
Copy-ready GPT Image 2.5 prompts, each with the image it produced and a link to where it came from. Text-to-image, precise edits, infographics, UI mockups, sprite sheets and product shots.
← All 238 GPT Image 2.5 prompts
Last updated: · GPT Image 2.5 model & pricing · API docs
GPT Image 2.5 is the image model OpenAI shipped on 9 September 2026, in two API variants: Flare, which matches GPT Image 2 on quality and editing at roughly half the latency, and Sunburst, which trades time for precision on demanding work. Both render text cleanly, generate natively at 1K, 2K and 4K, accept a mask for inpainting, and can return a transparent background. The headline change is controllable editing: you name what must not move, and it does not move. This page collects prompts that people actually ran, with the resulting image and a link to the source. On apimodels.app both variants are live priced by resolution and quality across fifteen cells — $0.008–$0.18 at 1K, $0.012–$0.35 at 2K, $0.02–$0.58 at 4K — billed only on success.
Source: OpenAI image prompting guide (the model vendor’s official site)


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.

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.

a domestic espresso machine drawn in section, 1960s service manual style, fine black line work with flat spot colour on cream paper. Fourteen numbered leader lines, a key down the right listing all fourteen parts, a scale bar in centimetres, and a title block reading FIG. 3 SECTIONAL VIEW MODEL C2.

a 1960s Sunday newspaper comic strip on yellowed newsprint, six panels in two rows of three. A park ranger and a bear with a notched ear, the same campsite in every panel, dialogue specified word for word, one sound effect, and one panel with no dialogue at all.

a cork notice board outside a Welsh village post office, overcast light, seven pinned items. A choral society flyer, a lost cat poster on yellow paper, a handwritten piano card, a bus timetable with four times, a sheepdog photo, tear off tabs, and one blank white card.

Realistic screenshot of Google Slides in Chrome on macOS. Deck title: Our Dynamic Sun. Selected slide: What Causes Solar Flares? Show chrome, sidebar continuity, and the current slide layout with four process steps plus a large sun photograph.

一幅数字插画:一只信天翁的形态由一组发光、干净且纯净的蓝色线条勾勒而成,悬浮于深色背景之上,突出其形态与特征。翼部的骨骼结构通过红色光晕加以强调,表示这一部位的特殊意义。整体风格兼具教育性与视觉吸引力,如同某种先进的生物成像技术,画面右下角配小号标注文字「ALBATROSS · 翼骨结构」。

以清晰的 45° 俯视角度展示一个等距微缩模型场景:上海东方明珠塔与外滩历史建筑群,多云天气效果巧妙融入场景,云影在楼宇间轻轻移动。使用基于物理的渲染(PBR)与逼真光照,纯色背景,居中构图,凸显三维模型精准细腻的美感。图片上方展示文字「上海 · 多云 20°C」,并附一朵云的天气图标。

特写镜头:一只手正拿着一张设计成 VS Code 中 JSON 文件外观的名片,名片上的代码以真实的 JSON 语法高亮格式呈现。窗口界面包含典型的工具栏图标和标题栏,标题显示为 Business Card.json,整体风格与 VS Code 界面完全一致,背景略微虚化。名片上的 JSON 代码为:{ "name": "Lin Yao", "title": "Product Designer", "email": "lin@studio.design", "theme": "minimal", "mood": "curious" }

创作一张手绘风格的信息图卡片,9:16 竖版。卡片主题鲜明,背景为带纸质肌理的米白色,整体质朴、亲切。卡片上方以红黑相间、对比鲜明的大号毛笔草书突出标题「深度工作的四个习惯」。正文分为四个小节,每节一句精炼中文短语:① 给一天定一个「灯塔任务」;② 让手机住进抽屉;③ 90 分钟冲刺,20 分钟散步;④ 收工前写三行复盘。字体保持草书流畅的韵律感,清晰可读又富有艺术气息。点缀简单有趣的手绘插画:台灯、闹钟、打盹的小猫、茶杯。周边适当留白。

主题:文化评论 / 英语等级:B2 / 字数:400 生成一份高端黑白社论风格的英文文章排版,类似于高级文学杂志、文化期刊或报纸专题页面。 文章语言必须为英语,写作必须严格遵循第一行指定的 CEFR 英语等级。英语等级可选 A1、A2、B1、B2、C1 或 C2;“主题”为文章话题;“字数”为目标英文单词数。 英语难度要求: - A1:非常基础,使用高频词汇和简单的短句。 - A2:常用生活词汇,简单的连接词和基础复合句。 - B1:更丰富的日常和抽象词汇,包含原因、示例和观点。 - B2:成熟的论证表达,词汇丰富,句式结构复杂且逻辑层次分明。 - C1:高级、准确且自然的英语,具备文学品质。 - C2:近乎母语者的文化评论或文学社论水平,运用细腻的修辞和抽象概念。 文章必须围绕指定主题展开,字数控制在目标字数的 ±10% 以内。排版应包含顶部的简洁报头(例如“THE LITERARY REVIEW”)、主标题使用优雅的高对比度衬线字体、作者署名以及三栏式社论网格。左侧包含一段醒目的粗体斜体引语,中心配有一张大型黑白纪实照片及说明文字。整体美学应克制、理性且具有学术感,使用带有轻微油墨晕染和颗粒感的米白色新闻纸纹理。仅限使用黑色、深灰色和米白色。底部应设有一个包含大型斜体行动号召(Call to Action)的信息框。

创建一个 2×2 的四格写实风格食谱拼图,展示在 乡村风格深色木质餐桌 上制作 奶油香蕉奶昔 的过程。 左上角:几根成熟的黄香蕉、一根剥皮的香蕉、一杯牛奶、一小碗浓稠的白酸奶以及一碗冰块,食材摆放整齐。 右上角:双手剥开成熟香蕉并将香蕉块放入透明玻璃搅拌杯的特写镜头。 左下角:牛奶从透明量杯中倒入装有香蕉块、酸奶和冰块的搅拌机中。 右下角:浓稠的奶油香蕉奶昔从搅拌机倒入透明玻璃杯中,背景中还有另一杯成品奶昔,木桌上散落着几片香蕉切片。 温暖的自然厨房光线,逼真的食物质感,奶油般的淡黄色奶昔,透明玻璃器皿,浅景深,乡村木质背景,构图简洁,专业美食摄影,高度细节,逼真的手部细节,自然阴影,4K 写实感,无文字,无标签,无水印。

一张逼真的手机拍摄照片,内容为用铅笔书写的手写论文,采用 Albert Einstein 的笔迹,书写在 8.5x11 英寸的横线纸上,主题关于 世界货币史。请确保笔迹呈现出 Einstein 特有的书写风格变化。在右上角添加一点 咖啡渍
创建一个超写实的美食摄影拼贴画,采用 2×2 网格,展示制作蓬松 美式松饼 的完整过程,并与参考构图保持一致。 左上:一张木质厨房餐桌,放着一个装满顺滑松饼面糊的大号白色陶瓷碗,周围整齐地摆放着各种配料:一个小碗里装着一颗生鸡蛋、一杯白面粉、一小碟黄油、一玻璃罐牛奶、一小碗泡打粉、一个打碎的蛋壳以及一个金属打蛋器。温暖的自然厨房光线,逼真的质感,整洁的俯视构图。 右上:炉灶上黑色不粘平底锅的特写。一只戴着米色隔热手套的手拿着汤勺,将浓稠的浅色松饼面糊倒入热锅中心。锅周围可见蒸汽和细小的黄油滴。温暖的木质厨房背景,逼真的烹饪动作。 左下:两个厚实蓬松的松饼在同一个黑色平底锅中煎制。其中一个松饼呈金棕色且已半熟,另一个正被铲子翻面。锅中升起淡淡的蒸汽,可见逼真的气泡和酥脆的边缘,温暖的自然光线。 右下:最终装盘,几块厚实、蓬松、金棕色的美式松饼精美地堆叠在盘子里,展现出柔软透气的层次和完美的焦黄色表面。令人垂涎的美食摄影特写,暖色调,逼真的质感和细腻的高光。 风格:照片级真实感,高级美食摄影,自然温暖的厨房光线,逼真的食材,适当的浅景深,细腻的纹理,真实的烹饪氛围,整洁的 2×2 分割构图,所有画面中厨具和食材保持一致,高细节,8K 分辨率,无文字,无标签,无水印。

Create a technical infographic of [OBJECT] 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 “OBJECT” 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.”
私は新しい疲労回復パジャマ(秋向け)の広告動画を作りたい。 疲労回復パジャマの名称は「RAKUNE」 その広告動画のストーリーボードを作って。 動画の尺は15秒。 映像スタイルはモーショングラフィックス。 カットの数は10。 動きがあり、派手なモーショングラフィックスにして欲しい。 癒しよりも「元気」や「活力」を打ち出したい。 CMに登場するのは架空の若手の日本人女優。 ナチュラルな魅力で、好感度は抜群、という設定。 全10カットの絵コンテを作って。アスペクト比は横長(16:9)
Prompt formula
What must not change + subject + scene, light and lens + exact text in quotes + material and surface detail + layout or aspect ratio + concrete negatives
Example: Keep the model, her pose, the studio lighting and the seamless grey backdrop exactly as they are. Replace only the tote she is holding with a natural-canvas one, and print the words "FIELD & FLOUR" across it in a bold condensed sans, dark brown, centred and following the fold of the fabric. Match the existing shadow direction and the slight warmth of the key light. Keep the canvas weave visible. No new props, no logo anywhere else, no change to her hands. 4:5.
GPT Image 2.5 is the image model OpenAI released on 9 September 2026. The API exposes two variants. Flare holds GPT Image 2 quality and editing ability while cutting latency by roughly half — it is the one to reach for by default. Sunburst spends longer per image and returns more precision, which shows up in skin, fabric, dense typography and complicated product surfaces. Both take a mask for inpainting, can return a transparent background, and generate natively at 1K, 2K and 4K rather than upscaling a smaller render.
Yes. Every prompt on this page is free to copy and run wherever you have access to GPT Image 2.5 — no login, no payment, no attribution required by us.
Three places, and each card says which. Some are the worked examples from OpenAI's own image prompting guide. Some were collected into public GitHub repositories, and we credit both the prompt author and the person who did the collecting. The rest are from creators' own posts on X, credited and linked back. Copyright stays with whoever wrote the prompt; we only curated and paired each one with the image its source published. If you wrote one of these and want it removed or the credit corrected, email us.
They are the images the source published alongside the prompt, not images we re-generated. Where a source only showed a design target or a side-by-side against an older model, the card says so rather than passing it off as that prompt's output. Eight prompts have no image because their source never published one, and we left those blank instead of substituting something else.
On apimodels.app, as gpt-image-2.5-flare and gpt-image-2.5-sunburst, live since 9 September 2026. Pricing runs on two axes, resolution and quality — $0.008–$0.18 at 1K, $0.012–$0.35 at 2K, $0.02–$0.58 at 4K (low to max) — so the tier you pick is both a detail and a cost decision. Charged only on success, with the same key covering GPT Image 2, Nano Banana, Seedream, Seedance, Kling, VEO and 110+ other models. Leave the quality parameter off and Flare defaults to medium, Sunburst to high.
Mostly, with one caveat. Composition, lighting, typography and style instructions transfer fine — that part of the craft is model-agnostic. What does not transfer is the strict edit locking: telling an older model to change only the jacket and leave everything else untouched gets you a partly re-imagined frame. If you are running these on something other than 2.5, expect to iterate more on the editing prompts and about the same on the text-to-image ones.
GPT Image 2.5 is live here alongside 120+ other image, video, audio and language models — one API, one key, pay as you go, with $0.10 of trial credit on sign-up.
The whole library is downloadable as JSON and CSV, one page per category with the full prompt text. Every entry credits the person who wrote it and links to the source; where a prompt reached us through someone else's collection, the collector is credited too. Prompt text belongs to its authors — the MIT licence covers the curation only. Open an issue to add a prompt or correct a credit.
View on GitHub