N→lossless PNG at L; verify dimensions+decode; deliver file+preview+prompts/settings. Describe detail as reconstructed; distinguish exported resolution from native generated resolution.
69
家族の写真、絵本の表紙にしてみない?
ChatGPTに写真を1枚渡すだけ。
人は画面の下に小さく、まわりは余白たっぷり。
色は4色まで、紙の手ざわりつき。
ふつうの散歩の写真が、
急に「いい話」っぽくなる笑
プロンプトはリプ欄に置いておきます。
1
546
プロンプトはこちら👇
ChatGPTに写真を1枚添付して、下の文をそのまま貼るだけで使えます(GPT Image 2で作成)
Transform the uploaded photo into a minimalist, hand-drawn, paper-textured artistic cover.
Composition
- The main subject should occupy only 10–20% of the frame.
- Position the subject near the bottom center of the composition.
- Leave generous negative space throughout the image.
- Suggest the environment using only a few lines or small blocks of color.
Preserve
- The most recognizable features of the original subject.
- The essential silhouette and proportions.
- The original pose or primary action.
- Important objects and defining details.
- The core story, relationships, and emotional atmosphere.
Color Palette
- Extract the dominant colors from the original photograph.
- Limit the palette to no more than four main colors.
- Use bold yet restrained, flat color blocks.
- Maintain a harmonious, muted color combination.
- Add subtle paper grain and handmade brush textures.
Simplification
Remove unnecessary details and visual clutter. Retain only the essential visual information needed to make the subject instantly recognizable.
Typography
- Optionally incorporate a small amount of simple text.
- Keep typography short, subtle, and aesthetically refined.
- Integrate the text naturally into the composition.
- Aim for the visual language of an art-book cover, independent publishing, modern editorial design, or a contemplative picture book.
- Do not force typography into the image if it doesn't improve the composition.
Style and Materials
- Delicate, slightly imperfect hand-drawn lines.
- A few clearly defined acrylic-like flat color blocks.
- Rough, tactile paper texture.
- Visible handmade brushstrokes.
- Organic, irregular, natural contours.
- Subtle imperfections that make the artwork feel genuinely handmade.
Overall Mood
Quiet, poetic, sophisticated, minimalist, innocent, relaxed, artistic, thoughtful, distinctive, and premium.
Avoid
- Colored-pencil rendering.
- Dry-brush effects.
- Watercolor washes or bleeding.
- Pure line-art illustration.
- Overly detailed or realistic illustrations.
- Heavy impasto or thick oil-paint textures.
- Smooth, polished digital illustration.
- 3D rendering, glossy surfaces, or artificial lighting effects.
- Generic commercial cartoon styles.
- E-commerce advertising aesthetics.
- Generic poster templates.
- Excessive decorative elements.
- Overly complex compositions.
- Too much text.
Final Result: A refined, minimalist, hand-crafted paper illustration with generous negative space, restrained colors, subtle tactile textures, and the sophistication of an independent art-book cover.
130
【ショーケースを1枚撮ったら、全カードに相場がついた】
海外のカード好きが、AIに
「店の写真から相場を出す仕組み」を作らせた。
40枚を2分で査定。
300ドルのリザードンが、
160ドルの復刻版だと見抜いた。
店員さんより詳しい客、誕生笑
493
【FXの自動売買、勝手に売買された】
GMOの自動売買用サーバー
「お名前.com デスクトップクラウド」に
不正なプログラム。対象は2万6739件。
中のログイン情報が抜かれ、
身に覚えのない取引の報告も出ている。
使っていた人は、パスワード変更を今すぐ。
231
【頼む前に、AIから連絡が来る】
Claudeの新アプリ「Claude Duet」。
メールや予定を見張って、
用事がある時だけ向こうから連絡してくる。
送信や支払いの前は、必ず確認つき。
公式いわく、
「急ぎかどうか、まだ見誤ることがある」。
新人の秘書っぽくてかわいい笑
167
【愛車×都道府県で、カーポスター】
車種と地名を入れるだけで、
その土地が車体に溶け込んだ広告ポスターになる。
京都×アルファード、東京×プリウス、千葉×N-BOXで作ってみた。
自分の愛車と地元でやりたくなる笑
プロンプトはリプ欄に👇
1
189
Create a premium cinematic automotive poster featuring [車種], designed as if the vehicle was born from the visual identity of [都道府県], Japan. The car is the hero, shown in a dramatic 3/4 front view, with its body subtly incorporating recognizable local architecture, road markings, textures, materials, and cultural design cues — never as literal decorations, but seamlessly integrated into the vehicle's form.
Surround the car with a minimal, atmospheric version of [都道府県], with iconic architecture appeae. Wet asphalt reflections, realistic headlights, subtle atmospheric haze, dramatic directional lightindeep shadows, fine automoint reflections, lowcamera angle, premium automotive advertising photography.
Poster composition: huge negative space, clean editorial layout, small refitypography reading "BUILTnical specificationsbeneath it, subtle blueprint/grid lines, sophisticated luxury-car magazine aesthetic, muted cinematitrong accent color inspired by the place, ultra-detailed, photorealistic, 8K, no people, no logos, no watermark.
152
【車のメーカーが、家族ロボの予約開始】
中国の自動車大手・奇瑞(チェリー)系AiMOGAが、
家庭用人型ロボ「Mobo」を発表。
身長90cm、20以上の言語を話す。
子どもにはお話と英語の相手、
祖父母には決めた時間のお知らせ。
家にロボ、どれくらいイメージ出来てる?笑
201





















