按模态浏览 PROMPTS

图像 Prompts — 1438 个精选示例

面向 图像 生成工作流的 prompt 示例。按分类筛选,复制 prompt,或打开模型专属 API 代码。

IM
图像
Illustration & 3D gpt-image-2

{ "global_settings": { "resolution": "8K", "qualit...

{ "global_settings": { "resolution": "8K", "quality": "ultra-high definition", "aspect_ratio": "2:3", "render_style": "AI-edited, high-detail 3D render", "lighting_quality": "soft studio lighting with realistic shadows", "sharpness": "extreme clarity, crisp edges", "noise": "none", "compression": "none" }, "Module_1_Image_1_Style": { "subject": { "character_type": "stylized 3D cartoon female", "pose": "standing, body slightly angled, one hand raised with index finger touching lips", "expression": "cheerful smile, wide eyes", "hair": { "color": "black", "style": "two braided pigtails", "accessories": "green cap" }, "face": { "eyes": "large, rounded, dark pupils", "skin": "smooth, matte, stylized texture" } }, "clothing": { "top": "sleeveless green crop top", "bottom": "loose green jogger-style pants with drawstring", "footwear": "white sneakers" }, "accessories": { "luggage": "green hard-shell suitcase with extended handle" }, "color_palette": [ "multiple shades of green", "white accents" ], "background": { "color": "solid green", "texture": "soft, slightly grainy studio backdrop" }, "composition": { "framing": "full body", "camera_angle": "eye-level", "depth": "subject sharply separated from background" } }, "Module_2_Image_2_Style": { "subject": { "character_type": "stylized 3D cartoon female", "pose": "leaning slightly backward against background", "expression": "playful, lips slightly pursed, eyes looking sideways", "hair": { "color": "brown", "style": "short, tousled", "accessories": "red sunglasses resting on head" } }, "clothing": { "dress": "form-fitting blue ribbed dress with thin straps", "footwear": "red high-heel sandals with bow detail" }, "color_palette": [ "bold red", "deep blue" ], "background": { "color": "solid red", "texture": "smooth matte surface" }, "lighting": { "direction": "soft directional light from one side", "shadow": "defined shadow cast on red background" }, "composition": { "framing": "full body", "pose_emphasis": "curved posture, crossed legs" } }, "Module_3_Image_3_Style": { "subject": { "characters": [ { "type": "stylized 3D cartoon female", "position": "left", "wrapped_in": "red textured blanket", "expression": "calm, slight smile, eyes looking upward" }, { "type": "stylized 3D cartoon male", "position": "right", "wrapped_in": "orange textured blanket", "expression": "neutral, gentle gaze upward" } ] }, "environment": { "furniture": "red sofa", "floor": "red surface", "background": { "color": "deep red", "texture": "fabric-like horizontal texture" } }, "details": { "feet": "female barefoot, male wearing socks", "blanket_texture": "thick, knitted fabric" }, "composition": { "framing": "centered, medium-wide shot", "symmetry": "balanced left and right composition" } },

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "{ \"global_settings\": { \"resolution\": \"8K\", \"quality\": \"ultra-high definition\", \"aspect_ratio\": \"2:3\", \"render_style\": \"AI-edited, high-detail 3D render\", \"lighting_quality\": \"soft studio lighting with realistic shadows\", \"sharpness\": \"extreme clarity, crisp edges\", \"noise\": \"none\", \"compression\": \"none\" }, \"Module_1_Image_1_Style\": { \"subject\": { \"character_type\": \"stylized 3D cartoon female\", \"pose\": \"standing, body slightly angled, one hand raised with index finger touching lips\", \"expression\": \"cheerful smile, wide eyes\", \"hair\": { \"color\": \"black\", \"style\": \"two braided pigtails\", \"accessories\": \"green cap\" }, \"face\": { \"eyes\": \"large, rounded, dark pupils\", \"skin\": \"smooth, matte, stylized texture\" } }, \"clothing\": { \"top\": \"sleeveless green crop top\", \"bottom\": \"loose green jogger-style pants with drawstring\", \"footwear\": \"white sneakers\" }, \"accessories\": { \"luggage\": \"green hard-shell suitcase with extended handle\" }, \"color_palette\": [ \"multiple shades of green\", \"white accents\" ], \"background\": { \"color\": \"solid green\", \"texture\": \"soft, slightly grainy studio backdrop\" }, \"composition\": { \"framing\": \"full body\", \"camera_angle\": \"eye-level\", \"depth\": \"subject sharply separated from background\" } }, \"Module_2_Image_2_Style\": { \"subject\": { \"character_type\": \"stylized 3D cartoon female\", \"pose\": \"leaning slightly backward against background\", \"expression\": \"playful, lips slightly pursed, eyes looking sideways\", \"hair\": { \"color\": \"brown\", \"style\": \"short, tousled\", \"accessories\": \"red sunglasses resting on head\" } }, \"clothing\": { \"dress\": \"form-fitting blue ribbed dress with thin straps\", \"footwear\": \"red high-heel sandals with bow detail\" }, \"color_palette\": [ \"bold red\", \"deep blue\" ], \"background\": { \"color\": \"solid red\", \"texture\": \"smooth matte surface\" }, \"lighting\": { \"direction\": \"soft directional light from one side\", \"shadow\": \"defined shadow cast on red background\" }, \"composition\": { \"framing\": \"full body\", \"pose_emphasis\": \"curved posture, crossed legs\" } }, \"Module_3_Image_3_Style\": { \"subject\": { \"characters\": [ { \"type\": \"stylized 3D cartoon female\", \"position\": \"left\", \"wrapped_in\": \"red textured blanket\", \"expression\": \"calm, slight smile, eyes looking upward\" }, { \"type\": \"stylized 3D cartoon male\", \"position\": \"right\", \"wrapped_in\": \"orange textured blanket\", \"expression\": \"neutral, gentle gaze upward\" } ] }, \"environment\": { \"furniture\": \"red sofa\", \"floor\": \"red surface\", \"background\": { \"color\": \"deep red\", \"texture\": \"fabric-like horizontal texture\" } }, \"details\": { \"feet\": \"female barefoot, male wearing socks\", \"blanket_texture\": \"thick, knitted fabric\" }, \"composition\": { \"framing\": \"centered, medium-wide shot\", \"symmetry\": \"balanced left and right composition\" } },"
}
JSON
IM
图像
Illustration & 3D gpt-image-2

A handcrafted felt miniature illustration of [Celebrity] rei...

A handcrafted felt miniature illustration of [Celebrity] reimagined as a soft wool doll character. The figure has simplified facial features, button-like eyes, subtle smile, and carefully crafted felt textures. He is wearing an outfit inspired by his iconic casual tech style—dark jacket, simple t-shirt, and trousers—recreated in knitted wool and fabric. The scene has a whimsical, storybook feel with grassy felt terrain, pastel hills, and a bright sky with soft clouds. Macro photography look, shallow depth of field, soft natural lighting, stop-motion animation aesthetic, ultra-detailed fibers and fabric textures, cozy yet futuristic mood, cinematic composition, high quality.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "A handcrafted felt miniature illustration of [Celebrity] reimagined as a soft wool doll character. The figure has simplified facial features, button-like eyes, subtle smile, and carefully crafted felt textures. He is wearing an outfit inspired by his iconic casual tech style—dark jacket, simple t-shirt, and trousers—recreated in knitted wool and fabric. The scene has a whimsical, storybook feel with grassy felt terrain, pastel hills, and a bright sky with soft clouds. Macro photography look, shallow depth of field, soft natural lighting, stop-motion animation aesthetic, ultra-detailed fibers and fabric textures, cozy yet futuristic mood, cinematic composition, high quality."
}
JSON
IM
图像
Illustration & 3D gpt-image-2

Transform the input photo into a refined monochromatic ink p...

Transform the input photo into a refined monochromatic ink portrait on a pure white background. Clean side profile facing left, preserving exact facial identity and proportions. Soft charcoal-gray ink with subtle tonal variation, controlled splatter accents, delicate watercolor diffusion, and faint mist-like dispersion along the edges.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "Transform the input photo into a refined monochromatic ink portrait on a pure white background. Clean side profile facing left, preserving exact facial identity and proportions. Soft charcoal-gray ink with subtle tonal variation, controlled splatter accents, delicate watercolor diffusion, and faint mist-like dispersion along the edges."
}
JSON
IM
图像
Illustration & 3D gpt-image-2

Create an ultra-HD, hyper-realistic digital poster of a floa...

Create an ultra-HD, hyper-realistic digital poster of a floating miniature island shaped like [Country], resting on white clouds in the sky. Blend iconic landmarks, natural landscapes (like [landmark 1], [landscape 2], or [landscape 3]), and cultural elements unique to [Country]. Carve "[Country]" into the terrain using large white 3D letters. Add artistic details like [wildlife], cinematic lighting, vivid colors, aerial perspective, and sun reflections to enhance realism

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "Create an ultra-HD, hyper-realistic digital poster of a floating miniature island shaped like [Country], resting on white clouds in the sky. Blend iconic landmarks, natural landscapes (like [landmark 1], [landscape 2], or [landscape 3]), and cultural elements unique to [Country]. Carve \"[Country]\" into the terrain using large white 3D letters. Add artistic details like [wildlife], cinematic lighting, vivid colors, aerial perspective, and sun reflections to enhance realism"
}
JSON
IM
图像
Illustration & 3D gpt-image-2

Minimalist food photograph, [1080x1080] – a single [FOOD] re...

Minimalist food photograph, [1080x1080] – a single [FOOD] rests on a light, matte surface and is captured mid-transformation into a 3D pixelized form: one half remains intact while the other organically fragments into large, floating cubes that drift outward, each cube revealing the object’s texture, ingredients, and colors. Studio lighting with soft, realistic shadows, shallow depth of field, tasteful perspective and composition, hyperrealistic detail, stylish geometric abstraction, subtle motion blur on the cubes, high resolution, cinematic close-up.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "Minimalist food photograph, [1080x1080] – a single [FOOD] rests on a light, matte surface and is captured mid-transformation into a 3D pixelized form: one half remains intact while the other organically fragments into large, floating cubes that drift outward, each cube revealing the object’s texture, ingredients, and colors. Studio lighting with soft, realistic shadows, shallow depth of field, tasteful perspective and composition, hyperrealistic detail, stylish geometric abstraction, subtle motion blur on the cubes, high resolution, cinematic close-up."
}
JSON
IM
图像
Illustration & 3D gpt-image-2

{ "type": "image_generation", "style": "hyper_realistic"...

{ "type": "image_generation", "style": "hyper_realistic", "quality": "8K DSLR", "aspect_ratio": "4:5", "camera": { "angle": "slightly tilted cinematic perspective", "lens": "50mm DSLR", "depth_of_field": "shallow", "focus": "smartphone and football action" }, "scene": { "setting": "smartphone placed on a wooden table", "concept": "phone screen transformed into a miniature football stadium", "environment": "indoor, soft daylight coming from the side", "atmosphere": "cinematic, immersive, realistic" }, "details": { "screen": "weathered green football pitch with visible wear, dirt patches, and grass texture", "players": "miniature football players actively playing a match with dynamic poses", "lighting": "soft diffused daylight with subtle lens flares and realistic reflections", "realism_effects": [ "fingerprints on screen", "light scratches on phone body", "natural smudges", "micro dust particles" ] }, "materials": { "phone": "metallic frame with realistic reflections", "table": "textured wooden surface with warm tones" }, "mood": "high-end cinematic, dramatic, premium advertising look", "rendering": { "sharpness": "ultra sharp", "texture_detail": "extreme", "lighting_quality": "studio grade", "photorealism": true } }

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "{ \"type\": \"image_generation\", \"style\": \"hyper_realistic\", \"quality\": \"8K DSLR\", \"aspect_ratio\": \"4:5\", \"camera\": { \"angle\": \"slightly tilted cinematic perspective\", \"lens\": \"50mm DSLR\", \"depth_of_field\": \"shallow\", \"focus\": \"smartphone and football action\" }, \"scene\": { \"setting\": \"smartphone placed on a wooden table\", \"concept\": \"phone screen transformed into a miniature football stadium\", \"environment\": \"indoor, soft daylight coming from the side\", \"atmosphere\": \"cinematic, immersive, realistic\" }, \"details\": { \"screen\": \"weathered green football pitch with visible wear, dirt patches, and grass texture\", \"players\": \"miniature football players actively playing a match with dynamic poses\", \"lighting\": \"soft diffused daylight with subtle lens flares and realistic reflections\", \"realism_effects\": [ \"fingerprints on screen\", \"light scratches on phone body\", \"natural smudges\", \"micro dust particles\" ] }, \"materials\": { \"phone\": \"metallic frame with realistic reflections\", \"table\": \"textured wooden surface with warm tones\" }, \"mood\": \"high-end cinematic, dramatic, premium advertising look\", \"rendering\": { \"sharpness\": \"ultra sharp\", \"texture_detail\": \"extreme\", \"lighting_quality\": \"studio grade\", \"photorealism\": true } }"
}
JSON
IM
图像
Illustration & 3D gpt-image-2

Present a clear, 45° top-down isometric miniature 3D cartoon...

Present a clear, 45° top-down isometric miniature 3D cartoon diorama of the [BRAND], with soft refined textures, realistic PBR materials, and gentle lifelike lighting. Create a small raised diorama-style base that includes the most recognizable elements of the store, along with tiny stylized characters if needed (no facial details). Use a clean solid [BACKGROUND COLOR] background. At the top-center, display [BRAND] in large bold text, and place the official logo associated with [BRAND] below the subtext. All text must automatically match the background contrast (white or black). Composition: perfectly centered layout, square 1080x1080, ultra-clean, high-clarity diorama aesthetic.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "Present a clear, 45° top-down isometric miniature 3D cartoon diorama of the [BRAND], with soft refined textures, realistic PBR materials, and gentle lifelike lighting. Create a small raised diorama-style base that includes the most recognizable elements of the store, along with tiny stylized characters if needed (no facial details). Use a clean solid [BACKGROUND COLOR] background. At the top-center, display [BRAND] in large bold text, and place the official logo associated with [BRAND] below the subtext. All text must automatically match the background contrast (white or black). Composition: perfectly centered layout, square 1080x1080, ultra-clean, high-clarity diorama aesthetic."
}
JSON
IM
图像
Illustration & 3D gpt-image-2

【テーマ】 {ここにテーマを入力} 【写真】 {ここに使用する写真の内容を簡潔に入力} (例:公園で遊ぶ子ども / 親...

【テーマ】 {ここにテーマを入力} 【写真】 {ここに使用する写真の内容を簡潔に入力} (例:公園で遊ぶ子ども / 親子の笑顔 / 走る子ども など) 【タイトル】 {画像内に入れるタイトルを入力} (例:こどもの日 / Happy Mother's Day / 春のはじまり など) --- テーマ「{テーマ}」に基づいた、 写真とクレヨンイラストを融合したライフスタイル系エディトリアルビジュアル。 提供された写真をメインビジュアルとして使用する。 ■ シーン 「{写真}」に合った自然な日常の瞬間。 作り込みすぎないリアルな空気感、やわらかい自然光、 人物の自然な動きや感情を重視。 ■ 構図 人物を切り抜いたように配置し、 ざらっとした紙質のクラフト系背景 (生成り、ベージュ、淡いグレー、ミルクティー)の上にレイアウト。 ・余白50%以上 ・左右非対称構図 ・抜け感のあるミニマルなエディトリアルデザイン ■ イラスト(最重要) オイルパステル/クレヨンで描いたような、 ざらつきとかすれのある手描きイラストを重ねる。 ▼ルール ・全体の30〜40%以内 ・線にムラとかすれ、紙のテクスチャが残る ・力の入り具合で濃淡が変化(濃い部分・薄い部分が混在) ・子どもが描いたような少し不器用なタッチ ・影・立体表現は禁止(フラット) ・人物の動きと連動させる(風・軌跡・流れ) ▼モチーフ(テーマ連動) ・{テーマ}を象徴する要素をクレヨンタッチで追加 (例:こどもの日 → 鯉のぼり、風、空、草、雲、紙かぶと) ・風の線、動きの線、小さなアイコン、太陽、雲、お花、ハート、星、ジグザグの動線 ・空気感をクレヨンの粗いストロークで演出 ■ タイトル文字(重要) 画像内に「{タイトル}」を手描きクレヨン文字で配置する。 ・配置は左上または右上の余白部分 ・クレヨンで書いたようなざらつき・かすれのある文字 ・少し不器用で味のある手書き風 ・文字色はアースカラー(テラコッタ、マスタード、ダークブラウン)から選択 ・サイズは控えめでミニマルに(主役は写真) ・装飾枠なし、フラット ■ 色 あたたかみのあるアースカラー、 やわらかいくすみカラー (テラコッタ、マスタード、オリーブ、ミルクティー、淡いブルー) ■ 雰囲気 あたたかい、ノスタルジック、こども心、ハンドメイド感、 やさしい、エモーショナル、ストーリー性のある日常 ■ スタイル 絵本的ぬくもり × 北欧ミニマル × 上質なライフスタイル広告 ■ 品質 高解像度、商用レベルのクオリティ

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "【テーマ】 {ここにテーマを入力} 【写真】 {ここに使用する写真の内容を簡潔に入力} (例:公園で遊ぶ子ども / 親子の笑顔 / 走る子ども など) 【タイトル】 {画像内に入れるタイトルを入力} (例:こどもの日 / Happy Mother's Day / 春のはじまり など) --- テーマ「{テーマ}」に基づいた、 写真とクレヨンイラストを融合したライフスタイル系エディトリアルビジュアル。 提供された写真をメインビジュアルとして使用する。 ■ シーン 「{写真}」に合った自然な日常の瞬間。 作り込みすぎないリアルな空気感、やわらかい自然光、 人物の自然な動きや感情を重視。 ■ 構図 人物を切り抜いたように配置し、 ざらっとした紙質のクラフト系背景 (生成り、ベージュ、淡いグレー、ミルクティー)の上にレイアウト。 ・余白50%以上 ・左右非対称構図 ・抜け感のあるミニマルなエディトリアルデザイン ■ イラスト(最重要) オイルパステル/クレヨンで描いたような、 ざらつきとかすれのある手描きイラストを重ねる。 ▼ルール ・全体の30〜40%以内 ・線にムラとかすれ、紙のテクスチャが残る ・力の入り具合で濃淡が変化(濃い部分・薄い部分が混在) ・子どもが描いたような少し不器用なタッチ ・影・立体表現は禁止(フラット) ・人物の動きと連動させる(風・軌跡・流れ) ▼モチーフ(テーマ連動) ・{テーマ}を象徴する要素をクレヨンタッチで追加 (例:こどもの日 → 鯉のぼり、風、空、草、雲、紙かぶと) ・風の線、動きの線、小さなアイコン、太陽、雲、お花、ハート、星、ジグザグの動線 ・空気感をクレヨンの粗いストロークで演出 ■ タイトル文字(重要) 画像内に「{タイトル}」を手描きクレヨン文字で配置する。 ・配置は左上または右上の余白部分 ・クレヨンで書いたようなざらつき・かすれのある文字 ・少し不器用で味のある手書き風 ・文字色はアースカラー(テラコッタ、マスタード、ダークブラウン)から選択 ・サイズは控えめでミニマルに(主役は写真) ・装飾枠なし、フラット ■ 色 あたたかみのあるアースカラー、 やわらかいくすみカラー (テラコッタ、マスタード、オリーブ、ミルクティー、淡いブルー) ■ 雰囲気 あたたかい、ノスタルジック、こども心、ハンドメイド感、 やさしい、エモーショナル、ストーリー性のある日常 ■ スタイル 絵本的ぬくもり × 北欧ミニマル × 上質なライフスタイル広告 ■ 品質 高解像度、商用レベルのクオリティ"
}
JSON
IM
图像
Illustration & 3D gpt-image-2

Extreme close-up macro of miniature city diorama [CITY, COUN...

Extreme close-up macro of miniature city diorama [CITY, COUNTRY] on a solid base, held between two human fingers. City fills 85–95% of frame. [COUNTRY] national flag stands prominently on flagpole in mid-ground, fully readable, gently waving—primary visual anchor. [ICONIC LANDMARK] positioned in clear foreground, unobstructed, instantly recognizable, naturally integrated. Small street sign or plaque displays “[CITY NAME]” as authentic urban detail, positioned organically at street corner or plaza edge. Surrounding architecture reflects city’s authentic character without oversizing elements. Ultra-realistic handcrafted miniature, detailed architecture, realistic materials, accurate proportions. Macro lens, deep depth of field keeping entire city sharp. Soft studio lighting, subtle shadows, tilt-shift realism. Neutral softly blurred background. Photorealistic, cinematic, premium quality.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "Extreme close-up macro of miniature city diorama [CITY, COUNTRY] on a solid base, held between two human fingers. City fills 85–95% of frame. [COUNTRY] national flag stands prominently on flagpole in mid-ground, fully readable, gently waving—primary visual anchor. [ICONIC LANDMARK] positioned in clear foreground, unobstructed, instantly recognizable, naturally integrated. Small street sign or plaque displays “[CITY NAME]” as authentic urban detail, positioned organically at street corner or plaza edge. Surrounding architecture reflects city’s authentic character without oversizing elements. Ultra-realistic handcrafted miniature, detailed architecture, realistic materials, accurate proportions. Macro lens, deep depth of field keeping entire city sharp. Soft studio lighting, subtle shadows, tilt-shift realism. Neutral softly blurred background. Photorealistic, cinematic, premium quality."
}
JSON
IM
图像
Illustration & 3D gpt-image-2

A hyper-detailed origami [FOOD ITEM] folded from realistic c...

A hyper-detailed origami [FOOD ITEM] folded from realistic colored paper with visible creases and paper texture. Complex geometric folds capture the food’s shape, layers, and distinctive features. Placed on clean surface with soft shadows, minimalist food art photography style

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "A hyper-detailed origami [FOOD ITEM] folded from realistic colored paper with visible creases and paper texture. Complex geometric folds capture the food’s shape, layers, and distinctive features. Placed on clean surface with soft shadows, minimalist food art photography style"
}
JSON
IM
图像
Illustration & 3D gpt-image-2

A high-quality 3D render of a cute young boy riding an orang...

A high-quality 3D render of a cute young boy riding an orange electric scooter next to a small, round, furry blue monster. Both characters have shocked expressions with wide eyes and open mouths. The boy is wearing a highly textured, fuzzy teal sweater with a white patch that reads "noo" in red text, along with brown patterned pants and white sneakers. Clean teal studio background, soft lighting.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "A high-quality 3D render of a cute young boy riding an orange electric scooter next to a small, round, furry blue monster. Both characters have shocked expressions with wide eyes and open mouths. The boy is wearing a highly textured, fuzzy teal sweater with a white patch that reads \"noo\" in red text, along with brown patterned pants and white sneakers. Clean teal studio background, soft lighting."
}
JSON
IM
图像
Illustration & 3D gpt-image-2

Create a high-detail 3D semi-realistic chibi character with...

Create a high-detail 3D semi-realistic chibi character with slightly exaggerated cute proportions but with photorealistic facial rendering, natural skin pores, realistic lighting, and finely detailed hair strands. The character should look like a collectible designer toy figure with smooth surfaces, high-end materials, and ultra-clean edges. The character is styled in an fashion look: A tailored designer jacket in deep emerald green with gold stitching accents A sleek black silk fitted top underneath High-fashion tapered trousers in matte ivory tone designer sneakers / footwear in white and gold with polished details Accessories must feel ultra- and fashionable: oversized sunglasses with glossy black lenses and gold frame wristwatch with metallic gold case and elegant dial Subtle designer bracelet and minimal accents The character stands confidently on top of a giant modern smartphone, like a collectible display piece. They are wearing stylish wireless over-ear headphones in metallic rose gold and holding the phone slightly forward while taking a playful joyful selfie, smiling and laughing with energetic expression. The smartphone screen displays a realistic modern music-player interface with colorful waveform animations and elegant UI elements. Scene style and lighting: Background: deep cinematic dark brown gradient studio backdrop Lighting: soft studio lighting with subtle reflections and rim light Materials: high-quality fabric textures, polished metals, and realistic plastics Style: collectible toy aesthetic mixed with semi-realistic chibi design Camera perspective: Aerial / top-down camera angle Slight cinematic depth of field for realism Rendering quality: Ultra-detailed 3D render 8K resolution smooth shading hyper-clean edges high clarity Add a small elegant watermark text “Naik Nelofar ” at the bottom of the image, subtle but clearly readable. Aspect ratio: 3:4 vertical composition

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "Create a high-detail 3D semi-realistic chibi character with slightly exaggerated cute proportions but with photorealistic facial rendering, natural skin pores, realistic lighting, and finely detailed hair strands. The character should look like a collectible designer toy figure with smooth surfaces, high-end materials, and ultra-clean edges. The character is styled in an fashion look: A tailored designer jacket in deep emerald green with gold stitching accents A sleek black silk fitted top underneath High-fashion tapered trousers in matte ivory tone designer sneakers / footwear in white and gold with polished details Accessories must feel ultra- and fashionable: oversized sunglasses with glossy black lenses and gold frame wristwatch with metallic gold case and elegant dial Subtle designer bracelet and minimal accents The character stands confidently on top of a giant modern smartphone, like a collectible display piece. They are wearing stylish wireless over-ear headphones in metallic rose gold and holding the phone slightly forward while taking a playful joyful selfie, smiling and laughing with energetic expression. The smartphone screen displays a realistic modern music-player interface with colorful waveform animations and elegant UI elements. Scene style and lighting: Background: deep cinematic dark brown gradient studio backdrop Lighting: soft studio lighting with subtle reflections and rim light Materials: high-quality fabric textures, polished metals, and realistic plastics Style: collectible toy aesthetic mixed with semi-realistic chibi design Camera perspective: Aerial / top-down camera angle Slight cinematic depth of field for realism Rendering quality: Ultra-detailed 3D render 8K resolution smooth shading hyper-clean edges high clarity Add a small elegant watermark text “Naik Nelofar ” at the bottom of the image, subtle but clearly readable. Aspect ratio: 3:4 vertical composition"
}
JSON
IM
图像
Illustration & 3D gpt-image-2

{ "prompt": "Create a hyper-realistic, ultra-detailed cine...

{ "prompt": "Create a hyper-realistic, ultra-detailed cinematic photo featuring a MINIATURE version of the person from the provided reference image (preserve facial likeness, skin tone, hairstyle, and overall identity). The tiny character is relaxing inside an OPEN vintage hard-shell suitcase that is used like a tiny bed. The suitcase sits on a clean stone/tile floor in a bright room with strong natural sunlight casting soft rectangular window shadows across the floor.\n\nONLY VARIABLES:\n1) Character: use the user reference photo for the person’s face and identity.\n2) Theme/Genre: {THEME}\n\nCOMPOSITION & SCALE:\n- The person must be clearly mini-sized (toy-scale) relative to the suitcase, with correct perspective and believable proportions.\n- The open suitcase interior is styled like a cozy miniature scene: pillow, textured blanket or towel, and themed tiny props.\n- Add realistic micro-details: fabric weave, zipper teeth, suitcase latches, scuffs, stitching, subtle dust, realistic contact shadows.\n\nTHEME STYLING (derive everything from {THEME}):\n- Choose a cohesive color palette and make the SUITCASE COLOR match the theme (e.g., beach = warm coral/sand; football = deep green/black or team-inspired; sporty = bold neon accents; cozy-casual = muted cream/tan; luxury = black/ivory/gold).\n- Dress the tiny character in an outfit that fits {THEME}.\n- Place 5–8 tiny theme props neatly inside the suitcase near the character (miniature scale, photoreal materials). Examples by theme:\n • Beach: tiny sunscreen bottle, mini sunglasses, seashells, flip-flops, mini straw hat, folded towel.\n • Football/Soccer: tiny soccer ball, mini jersey/scarf, cleats, shin guards, whistle, small tactic board.\n • Sporty/Fitness: tiny water bottle, mini dumbbell, resistance band, smartwatch, towel, energy bar.\n • Cozy/Casual: tiny book/magazine, mug, knitted throw, headphones, mini candle.\n(If {THEME} is different, invent equivalent props that strongly communicate that theme.)\n\nLIGHTING & CAMERA:\n- Bright natural sunlight, soft realistic shadows, subtle bounce light, HDR-like dynamic range.\n- Photographic realism: shallow depth of field (but keep face and key props sharp), 50–85mm lens look.\n- No text, no logos, no watermarks.\n\nFINAL LOOK:\n- Hyper-real, high detail, clean editorial product-photography vibe, believable miniature diorama realism, crisp textures and natural skin rendering.", "negative_prompt": "cartoon, CGI, illustration, anime, plastic-looking skin, uncanny face, distorted anatomy, extra fingers, deformed hands, duplicated limbs, wrong perspective, unrealistic scale, blurry, low-res, noisy, harsh artifacts, over-smoothed, bad shadows, floating objects, cluttered scene, messy background, text, watermark, logo, brand names, extra people, face not matching reference", "variables": { "THEME": "beach | football | sporty | cozy-casual | luxury | etc.", "USER_IMAGE": "reference photo uploaded by the user (required)" } }

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "{ \"prompt\": \"Create a hyper-realistic, ultra-detailed cinematic photo featuring a MINIATURE version of the person from the provided reference image (preserve facial likeness, skin tone, hairstyle, and overall identity). The tiny character is relaxing inside an OPEN vintage hard-shell suitcase that is used like a tiny bed. The suitcase sits on a clean stone/tile floor in a bright room with strong natural sunlight casting soft rectangular window shadows across the floor.\\n\\nONLY VARIABLES:\\n1) Character: use the user reference photo for the person’s face and identity.\\n2) Theme/Genre: {THEME}\\n\\nCOMPOSITION & SCALE:\\n- The person must be clearly mini-sized (toy-scale) relative to the suitcase, with correct perspective and believable proportions.\\n- The open suitcase interior is styled like a cozy miniature scene: pillow, textured blanket or towel, and themed tiny props.\\n- Add realistic micro-details: fabric weave, zipper teeth, suitcase latches, scuffs, stitching, subtle dust, realistic contact shadows.\\n\\nTHEME STYLING (derive everything from {THEME}):\\n- Choose a cohesive color palette and make the SUITCASE COLOR match the theme (e.g., beach = warm coral/sand; football = deep green/black or team-inspired; sporty = bold neon accents; cozy-casual = muted cream/tan; luxury = black/ivory/gold).\\n- Dress the tiny character in an outfit that fits {THEME}.\\n- Place 5–8 tiny theme props neatly inside the suitcase near the character (miniature scale, photoreal materials). Examples by theme:\\n • Beach: tiny sunscreen bottle, mini sunglasses, seashells, flip-flops, mini straw hat, folded towel.\\n • Football/Soccer: tiny soccer ball, mini jersey/scarf, cleats, shin guards, whistle, small tactic board.\\n • Sporty/Fitness: tiny water bottle, mini dumbbell, resistance band, smartwatch, towel, energy bar.\\n • Cozy/Casual: tiny book/magazine, mug, knitted throw, headphones, mini candle.\\n(If {THEME} is different, invent equivalent props that strongly communicate that theme.)\\n\\nLIGHTING & CAMERA:\\n- Bright natural sunlight, soft realistic shadows, subtle bounce light, HDR-like dynamic range.\\n- Photographic realism: shallow depth of field (but keep face and key props sharp), 50–85mm lens look.\\n- No text, no logos, no watermarks.\\n\\nFINAL LOOK:\\n- Hyper-real, high detail, clean editorial product-photography vibe, believable miniature diorama realism, crisp textures and natural skin rendering.\", \"negative_prompt\": \"cartoon, CGI, illustration, anime, plastic-looking skin, uncanny face, distorted anatomy, extra fingers, deformed hands, duplicated limbs, wrong perspective, unrealistic scale, blurry, low-res, noisy, harsh artifacts, over-smoothed, bad shadows, floating objects, cluttered scene, messy background, text, watermark, logo, brand names, extra people, face not matching reference\", \"variables\": { \"THEME\": \"beach | football | sporty | cozy-casual | luxury | etc.\", \"USER_IMAGE\": \"reference photo uploaded by the user (required)\" } }"
}
JSON
IM
图像
Illustration & 3D gpt-image-2

Hyper-realistic open [COUNTRY] passport on a studio surface,...

Hyper-realistic open [COUNTRY] passport on a studio surface, with gold-embossed “[Official Passport Name]” text and leather texture. From its pages rises a miniature 3D diorama of [COUNTRY], featuring [ICONIC LANDMARKS], [CITYSCAPES/COASTLINES/COUNTRYSIDE], and tiny human figures for scale. Passport pages show stamps and paper texture. Soft cinematic lighting, shallow depth of field, ultra-detailed photorealistic luxury style.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "Hyper-realistic open [COUNTRY] passport on a studio surface, with gold-embossed “[Official Passport Name]” text and leather texture. From its pages rises a miniature 3D diorama of [COUNTRY], featuring [ICONIC LANDMARKS], [CITYSCAPES/COASTLINES/COUNTRYSIDE], and tiny human figures for scale. Passport pages show stamps and paper texture. Soft cinematic lighting, shallow depth of field, ultra-detailed photorealistic luxury style."
}
JSON
IM
图像
Illustration & 3D gpt-image-2

A high-fidelity 3D character render of a cute, stylized boy...

A high-fidelity 3D character render of a cute, stylized boy skateboarding in a dynamic pose. The boy has 'chibi' proportions with a large head, wearing oversized round wire-frame glasses and making a surprised 'O' mouth expression. He is dressed in an extremely fuzzy, textured blue mohair sweater with the text "OID" on the chest, a matching fuzzy blue beanie with a cream patch, and baggy camouflage-patterned pants made of a soft, velvet-like fabric. He wears chunky white sneakers and a small necklace pouch with a cartoon face. The background is a solid, seamless teal color. The lighting is soft and diffuse studio lighting, creating a clean, high-end "blind box" art toy aesthetic with hyper-realistic fabric textures.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "A high-fidelity 3D character render of a cute, stylized boy skateboarding in a dynamic pose. The boy has 'chibi' proportions with a large head, wearing oversized round wire-frame glasses and making a surprised 'O' mouth expression. He is dressed in an extremely fuzzy, textured blue mohair sweater with the text \"OID\" on the chest, a matching fuzzy blue beanie with a cream patch, and baggy camouflage-patterned pants made of a soft, velvet-like fabric. He wears chunky white sneakers and a small necklace pouch with a cartoon face. The background is a solid, seamless teal color. The lighting is soft and diffuse studio lighting, creating a clean, high-end \"blind box\" art toy aesthetic with hyper-realistic fabric textures."
}
JSON
IM
图像
Illustration & 3D gpt-image-2

The scene is lit by warm golden hour sunlight, with glowing...

The scene is lit by warm golden hour sunlight, with glowing dust particles floating in the air, creating a soft magical atmosphere. Background is a rustic wooden village setting, softly blurred with shallow depth of field. Cinematic lighting, soft rim light on hair, volumetric light rays, ultra-detailed, high quality, Pixar / Disney-style 3D render, cute, cozy, whimsical, warm color palette, 4k, bokeh, soft focus.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "The scene is lit by warm golden hour sunlight, with glowing dust particles floating in the air, creating a soft magical atmosphere. Background is a rustic wooden village setting, softly blurred with shallow depth of field. Cinematic lighting, soft rim light on hair, volumetric light rays, ultra-detailed, high quality, Pixar / Disney-style 3D render, cute, cozy, whimsical, warm color palette, 4k, bokeh, soft focus."
}
JSON
IM
图像
Illustration & 3D gpt-image-2

Create a technical infographic of [VEHICLE] with a 45-degree...

Create a technical infographic of [VEHICLE] with a 45-degree isometric 3D perspective showing the device slightly tilted to reveal depth and dimension. Combine a realistic photoreal render with black ink technical annotations on pure white background. Include: Key component labels with color-coded callout boxes Internal component visibility through transparent/cutaway sections Measurements, dimensions, and precise scale markers Material callouts and quantities Color-coded arrows for function/flow: RED (power/battery), BLUE (data/connectivity), ORANGE (thermal/processor), GREEN (sensors/haptics) Simple schematics or cross-sectional diagrams where relevant Place “VEHICLE” title in a hand-drawn technical box (top-left corner). Style: Black linework (technical pen/architectural), sketched but precise. Object remains clearly visible. Educational museum-exhibit vibe. Clean composition, balanced negative space. Perspective: Isometric 3D angle—tilted to show depth, dimension, and internal architecture dramatically. Like a professional product teardown or engineering manual. Colors: ~10-15% accent density. Black dominant. White background. Output: 1080×1080, ultra-crisp, social-feed optimized

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "Create a technical infographic of [VEHICLE] with a 45-degree isometric 3D perspective showing the device slightly tilted to reveal depth and dimension. Combine a realistic photoreal render with black ink technical annotations on pure white background. Include: Key component labels with color-coded callout boxes Internal component visibility through transparent/cutaway sections Measurements, dimensions, and precise scale markers Material callouts and quantities Color-coded arrows for function/flow: RED (power/battery), BLUE (data/connectivity), ORANGE (thermal/processor), GREEN (sensors/haptics) Simple schematics or cross-sectional diagrams where relevant Place “VEHICLE” title in a hand-drawn technical box (top-left corner). Style: Black linework (technical pen/architectural), sketched but precise. Object remains clearly visible. Educational museum-exhibit vibe. Clean composition, balanced negative space. Perspective: Isometric 3D angle—tilted to show depth, dimension, and internal architecture dramatically. Like a professional product teardown or engineering manual. Colors: ~10-15% accent density. Black dominant. White background. Output: 1080×1080, ultra-crisp, social-feed optimized"
}
JSON
IM
图像
Illustration & 3D gpt-image-2

A soft, high-quality plush toy of [CHARACTER], with an overs...

A soft, high-quality plush toy of [CHARACTER], with an oversized head, small body, and stubby limbs. Made of fuzzy fabric with visible stitching and embroidered facial features. The plush is shown sitting or standing against a neutral background. The expression is cute or expressive, and it wears simple clothes or iconic accessories if relevant. Lighting is soft and even, with a realistic, collectible plush look. Centered, full-body view

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "A soft, high-quality plush toy of [CHARACTER], with an oversized head, small body, and stubby limbs. Made of fuzzy fabric with visible stitching and embroidered facial features. The plush is shown sitting or standing against a neutral background. The expression is cute or expressive, and it wears simple clothes or iconic accessories if relevant. Lighting is soft and even, with a realistic, collectible plush look. Centered, full-body view"
}
JSON
IM
图像
Illustration & 3D gpt-image-2

Generate a whimsical miniature world featuring [LANDMARK NAM...

Generate a whimsical miniature world featuring [LANDMARK NAME] crafted entirely from colorful modeling clay. Every element - buildings, trees, waterways, and urban features - should appear hand-sculpted with visible fingerprints and organic clay textures. Use a playful, childlike style with vibrant colors: bright azure sky, puffy cream clouds, emerald trees, and buildings in warm yellows, oranges, reds, and blues. The handmade quality should be evident in every surface and gentle curve. Capture from a wide perspective showcasing the entire miniature landscape in a harmonious, joyful composition. Include no text, words, or signage - only sculptural clay elements that define the location through recognizable architectural features

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "Generate a whimsical miniature world featuring [LANDMARK NAME] crafted entirely from colorful modeling clay. Every element - buildings, trees, waterways, and urban features - should appear hand-sculpted with visible fingerprints and organic clay textures. Use a playful, childlike style with vibrant colors: bright azure sky, puffy cream clouds, emerald trees, and buildings in warm yellows, oranges, reds, and blues. The handmade quality should be evident in every surface and gentle curve. Capture from a wide perspective showcasing the entire miniature landscape in a harmonious, joyful composition. Include no text, words, or signage - only sculptural clay elements that define the location through recognizable architectural features"
}
JSON
IM
图像
Illustration & 3D gpt-image-2

Depict [LANDMARK] frozen in an eternal state of construction...

Depict [LANDMARK] frozen in an eternal state of construction. Camera & Angle (LOCKED): 45° elevated isometric view, camera distance fixed so the full landmark fills ~70% of the frame. No tilt variation. Structure: Lower sections are fully completed, solid, and instantly recognizable. Upper sections transition cleanly into unfinished construction: scaffolding, cranes, exposed beams, cables, and skeletal frameworks. The transition line between finished and unfinished is clearly visible and architecturally precise. Scale & Detail: Include small, static construction workers placed on scaffolding for scale. Include exactly 1–2 construction machines (crane arm, lift, or hoist), frozen in place. No motion, no blur, no debris falling. Materials (CONSISTENT): Finished areas: polished stone / glass / steel (appropriate to the landmark). Unfinished areas: raw concrete, steel beams, cables, structural frames. Materials are clean, realistic, and consistent across all renders. Lighting (LOCKED): Soft neutral cinematic lighting from upper left. Balanced exposure, gentle shadows, no dramatic highlights. Composition (LOCKED): Perfectly centered, symmetrical balance. Landmark sits on a subtle base or ground plane. Square format 1080×1080. Background (LOCKED): Minimal neutral sky or studio-gray backdrop. No clouds, no gradients, no distractions. Style: Hyper-realistic architectural render. Clean, precise, calm, and monumental. No stylization, no painterly effects. Mood: Timeless, quiet, contemplative. Frozen progress — never finished, never decaying.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "Depict [LANDMARK] frozen in an eternal state of construction. Camera & Angle (LOCKED): 45° elevated isometric view, camera distance fixed so the full landmark fills ~70% of the frame. No tilt variation. Structure: Lower sections are fully completed, solid, and instantly recognizable. Upper sections transition cleanly into unfinished construction: scaffolding, cranes, exposed beams, cables, and skeletal frameworks. The transition line between finished and unfinished is clearly visible and architecturally precise. Scale & Detail: Include small, static construction workers placed on scaffolding for scale. Include exactly 1–2 construction machines (crane arm, lift, or hoist), frozen in place. No motion, no blur, no debris falling. Materials (CONSISTENT): Finished areas: polished stone / glass / steel (appropriate to the landmark). Unfinished areas: raw concrete, steel beams, cables, structural frames. Materials are clean, realistic, and consistent across all renders. Lighting (LOCKED): Soft neutral cinematic lighting from upper left. Balanced exposure, gentle shadows, no dramatic highlights. Composition (LOCKED): Perfectly centered, symmetrical balance. Landmark sits on a subtle base or ground plane. Square format 1080×1080. Background (LOCKED): Minimal neutral sky or studio-gray backdrop. No clouds, no gradients, no distractions. Style: Hyper-realistic architectural render. Clean, precise, calm, and monumental. No stylization, no painterly effects. Mood: Timeless, quiet, contemplative. Frozen progress — never finished, never decaying."
}
JSON
IM
图像
Illustration & 3D gpt-image-2

A hand-carved wooden miniature figure of [NAME], shaped with...

A hand-carved wooden miniature figure of [NAME], shaped with visible knife marks, natural grain texture, and smooth unfinished edges. Placed on a workshop table with carving tools, wood shavings, and soft warm directional lighting. 1080×1080.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "A hand-carved wooden miniature figure of [NAME], shaped with visible knife marks, natural grain texture, and smooth unfinished edges. Placed on a workshop table with carving tools, wood shavings, and soft warm directional lighting. 1080×1080."
}
JSON
IM
图像
Illustration & 3D gpt-image-2

A hyper-realistic 1080x1080 photograph of a glass cube diora...

A hyper-realistic 1080x1080 photograph of a glass cube diorama placed on a lush, mossy forest floor with dappled sunlight. Inside the cube are miniature, highly detailed landmarks and cultural icons from [COUNTRY]. Include its most famous and recognizable architecture—traditional and modern—surrounded by greenery. Prominently display the 3D word “COUNTRY” at the base inside the cube, using large, bold white block letters and a flagpole of the country's flag. The scene is crisp, elegant, and immersive, with the forest background softly blurred to focus on the diorama’s sharp details.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "A hyper-realistic 1080x1080 photograph of a glass cube diorama placed on a lush, mossy forest floor with dappled sunlight. Inside the cube are miniature, highly detailed landmarks and cultural icons from [COUNTRY]. Include its most famous and recognizable architecture—traditional and modern—surrounded by greenery. Prominently display the 3D word “COUNTRY” at the base inside the cube, using large, bold white block letters and a flagpole of the country's flag. The scene is crisp, elegant, and immersive, with the forest background softly blurred to focus on the diorama’s sharp details."
}
JSON
IM
图像
Illustration & 3D gpt-image-2

Create a highly detailed isometric 3D rendering of [LANDMARK...

Create a highly detailed isometric 3D rendering of [LANDMARK] in architectural visualization style. The building is shown at a 45-degree angle from above, displaying three visible sides with intricate architectural detail. Photorealistic textures showing materials like stone, glass, metal, or brick. Include the base/ground level with tiny people, cars, and landscaping for scale. Clean white or light grey background. Professional architectural rendering with soft ambient shadows beneath the structure. Every window, column, ornamental detail, and structural element clearly visible. 1080x1080 dimension, centered composition. Style similar to video game building assets or architectural presentation models - clean, detailed, slightly stylized but realistic.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "Create a highly detailed isometric 3D rendering of [LANDMARK] in architectural visualization style. The building is shown at a 45-degree angle from above, displaying three visible sides with intricate architectural detail. Photorealistic textures showing materials like stone, glass, metal, or brick. Include the base/ground level with tiny people, cars, and landscaping for scale. Clean white or light grey background. Professional architectural rendering with soft ambient shadows beneath the structure. Every window, column, ornamental detail, and structural element clearly visible. 1080x1080 dimension, centered composition. Style similar to video game building assets or architectural presentation models - clean, detailed, slightly stylized but realistic."
}
JSON
IM
图像
Illustration & 3D gpt-image-2

Present a clear, 45° top-down isometric miniature 3D cartoon...

Present a clear, 45° top-down isometric miniature 3D cartoon scene of [STADIUM], with soft refined textures, realistic PBR materials, and gentle lifelike lighting. Use a clean solid [COLOR] background. At the top-center, display the name of this stadium in large bold text, then directly beneath it show its real seating capacity in medium text, and place the official logo associated with this stadium below the capacity. All text must match the background contrast automatically (white or black). Centered layout, square 1080x1080 dimension

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "Present a clear, 45° top-down isometric miniature 3D cartoon scene of [STADIUM], with soft refined textures, realistic PBR materials, and gentle lifelike lighting. Use a clean solid [COLOR] background. At the top-center, display the name of this stadium in large bold text, then directly beneath it show its real seating capacity in medium text, and place the official logo associated with this stadium below the capacity. All text must match the background contrast automatically (white or black). Centered layout, square 1080x1080 dimension"
}
JSON
常见问题

使用图像 prompts

好的%{model} prompt 应该包含什么?

有用的%{model} prompt 会清楚写出主体、风格、约束和输出目标。这里的示例足够短,便于复制;同时也足够具体,agent 或后端任务能保留生成意图。

这些 prompts 可以跨模型复用吗?

多数情况下可以。先从同一模态的 prompt 开始,再按模型调整画幅、时长、声音设置或风格控制。详情页会把保存过的参数列在 prompt 文本旁边。

在哪里找正确的模型 slug?

每张卡片都会显示 RunAPI 模型 slug。只想看一个模型的示例时,打开模型页;需要定价和能力细节时,进入模型目录页查看。

agent 可以直接调用这些 prompts 吗?

可以。安装 RunAPI MCP Server 后,复制 prompt 详情页里的 agent 指令。页面会把 prompt 文本、模型 slug 和 endpoint 路径放在一起,给 agent 足够上下文。