GPT-image-2 AI画像API
GPT Image 2 は Flatkey の画像生成フローで提供される OpenAI の画像モデルです。/v1/images/generations を使い、送信前に枚数、サイズ、品質、形式、背景、モデレーションを設定します。
出力
プレビュー
リクエスト概要
- エンドポイント
- POST /v1/images/generations
- モデル ID
- GPT-image-2
- アスペクト比
- 4:5
- 解像度
- 1024x1024
- 品質
- high
- 出力数
- 1
プレビューのみです。Flatkey に送信するにはログインしてください。
{
"model": "gpt-image-2",
"prompt": "Goal: Create a luxury fantasy tea advertisement poster for {argument name=\"product name\" default=\"MARINE LUCENT\"}, themed as an oceanic, character-inspired magical tea extracted from an ethereal mermaid-like heroine. The mood is translucent, premium, dreamy, and not a normal cafe menu.\n\nCanvas: Vertical 4:5 high-resolution poster, soft pastel blue, lavender, pearl white, and iridescent aqua palette. Use glossy commercial advertising composition with delicate typography and a high-fashion fantasy tea brand atmosphere.\n\nLayout: Place the main product scene on the right and lower center: a clear glass teapot in the upper-right pours glowing blue-violet tea in a sparkling stream into a transparent glass teacup on a saucer at the lower center. On the left side, create a refined editorial text column with the brand logo at top, product title in large serif letters, subtitle, flavor copy, and ingredient list. Add a pale lavender rectangular placeholder block near the upper-left/center, partially covering the background character art. Keep the whole design airy, luminous, and layered with bokeh, water reflections, and glass highlights.\n\nBackground and subject details: Behind the tea, show a barely visible ethereal anime-style marine princess figure as a soft-focus illustration: long flowing aqua-blue hair, shell and pearl accessories, pale skin, delicate floral/starfish ornaments, translucent fabric, and an underwater fantasy aura. She should feel like the source of the tea’s identity and world, but remain mostly hidden behind mist, glass, and typography.\n\nMain visual: The teapot is round, transparent, crystal-like, and filled with vivid magical tea in gradients of electric blue, cobalt, violet, and cyan. Inside the tea, show exactly 8 visible floating decorative elements: 3 lavender star-shaped flowers, 2 pale pearl-shell spheres, 1 small golden starfish, 1 purple blossom cluster, and 1 cloud of glittering bubbles. The pouring stream should look like liquid starlight, with tiny bubbles and radiant sparkles. The teacup contains the same glowing ocean tea, with suspended flowers, bubbles, shell-like pearls, and refracted light. Add a glass saucer, a small starfish charm, pearls, seashells, crystalline ice-like rocks, and a tiny ornate perfume-bottle-like vessel in the background.\n\nText content: At the top-left, create a diamond monogram logo with the letter “M”, then the brand name “MAISON DE LUMIÈRE” and small line “FINE FANTASY TEA”. Add the tagline in Japanese “彼女の世界を、あなたの一杯に。” and below it “Her world, in your teacup.” Set the product title as large elegant serif text: “{argument name=\"headline text\" default=\"MARINE LUCENT\"}”. Below it add small Japanese reading “マリン・ルーセント”. Add the flavor name “{argument name=\"flavor name\" default=\"AURORA BLUE BLOOM\"}” and Japanese reading “オーロラブルー・ブルーム”. Add a short Japanese body copy block, then English copy: “The sparkle of waves, the dance of bubbles, the gentleness of a clear blue breeze—blended into a tea that is pure, radiant, and enchantingly alive.” Add an ingredient list with exactly 6 items and small matching icons: “BLUE PEA”, “WHITE TEA”, “CORNFLOWER”, “PEARL SHELL”, “CITRUS & PEACH”, and “SEA SALT DROP”, each with smaller Japanese text underneath. At bottom-right, add handwritten script: “{argument name=\"signature phrase\" default=\"Sip the Ocean’s Whisper.\"}” with Japanese “海のささやきを、ひとくちに。” and the brand name “MAISON DE LUMIÈRE”.\n\nVisual style: Ultra-detailed glossy fantasy advertising, premium cosmetics-ad lighting, crystalline glass refractions, shimmering caustics, pearlescent highlights, soft bloom, layered transparency, pastel marine glow, elegant serif typography mixed with delicate script. Make the typography readable and balanced, with the title dominating the left lower half.\n\nConstraints: Use exactly one teapot and one teacup. Use exactly 6 listed ingredient rows. Preserve the luxury tea poster format, do not make it a cafe menu, product package, or character sheet. Avoid extra brand logos, watermarks, QR codes, or unrelated objects.",
"n": 1,
"size": "1024x1024",
"quality": "high",
"output_format": "png",
"background": "opaque",
"moderation": "auto"
}機能
GPT Image 2 API の性能と可用性
Flatkey の GPT Image 2 に関するリクエストテレメトリは、十分なトラフィックがある場合に表示されます。ベンチマークや品質スコアを推測するものではありません。
API
GPT Image 2 API の利用状況とリクエスト活動
このセクションは GPT Image 2 への Flatkey の実際のリクエストを反映します。十分なトラフィックが集まるまでデータは報告されません。
料金
GPT Image 2 の画像入力トークン別料金
以下の料金は、このモデルの Flatkey 料金データと料金 API が返す表示可能グループから計算されます。
クレジットを追加
画像・動画・音声・テキストモデルで同じFlatkey残高とAPIキーを使えます。
- モデルタイプ
- テキストから画像
- API
- /v1/images/generations
- 課金基準
- 画像
- 出力数
- 1–10
GPT Image 2 の画像生成・編集機能
以下は文書化された統合項目です。ベンチマークや品質の約束は推測していません。
テキストから画像生成と編集
/v1/images/generations で新しい画像を生成し、/v1/images/edits で既存画像を編集できます。
参照画像を使った制作
画像コンテキストを使い、商品・編集・キャンペーンの主題と構図を保ちます。
柔軟なビジュアル展開
1つの企画から正方形・縦長・横長の素材を各チャネル向けに展開します。
安全な制作納品
記録された品質、形式、背景、モデレーションの挙動に沿って成果物を整えます。
比較
GPT Image 2 と GPT Image 1:移行項目の比較
以下は文書化された統合項目です。ベンチマークや品質の約束は推測していません。
| 機能 | GPT Image 1 | GPT Image 2 |
|---|---|---|
| エンドポイント | ここでは不明 | /v1/images/generations; /v1/images/edits |
| サイズ | ここでは不明 | 1024x1024, 1536x1024, 1024x1536, auto |
| 形式 | ここでは不明 | PNG, JPEG, WebP |
| 品質/背景/モデレーション | ここでは不明 | 上記に記載 |
| 画像品質の順位 | 主張なし | 主張なし |
統合前に正しいリクエストを選択
対応ワークフロー、現在の費用、Flatkey の正確なパラメータ契約を確認します。
固定単価がある場合、現在の設定とライブ料金から計算します。
- 現在の設定
- 1024x1024 · high · 1×
- ライブ料金
- $0.0088 / 画像
- リクエスト見積もり
- $0.0088
最終料金は送信内容とアカウントグループに従います。トークン・段階料金は固定額にできません。
ワークフローと Model ID
利用可能なものだけを使用します。公開モデル ID は共通で、入力方式はリクエスト本文で選択します。
テキストから画像
テキストから新しい画像を生成します。
- モデル ID
gpt-image-2- エンドポイント
/v1/images/generations
参照画像による生成
参照画像で編集やバリエーションを作ります。
- モデル ID
gpt-image-2- エンドポイント
/v1/images/generations
パラメータ互換性
Playground と同じモデル設定に基づく値です。
n画像数1–10
既定値: 1sizeサイズ1024x1024 · 1536x1024 · 1024x1536 · auto
既定値: 1024x1024quality品質auto · high · medium · low
既定値: highoutput_format出力形式png · jpeg · webp
既定値: pngbackground背景opaque · auto
既定値: opaquemoderationモデレーションauto · low
既定値: autoimage参照上限4 ファイル
エンドポイント: /v1/images/generations初回テストから本番へ
Playground と API で同じ契約を使い、検証、残高、状態、結果取得を明示的に処理します。
リクエストの流れ
- 1
モデル、プロンプト、参照、出力を検証。
- 2
画像リクエストを送信。
- 3
結果または非同期タスクを取得。
- 4
ファイルとメタデータを保存。
本番チェック
非対応の値や参照数を送信前に拒否します。
キー、残高、制限、グループ料金を分けて処理します。
交換すべきプロンプトや素材を明示します。
task ID を保持し、再試行を制限し、成功扱いしません。
プロンプトライブラリ
GPT Image 2 の商品・マーケティング向けプロンプト例
具体的な被写体、動作、カメラまたは構図と出力設定から始め、リクエスト項目はプロンプトとは別に指定します。
Image 2 で生成
Scene: A 16:9 sci-fi game loadout screen in a blue-purple spaceship hangar. A female armored character stands centered with a glowing violet rifle; armor slots line the left, three weapon slots line the right, and the lower slot is highlighted. Keep the HUD hierarchy, pose, lighting, and equipment geometry fixed for an exact equipment-switch frame. No readable words, logos, invented stats, or watermark. Composition and rendering: Deliver one 16:9 game-interface keyframe. Separate the character, held equipment and HUD into clear depth layers; keep slot spacing and icon scale consistent, with the selected item visually dominant. Preserve the scene-specific game art style. Let material edges catch the existing light without letting interface glow obscure the silhouette. Keep all equipment fully inside the frame. Avoid: warped perspective, malformed anatomy, merged objects, inconsistent shadows, excessive sharpening and watermarks. Follow the scene-specific text and branding restrictions above.
Image 2 で生成
Scene: A rainy night soccer broadcast frame under bright stadium floodlights. A black-uniform player strikes the ball while two white-uniform defenders close in, with the goal and a blurred crowd behind. Keep the broadcast camera angle, blank blue score bars, spray, and motion blur consistent; leave overlays abstract and text-free. No real teams, athletes, logos, or watermark. Composition and rendering: Deliver one 16:9 broadcast still at the decisive instant. Use coherent perspective for the playing surface and equipment, readable separation between competitors, and a softer crowd behind the action. Keep the principal subject sharp, with directional blur limited to fast extremities and spray. Preserve the specified broadcast angle and reserve overlay areas clear of the action. Avoid: warped perspective, malformed anatomy, merged objects, inconsistent shadows, excessive sharpening and watermarks. Follow the scene-specific text and branding restrictions above.
Image 2 で生成
Scene: A closed matte-black square smartwatch with a black strap rests on a wet glossy black tabletop. Water droplets catch a cool blue rim light and a soft reflection sits beneath the watch. Use a low three-quarter product camera and preserve the case, strap, highlights, and empty dark background. No readable branding, extra products, hands, or watermark. Composition and rendering: Deliver one 16:9 commercial product still. Keep the complete product silhouette inside generous crop-safe margins. Resolve edges, seams and material transitions precisely; shape highlights to describe volume without clipping bright surfaces or crushing dark details. Align reflections with the object and light source. Retain the stated camera angle and existing negative space; add no decorative props. Avoid: warped perspective, malformed anatomy, merged objects, inconsistent shadows, excessive sharpening and watermarks. Follow the scene-specific text and branding restrictions above.
Image 2 で生成
Scene: On a rain-soaked observatory roof at sunrise, a lone figure in a long dark coat walks toward a large telescope beside an open dome. Wet stone reflects the warm doorway light; cloud-covered mountains sit beyond. Hold the screen direction and end on the telescope and figure in the same wide composition. No readable text, logos, or watermark. Composition and rendering: Deliver one 16:9 storyboard keyframe, not a collage or an action sequence. Separate foreground, character plane and background through the existing light and atmospheric depth. Keep the stated pose and eyelines readable, and retain environmental landmarks for continuity. Match the described photographic, illustrated or puppet medium; give fabric and surfaces texture appropriate to that medium. Avoid: warped perspective, malformed anatomy, merged objects, inconsistent shadows, excessive sharpening and watermarks. Follow the scene-specific text and branding restrictions above.
Image 2 で生成
Scene: In a bright home kitchen, a surprised cook in a blue shirt and cream apron reaches toward pancakes, a frying pan, flour, bowl, and whisk suspended midair. Freeze the comic cause-and-effect moment with believable weight, warm daylight, and a clear path for each object. No injury, logos, readable words, or watermark. Composition and rendering: Deliver one 16:9 physical-comedy still at the described instant. Make the cause of the gag readable through body balance, grip and object spacing. Separate the reaction from the airborne props; retain believable gravity and contact points. Keep the face and important props sharp, with only restrained directional blur on fast edges. Preserve the stated lighting and room or stage layout. Avoid: warped perspective, malformed anatomy, merged objects, inconsistent shadows, excessive sharpening and watermarks. Follow the scene-specific text and branding restrictions above.
Image 2 で生成
Scene: A rainy period harbor platform shelters people in era-appropriate coats and umbrellas as a vintage green tram arrives on wet tracks. Wooden waterfront buildings and misty mountains sit behind the reflections. Preserve the historical clothing, tram shape, rain direction, and stable wide composition; no readable signage, logos, or watermark. Composition and restoration: Deliver one 16:9 archival-style still. Preserve the original framing, period-specific construction and restrained tonal range; retain monochrome, sepia or faded color as described. Recover modest detail in faces, clothing and architecture without synthetic sharpening. Keep fine grain and authentic aging consistent across the frame; repair damage without replacing historical features. Avoid: warped perspective, malformed anatomy, merged objects, inconsistent shadows, excessive sharpening and watermarks. Follow the scene-specific text and branding restrictions above.
Flatkey を選ぶ理由
GPT Image 2 を Flatkey で使う理由
テストから本番へ移行する間も、GPT Image 2 の事実、リクエスト項目、料金の境界を確認できます。
文書化された設定を集約
コンソールに渡す前に n、size、quality、output format、background、moderation を設定します。
料金項目を明確に表示
GPT Image 2 の入力・出力・キャッシュの各項目を確認し、見出しの価格を一律料金とみなさないでください。
用途別の出発点
商品、広告、絵コンテの例を編集可能なプロンプトの出発点として使います。
未確認の約束をしない
確認されていない事実について、透明な出力、無料生成、固定の画像単価を約束しません。
API
GPT Image 2 API のエンドポイントとリクエスト設定
モデル ID と対応する画像設定を一緒に送信します。
curl https://router.flatkey.ai/v1/images/generations \ -H "Content-Type: application/json" \ -H "Authorization: Bearer sk-***" \ -d '{"model":"gpt-image-2","prompt":"Creative direction: Create a vertical illustrated fantasy narrative poster with a large dark-haired profile silhouette on the left, a layered mountain temple city in the center, a red torii gate, drifting cherry blossoms, and small travelers along the bottom edge. Use a cream paper texture with ink-and-wash detail, a restrained charcoal, vermilion, and muted violet palette, and reserve a clean right margin for the title and credits.\n\nComposition, material and finish: Build the silhouette and temple city as nested visual layers, with the gate as the vermilion focal accent. Keep small travelers distinct from architectural detail. Use delicate ink edges and paper grain rather than photographic skin or glossy 3D surfaces. Leave the right title margin genuinely empty; avoid added lettering, duplicated gates, muddied silhouettes and watermarks.","n":1,"size":"1024x1024","quality":"high","output_format":"png","background":"opaque","moderation":"auto"}'
よくある質問
GPT Image 2
API: 料金とプロンプトの質問
料金、互換性、制限、モデル固有のリクエスト情報。





