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
- 5:7
- 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": "Design a high-end e-commerce pastry packaging solution for [Brand Name] that can be mass-produced. The product name is [Product Name], the product type is [Pastry Type], the brand positioning is [Brand Positioning], and the target audience is [Target Users]. Packaging types include [Heaven-and-Earth Lid Gift Box / Drawer Box / Window Color Box / Handheld Gift Box / Magnetic Gift Box / Color Box / Paper Tube / Soft Bag / E-commerce Shipping Gift Box]. The finished product dimensions are [Length × Width × Height mm]. Internal specifications are [quantity] pieces or [combination pack], and each piece is specified as [Single Weight or Size]. \n\nPlease design a professional-grade high-end e-commerce pastry packaging design proposal board. Overall, it must meet international packaging design award-level standards, combining brand recognition, main e-commerce image appeal, shelf display effect, gift value, structural rationality, printability, transportation protection, and factory mass production feasibility.\n\nThe overall style is [Oriental New Luxury / Minimalist and Sophisticated / Natural Organic / Young National Trend / New Chinese Elegance / Vintage Collection / Holiday Gifts / Light Luxury Souvenirs / French Dessert Style / Japanese Minimalist / Regional Culture Style]. The visual temperament should be high-end, refined, clean, appetizing, and have brand memorability, avoiding a sense of cheapness, clutter, and template-like feeling. The color scheme should focus on the main color, paired with auxiliary colors and accent colors. The overall color should match the product's taste, brand positioning, and gifting scenario.\n\nThe image is a horizontal professional packaging design proposal board, clearly divided into zones, with advanced layout, reasonable white space, and complete information. It includes: main visual 3D packaging rendering, front of packaging, back of packaging, left left, right right, top top, bottom bottom, internal structure of unboxing, cake tray display, complete unfolding knife pattern diagram, dimensioning, line pattern legend, material description, printing process description, partial process enlargement drawing, color scheme, font scheme, and manufacturer production information.\n\nThe main visual 3D packaging rendering should show the packaging box from a 45° stereoscopic perspective, with authentic packaging materials, delicate paper texture, clear box thickness, reasonable structure, and soft, high-end light and shadow. Surrounding items can be arranged with real pastries, ingredients, tea sets, plates, wooden trays, ribbons, flowers, grains, nuts, fruits, cream, sesame, egg yolks, red beans, cocoa, honey, wheat ears, festive elements, or regional cultural elements to create a high-end e-commerce main image. The color and shape of the pastries must match the specific product type and are not limited to green.\n\nThe front design must include the brand name, product name, English auxiliary name, core selling points, net content, specification information, brand symbol, and main visual design. The main visual can use pastry photography, illustrations, patterns, window structures, oriental graphics, regional cultural symbols, raw material graphics, abstract brand symbols, or holiday designs. The composition needs to be strongly memorable, suitable for e-commerce thumbnail clicks.\n\nThe back design must include the product name, ingredient list, allergen warnings, nutrition facts sheet, production information, storage methods, consumption recommendations, standards, production license number, manufacturer information, barcode, QR code, environmental label, and a reserved area for the production batch number. The information hierarchy is clear, and the layout is authentic and trustworthy. The left and right sides should include the brand slogan, product series name, flavor label, unboxing direction, decorative patterns, or brand auxiliary graphics. The top displays brand symbols, gift box opening methods, sealing structures, or main visual extension patterns. The bottom displays the folded structure, production batch number location, environmental label, or simplified information area.\n\nThe internal structure display must include food-grade PET trays, eco-friendly pulp trays, paper card partitions, individual small boxes, individual packaging bags, or greaseproof paper linings. Each pastry is placed independently, ensuring shock resistance, pressure resistance, flavor transfer, oil stain resistance, and e-commerce transportation safety. The pastries have realistic shapes and appetizing appeals, with naturally sophisticated colors.\n\nThe unfolding tool diagram must show the complete packaging unfolding structure, including front, back, left and right sides, top, bottom, tongue insert, latch, adhesive position, window area, internal tray diagram, barcode QR code position, size marking, and process layout. The die diagram must resemble the actual packaging engineering drawing, with accurate proportions and clear lines, making it suitable for manufacturer sample reference.\n\nThe die drawing must be clear, professional, and mass-producible, with all units in mm. Line type legends must be annotated: Red solid line = cutting line / cutting line; Blue dashed line = indentation line / polyline; Green line = bleeding line; Purple line = safety line; Gray line = reference line, not printed; Yellow area = adhesive position; Translucent light blue area = food-grade PET window area; Gold area = hot stamping edition; Bright white area = partial UV version; Embossed shadow area = bump / recess area.\n\nSize standard: bleeding 3 mm per side; Safety margin 5 mm; Dimensional tolerance ±1 mm; Die-cutting tolerance ±0.5 mm; Printing nest tolerance ±0.3 mm; Barcode areas must be clearly marked with a white background; QR codes must be reserved in the scanning safe area; The food label information area must be clear and legible; All folds, tongue inserts, adhesive points, and window areas must be clearly marked.\n\nMaterial recommendations: [350g food-grade white card paper / 400g food-grade white card paper / specialty paper / grayboard mounting / kraft paper / eco-friendly pulp / biodegradable paper tray / food-grade PET / food-grade oilproof paper / aluminum foil inner bag / individual small packaging]. The food-contact section must use food-grade materials, and e-commerce transportation must consider pressure resistance, shock resistance, moisture resistance, oil stain resistance, and odor transfer.\n\nPrinting method: CMYK four-color printing, with Pantone spot colors, metal spot colors, and special plate processes available. Surface Processing: [Matte Film / Glossy Film / Tactile Film / Localized UV / Hot Stamping / Silver Hot Stamping / Rose Gold Hot Stamping / Embossing / Embossing / Embossing / Pearlescent Ink / Spot Color Printing / Food-Grade Eco-friendly Ink].\n\nThe partial process enlargement should display the logo stamping, brand name accents, product name partial UV exposure, paper embossing, illustration details, window PET frame, lock structure, inner tray details, and food label information area. The color scheme should display the main color, secondary color, accent color, and indicate the Pantone color code, CMYK value, RGB value, or approximate color value. The font scheme should display the brand's Chinese font, product name font, English auxiliary font, numeric font, and information font.\n\nOverall image requirements: award-winning pastry packaging design, premium bakery packaging, high-end confectionery packaging, luxury e-commerce dessert gift box, production-ready packaging blueprint, manufacturer-ready dieline layout, structural packaging engineering drawing, realistic paper texture, refined typography, premium brand identity system, elegant food packaging design, photorealistic 3D packaging mockup, detailed printing process annotations, CMYK print-ready layout, Pantone color system, gold foil stamping, embossed logo, debossed texture, spot UV details, food-grade PET window, inner tray structure, sustainable food packaging, premium gift box design, clean white studio background, soft natural lighting, ultra detailed, high resolution, commercial product design board",
"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。





