GPT Image 生图与修图提示词指南

Create a photorealistic candid photograph of an elderly sailor standing on a small fishing boat.
He has weathered skin with visible wrinkles, pores, and sun texture, and a few faded traditional sailor tattoos on his arms.
He is calmly adjusting a net while his dog sits nearby on the deck. Shot like a 35mm film photograph, medium close-up at eye level, using a 50mm lens.
Soft coastal daylight, shallow depth of field, subtle film grain, natural color balance.
The image should feel honest and unposed, with real skin texture, worn materials, and everyday detail. No glamorization, no heavy retouching.

# 中文对应写法：
生成一张极具真实感的抓拍照片：一位年迈的水手站在小渔船上。
他饱经风霜的皮肤上有清晰可见的皱纹、毛孔与日晒肌理，手臂上有几处褪色的传统水手纹身。
他正平静地整理渔网，他的狗坐在旁边的甲板上。画面质感如同用 50mm 镜头在平视角度拍摄的 35mm 胶片近景照片。
柔和的海岸日光、浅景深、细腻的胶片颗粒感、自然的色彩平衡。
整张照片应当真实自然、毫无摆拍痕迹，展现出真实的皮肤纹理、磨损的衣物材质与日常细节。不要过度美化，不要重度磨皮修图。

Create a detailed Infographic of the functioning and flow of an automatic coffee machine like a Jura.
From bean basket, to grinding, to scale, water tank, boiler, etc.
I'd like to understand technically and visually the flow.

# 中文对应写法：
生成一张详细的信息图，展示像 Jura 这类全自动咖啡机的内部工作原理与完整流程。
涵盖从咖啡豆仓、研磨器、称重计量、水箱到锅炉萃取等各个核心环节。
我希望能够从技术结构和视觉流向上直观看懂它的工作全过程。

Give me a cool in culture ad / fashion shot for a brand called Thread.
It's a hip young street brand. The ad shows a group of friends hanging out together with the tagline "Yours to Create."
Make it feel like a polished campaign image for a youth streetwear audience: stylish, contemporary, energetic, and tasteful.
Use clean composition, strong color direction, natural poses, and premium fashion photography cues.
Render the tagline exactly once, clearly and legibly, integrated into the ad layout.
No extra text, no watermarks, no unrelated logos.

# 中文对应写法：
为年轻街头潮流品牌 Thread 生成一张充满青年文化气息的时尚广告大片。
画面展示一群朋友聚在一起自在玩乐，并印有品牌标语 "Yours to Create."。
整体质感要像面向年轻街头服饰受众的成熟商业广告大片：时髦、现代、充满活力且品味在线。
采用干净的构图、鲜明的色彩导向、自然的肢体姿态以及高级时尚摄影的灯光质感。
将标语清晰、易读地融入广告版式中，且严格只渲染一次。
不要出现任何额外文字、不要水印、不要无关 Logo。

Create an original, non-infringing logo for a company called Field & Flour, a local bakery.
The logo should feel warm, simple, and timeless. Use clean, vector-like shapes, a strong silhouette, and balanced negative space.
Favor simplicity over detail so it reads clearly at small and large sizes. Flat design, minimal strokes, no gradients unless essential.
Fully transparent background. Deliver a single centered logo with generous padding, clean alpha edges, and no solid backdrop, scenery, checkerboard, or watermark.

# 中文对应写法：
为一家名为 Field & Flour 的本地烘焙坊设计一款原创、无侵权风险的品牌 Logo。
Logo 整体感觉应当温暖、简洁且经典耐看。使用干净的类矢量几何图形、鲜明的剪影轮廓以及均衡的正负空间。
优先追求简洁而非繁琐细节，确保在小尺寸和大尺寸下都清晰易读。采用扁平化设计、极简线条，非必要不使用渐变。
全透明背景。输出单个居中的 Logo，四周留出充足边距，保持干净的 Alpha 透明边缘，严禁添加纯色底板、背景景物、灰白棋盘格或水印。

Create a realistic outdoor crowd scene in Bethel, New York on August 16, 1969.
Photorealistic, period-accurate clothing, staging, and environment.

# 中文对应写法：
生成一张 1969 年 8 月 16 日美国纽约州伯特利（Bethel, New York，即伍德斯托克音乐节现场）的写实户外人群场景。
要求真实照片质感，人物服饰、舞台搭景与现场环境均需严格符合当时的年代特征。

Create a short vertical comic-style reel with 4 panels.
Panel 1: The owner leaves through the front door. The pet is framed in the window behind them, small against the glass, eyes wide, paws pressed high, the house suddenly quiet.
Panel 2: The door clicks shut. Silence breaks. The pet slowly turns toward the empty house, posture shifting, eyes sharp with possibility.
Panel 3: The house transformed. The pet sprawls across the couch like it owns the place, crumbs nearby, sunlight cutting across the room like a spotlight.
Panel 4: The door opens. The pet is seated perfectly by the entrance, alert and composed, as if nothing happened.

# 中文对应写法：
生成一幅包含 4 个分镜的竖版四格条漫。
第 1 格：主人走出前门离开。宠物被框在身后的窗户里，小小的身躯贴着玻璃，瞪大双眼，前爪高高扒在窗上，屋里瞬间安静下来。
第 2 格：门咔哒一声关上。寂静被打破。宠物缓缓转身面向空无一人的屋子，姿态突变，眼神里闪烁着蠢蠢欲动的光芒。
第 3 格：屋子彻底变了样。宠物像大爷一样四仰八叉地瘫在沙发上，旁边散落着零食碎屑，阳光像聚光灯一样斜射进房间。
第 4 格：门开了。宠物端端正正地坐在玄关门口，神情警觉又乖巧淡定，仿佛什么都没发生过一样。

Create a realistic mobile app UI mockup for a local farmers market.
Show today’s market with a simple header, a short list of vendors with small photos and categories, a small “Today’s specials” section, and basic information for location and hours.
Design it to be practical, and easy to use. White background, subtle natural accent colors, clear typography, and minimal decoration.
It should look like a real, well-designed, beautiful app for a small local market.
Place the UI mockup in an iPhone frame.

# 中文对应写法：
为一家本地农贸市场生成一张真实的移动端 App 界面视觉稿（UI Mockup）。
展示今日集市页面：包含简洁的顶部导航栏、带有缩略图和分类标签的摊主列表、小巧的“今日特惠（Today’s specials）”板块，以及集市地点与营业时间等基础信息。
整体设计注重实用性与易用性：纯白背景、柔和自然的点缀色、清晰的字体层级与极简装饰。
它看起来应该像一款真正已经上线、设计考究、美观好用的本地小集市 App。
将界面视觉稿放置在 iPhone 手机外框中展示。

Create a simple biology diagram titled "Cellular Respiration at a Glance" for high school students.

Show how glucose turns into energy inside a cell. Include glycolysis, the Krebs cycle, and the electron transport chain.
Use arrows to connect the steps, and label the main molecules: glucose, pyruvate, ATP, NADH, FADH2, CO2, O2, and H2O.
Make it look like a clean classroom handout or slide, with a white background, simple icons, clear labels, and easy-to-read text.

Avoid tiny text, extra decoration, or anything that makes the diagram hard to understand.

# 中文对应写法：
面向高中生生成一张简洁的生物教学原理图，标题为 "Cellular Respiration at a Glance"（细胞呼吸速览）。

展示葡萄糖如何在细胞内转化为能量。必须包含糖酵解（glycolysis）、克雷布斯循环/柠檬酸循环（the Krebs cycle）和电子传递链（the electron transport chain）三个阶段。
使用箭头连接各个步骤，并准确标注主要分子名称：glucose、pyruvate、ATP、NADH、FADH2、CO2、O2 和 H2O。
整体视觉效果要像一份干净的课堂讲义或教学幻灯片：纯白背景、简洁图标、清晰标签与易读文字。

避免使用过小的字号、多余的装饰，或任何会让原理图变得难以理解的杂乱元素。

Create one pitch-deck slide titled **"Market Opportunity"** that feels like a real Series A fundraising slide from a YC-backed startup.

Use a clean white background, modern sans-serif typography like Inter, and a crisp, minimal layout. The slide should include:

* A TAM/SAM/SOM concentric-circle diagram in muted blues and grays
* Specific, believable market sizing numbers:
  * **TAM:** $42B
  * **SAM:** $8.7B
  * **SOM:** $340M
* A clean bar chart below showing market growth from **2021 to 2026**, with a subtle upward trend
* Small footnotes: **"AGI Research, 2024"** and **"Internal analysis"**
* A company logo placeholder in the bottom-right corner

The design should look like it belongs in a deck that actually raised money: highly readable text, clear data hierarchy, polished spacing, and professional startup-style visual language.

Avoid clip art, stock photography, gradients, shadows, decorative elements, or anything that feels generic or overdesigned.

# 中文对应写法：
生成一页标题为 **"Market Opportunity"** 的融资路演幻灯片（Pitch-deck Slide），整体质感要像硅谷 YC 孵化初创公司真实的 A 轮融资 PPT。

使用干净的纯白背景、类似 Inter 的现代无衬线字体，以及利落极简的排版布局。该页幻灯片需包含：

* 采用低饱和灰蓝色调绘制的 TAM/SAM/SOM 同心圆市场规模图
* 具体、可信的市场规模数值标注：
  * **TAM:** $42B
  * **SAM:** $8.7B
  * **SOM:** $340M
* 下方配一张干净的柱状图，展示 **2021 至 2026 年**稳步增长的市场趋势
* 底部小字脚注：**"AGI Research, 2024"** 与 **"Internal analysis"**
* 右下角预留一个公司 Logo 占位符

整体设计应当具备真正拿到融资的顶级路演 PPT 水准：文字极易阅读、数据层级分明、间距考究、视觉语言专业克制。

严禁出现剪贴画（Clip art）、廉价图库照片、花哨渐变、阴影、多余装饰元素，或任何显得俗套、过度设计的痕迹。

Translate the text in the infographic to Spanish. Do not change any other aspect of the image.

# 中文对应写法：
将这张信息图中的所有文字翻译为西班牙语（或简体中文）。不要改变画面的任何其他部分。

Use the same style from the input image and generate a man riding a motorcycle on a white background.

# 中文对应写法：
严格沿用输入图片的视觉画风，在纯白背景上生成一名骑着摩托车的男子。

Edit the image to dress the woman using the provided clothing images. Do not change her face, facial features, skin tone, body shape, pose, or identity in any way. Preserve her exact likeness, expression, hairstyle, and proportions. Replace only the clothing, fitting the garments naturally to her existing pose and body geometry with realistic fabric behavior. Match lighting, shadows, and color temperature to the original photo so the outfit integrates photorealistically, without looking pasted on. Do not change the background, camera angle, framing, or image quality, and do not add accessories, text, logos, or watermarks.

# 中文对应写法：
使用提供的服装参考图，为原图中的女性换上这套穿搭。严禁以任何方式改变她的脸部、五官特征、肤色、身形、姿势或个人身份特征。完整保留她原本的相貌神态、表情、发型与身体比例。仅替换身上的服装，让衣物顺应她现有的姿态与身体结构自然贴合，展现出真实的布料垂坠与褶皱质感。将光线、阴影与色温与原照片严格对齐，使整套穿搭呈现出照片级的自然融合感，绝不能像生硬贴上去的贴纸。不要改变背景、机位角度、取景框范围或画面画质，也不要添加任何额外配饰、文字、Logo 或水印。

Place the dog from the second image into the setting of image 1, right next to the woman, use the same style of lighting, composition and background. Do not change anything else.

# 中文对应写法：
将第 2 张图片中的小狗放置到第 1 张图片的场景里，就安排在那位女性身旁；保持与图 1 完全一致的光线风格、构图与背景。不要改变画面的任何其他内容。

Extract the product from the input image and isolate it on a fully transparent background.
Output: centered product, crisp silhouette, no halos/fringing.
Preserve product geometry and label legibility exactly.
Add only light polishing. Do not add a solid backdrop, checkerboard, scenery, or shadow.
Do not restyle the product; remove the background and preserve clean alpha transparency.

# 中文对应写法：
从输入图片中提取出商品主体，并将其独立放置在完全透明的背景上。
输出要求：商品居中、外轮廓利落清晰、边缘无白边或杂色光晕（No halos/fringing）。
100% 原样保留商品的几何外观结构与瓶身标签文字的清晰度。
仅做轻微的质感润色。严禁添加纯色背景板、灰白假棋盘格、环境景物或投影。
严禁重绘或改变商品设计风格；仅移除背景并保留干净的 Alpha 透明通道。

Turn this drawing into a photorealistic image.
Preserve the exact layout, proportions, and perspective.
Choose realistic materials and lighting consistent with the sketch intent.
Do not add new elements or text.

# 中文对应写法：
将这幅手绘线稿转化为照片级写实图像。
严格保留原稿的构图布局、比例关系与空间透视。
选用符合线稿原本意图的真实自然材质与光影效果。
不要添加任何多余的新元素或文字。

Remove the flower from man's hand. Do not change anything else.

# 中文对应写法：
移除男子手中的花朵。不要改变画面的任何其他部分。

Generate a highly realistic action scene where this person is running away from a large, realistic brown bear attacking a campsite. The image should look like a real photograph someone could have taken, not an overly enhanced or cinematic movie-poster image.
She is centered in the image but looking away from the camera, wearing outdoorsy camping attire, with dirt on her face and tears in her clothing. She is clearly afraid but focused on escaping, running away from the bear as it destroys the campsite behind her.
The campsite is in Yosemite National Park, with believable natural details. The time of day is dusk, with natural lighting and realistic colors. Everything should feel grounded, authentic, and unstyled, as if captured in a real moment. Avoid cinematic lighting, dramatic color grading, or stylized composition.

# 中文对应写法：
生成一张高度写实的动态抓拍场景：图中的这位人物正在逃离一头袭击露营地的巨大真实棕熊。整张图片看起来应当像有人在现场随手拍下的真实照片，而不是过度修饰或像电影海报那样的渲染图。
她位于画面中央但视线看向镜头之外，身穿户外露营服装，脸上有泥土痕迹，衣服上有撕裂破损。她神情明显惊恐但正全神贯注地逃生，在棕熊摧毁身后营地时奋力奔跑。
露营地位于优胜美地国家公园（Yosemite National Park），具备可信的自然环境细节。时间是黄昏时分，采用自然光线与真实色彩。一切都应当显得真实接地气、毫无刻意摆拍或美化痕迹，就像在真实瞬间抓拍到的一样。避免使用电影感布光、戏剧化调色或风格化构图。

Create a realistic billboard mockup of the shampoo on a highway scene during sunset.
Billboard text (EXACT, verbatim, no extra characters):
"Fresh and clean"
Typography: bold sans-serif, high contrast, centered, clean kerning.
Ensure text appears once and is perfectly legible.
No watermarks, no logos.

# 中文对应写法：
生成一张写实的户外广告牌视觉稿（Billboard Mockup），展示这款洗发水矗立在日落时分的高速公路场景中。
广告牌文字（严格逐字匹配，不得增删任何字符）：
"Fresh and clean"
字体排版：粗体无衬线字、高对比度、居中对齐、字距干净整洁。
确保该文字仅出现一次且清晰易读。
不要水印，不要多余 Logo。

Make it look like a winter evening with snowfall.

# 中文对应写法：
把画面改成正在下雪的冬日夜晚。

Create a children’s book illustration introducing a main character.

Character:
A young, storybook-style hero inspired by a little forest outlaw,
wearing a simple green hooded tunic, soft brown boots, and a small belt pouch.
The character has a kind expression, gentle eyes, and a brave but warm demeanor.
Carries a small wooden bow used only for helping, never harming.

Theme:
The character protects and rescues small forest animals like squirrels, birds, and rabbits.

Style:
Children’s book illustration, hand-painted watercolor look,
soft outlines, warm earthy colors, whimsical and friendly.
Proportions suitable for picture books (slightly oversized head, expressive face).

Constraints:
- Original character (no copyrighted characters)
- No text
- No watermarks
- Plain forest background to clearly showcase the character

# 中文对应写法：
生成一幅介绍主角登场的儿童绘本插画。

角色设定（Character）：
一位充满童话故事感的森林小侠客主角，身穿简洁的绿色连帽短袍、柔软的棕色短靴，腰间系着一个小皮袋。
角色神情友善、眼神温和，气质勇敢而又温暖。
背着一把只用来提供帮助、绝不伤害生灵的小木弓。

主题（Theme）：
这位主角专门在森林里保护和救助松鼠、小鸟和兔子等小动物。

画风（Style）：
儿童绘本插画风格，手绘水彩质感，柔和的轮廓线，温暖的大地色系，充满童趣且亲切友好。
采用适合图画书的头身比例（头部略微偏大，面部表情生动传神）。

约束条件（Constraints）：
- 100% 原创角色（严禁借用受版权保护的现成动漫角色）
- 画面中不出现任何文字
- 不要水印
- 使用简洁的森林背景，以便清晰突出主角形象

Continue the children’s book story using the same character.

Scene:
The same young forest hero is gently helping a frightened squirrel
out of a fallen tree after a winter storm.
The character kneels beside the squirrel, offering reassurance.

Character Consistency:
- Same green hooded tunic
- Same facial features, proportions, and color palette
- Same gentle, heroic personality

Style:
Children’s book watercolor illustration,
soft lighting, snowy forest environment,
warm and comforting mood.

Constraints:
- Do not redesign the character
- No text
- No watermarks

# 中文对应写法：
沿用同一个主角形象，继续绘制儿童绘本的下一幕故事。

场景（Scene）：
同一位年轻的森林小英雄，在一场冬季暴风雪过后，正温柔地帮助一只受惊的小松鼠从倒下的树干里脱困。
主角单膝跪在松鼠身旁，轻声安抚它。

角色一致性要求（Character Consistency）：
- 保持完全相同的绿色连帽短袍
- 保持完全相同的五官特征、头身比例与色彩搭配
- 保持同样温和、勇敢的气质

画风（Style）：
儿童绘本水彩插画风格，柔和的光线，白雪皑皑的森林环境，温暖治愈的氛围。

约束条件（Constraints）：
- 严禁重新设计或改动主角形象
- 画面中不出现任何文字
- 不要水印

In this room photo, replace ONLY the white chairs with chairs made of wood.
Preserve camera angle, room lighting, floor shadows, and surrounding objects.
Keep all other aspects of the image unchanged.
Photorealistic contact shadows and fabric texture.

# 中文对应写法：
在这张房间照片中，仅将白色餐椅替换为木质餐椅。
完整保留原有的相机机位角度、房间光线、地板投影以及周围的所有物品。
保持画面的所有其他部分完全不变。
呈现出照片级真实的地面接触阴影与材质肌理。

Create a Christmas holiday card illustration.

Scene:
a cozy Christmas scene with an old teddy bear sitting inside a keepsake box, slightly worn fur, soft stitching repairs, placed near a window with falling snow outside. The scene suggests the child has grown up, but the memories remain.

Mood:
Warm, nostalgic, gentle, emotional.

Style:
Premium holiday card photography, soft cinematic lighting,
realistic textures, shallow depth of field,
tasteful bokeh lights, high print-quality composition.

Constraints:
- Original artwork only
- No trademarks
- No watermarks
- No logos

Include ONLY this card text (verbatim):
"Merry Christmas — some memories never fade."

# 中文对应写法：
生成一张圣诞节日贺卡画面。

场景（Scene）：
温馨的圣诞一角：一只旧泰迪熊坐在纪念品木盒里，绒毛微微磨损，带着温柔的缝补针脚，木盒摆在窗边，窗外正飘着雪花。画面暗示当年的孩子已经长大，但温暖的记忆依然留存。

情绪（Mood）：
温暖、怀旧、轻柔、触动人心。

风格（Style）：
高档节日贺卡商业摄影质感，柔和的电影感布光，真实的毛绒与木盒肌理，浅景深，雅致的暖光背景光斑（Bokeh），符合高规格印刷品的考究构图。

约束条件（Constraints）：
- 仅限原创画面
- 不得包含任何受保护商标
- 不要水印
- 不要 Logo

画面中仅包含以下贺卡文字（严格逐字匹配）：
"Merry Christmas — some memories never fade."

Create a collectible action figure of a vintage-style toy propeller airplane with rounded wings, a front-mounted spinning propeller, slightly worn paint edges, classic childhood proportions, designed as a nostalgic holiday collectible, in blister packaging.

Concept:
A nostalgic holiday collectible inspired by the simple toy airplanes
children used to play with during winter holidays.
Evokes warmth, imagination, and childhood wonder.

Style:
Premium toy photography, realistic plastic and painted metal textures,
studio lighting, shallow depth of field,
sharp label printing, high-end retail presentation.

Constraints:
- Original design only
- No trademarks
- No watermarks
- No logos

Include ONLY this packaging text (verbatim):
"Christmas Memories Edition"

# 中文对应写法：
生成一款装在透明吸塑包装盒（Blister Packaging）里的复古风螺旋桨玩具飞机收藏手办：圆润的机翼、前置旋转螺旋桨、边缘带有轻微做旧磨损的漆面、经典的童年玩具比例，整体定位为怀旧节日限定收藏品。

概念定位（Concept）：
灵感源自过去孩子们在冬日假期常玩的简单玩具小飞机，唤起温暖、想象力与童年惊喜感。

视觉风格（Style）：
高档潮玩商业摄影质感，逼真的塑料与涂装金属表面肌理，专业摄影棚布光，浅景深，锐利清晰的包装卡纸印刷，高端零售陈列质感。

约束条件（Constraints）：
- 仅限原创设计
- 不得包含任何商标
- 不要水印
- 不要 Logo

包装上仅包含以下文字（严格逐字匹配）：
"Christmas Memories Edition"

import base64
from pathlib import Path
from openai import OpenAI

client = OpenAI()

# 任务 1：批量生成 4 个版本的透明底品牌 Logo
logo_prompt = """
Create an original, non-infringing logo for a company called Field & Flour, a local bakery.
The logo should feel warm, simple, and timeless. Use clean, vector-like shapes, a strong silhouette, and balanced negative space.
Favor simplicity over detail so it reads clearly at small and large sizes. Flat design, minimal strokes, no gradients unless essential.
Fully transparent background. Deliver a single centered logo with generous padding, clean alpha edges, and no solid backdrop, scenery, checkerboard, or watermark.
"""

result = client.images.generate(
    model="gpt-image-2.5-sunburst",  # 也可切换为 gpt-image-2.5-flare 或 gpt-image-2
    prompt=logo_prompt,
    size="1024x1536",
    quality="medium",
    background="transparent",
    output_format="png",
    n=4,  # 一次生成 4 个变体方案
)

# 直接解码写入原始 PNG 字节流，完整保留 Alpha 透明通道
for index, item in enumerate(result.data, start=1):
    Path(f"logo-generation-{index}.png").write_bytes(
        base64.b64decode(item.b64_json)
    )

# 任务 2：从实拍参考图中提取透明底商品素材
cutout_prompt = """
Extract the product from the input image and isolate it on a fully transparent background.
Output: centered product, crisp silhouette, no halos/fringing.
Preserve product geometry and label legibility exactly.
Add only light polishing. Do not add a solid backdrop, checkerboard, scenery, or shadow.
Do not restyle the product; remove the background and preserve clean alpha transparency.
"""

edit_result = client.images.edit(
    model="gpt-image-2.5-sunburst",
    image=[
        Path("input_images/shampoo.webp"),
    ],
    prompt=cutout_prompt,
    size="1024x1536",
    quality="medium",
    background="transparent",
    output_format="png",
)

Path("extract-product.png").write_bytes(
    base64.b64decode(edit_result.data[0].b64_json)
)

require "base64"
require "openai"
require "pathname"

client = OpenAI::Client.new

result = client.images.generate(
  model: "gpt-image-2.5-sunburst",
  prompt: "Create an original logo for Field & Flour, a local bakery. Use warm, simple shapes on a fully transparent background, with clean alpha edges and no shadow or checkerboard.",
  size: "1024x1536",
  quality: :medium,
  background: :transparent,
  output_format: :png,
  n: 4
)

Array(result.data).each_with_index do |item, index|
  File.binwrite(
    "logo-generation-#{index + 1}-gpt-image-2.5-sunburst.png",
    Base64.strict_decode64(item.b64_json || raise("No PNG returned"))
  )
end

edit_result = client.images.edit(
  model: "gpt-image-2.5-sunburst",
  image: OpenAI::FilePart.new(Pathname("input_images/shampoo.webp"), content_type: "image/webp"),
  prompt: "Extract the product onto a fully transparent background. Preserve its geometry and label, with clean edges and no shadow or restyling.",
  size: "1024x1536",
  quality: :medium,
  background: :transparent,
  output_format: :png
)

File.binwrite(
  "extract-product-gpt-image-2.5-sunburst.png",
  Base64.strict_decode64(Array(edit_result.data).fetch(0).b64_json || raise("No PNG returned"))
)