28+ prompts. 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.
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.
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.
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.
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."
Create a premium, ultra-refined Showa-era Japanese vintage travel poster for [LOCATION].
FORMAT: Vertical 3:4 | Collector’s travel poster | Mid-century Japanese railway tourism aesthetic
CORE CONCEPT
Create a beautifully composed, instantly recognizable travel scene representing [LOCATION]. Feature its most iconic landmark, architecture, landscape, streets, transportation, and atmospheric details, selecting elements that naturally define the destination.
Reimagine the scene as an authentic 1960s–1970s Japanese railway tourism poster, inspired by classic Japanese National Railways travel advertising and sophisticated vintage screen-printed graphics.
The result should feel like an originally designed vintage poster, not a modern photograph with a retro filter.
VISUAL STYLE
Use bold geometric forms, simplified architecture, clean perspective lines, strong silhouettes, and elegant flat graphic shapes.
Combine sophisticated mid-century Japanese graphic design with traditional screen-print and lithographic aesthetics. Keep the composition cinematic, balanced, spacious, and visually striking.
People and vehicles should be minimal and stylized rather than photorealistic.
COLOR & PRINT TEXTURE
Use a restrained vintage palette of:
deep navy blue, warm ivory/aged paper, muted mustard yellow, and vermilion red accents.
Use flat printed color fields rather than digital gradients. Add subtle paper grain, authentic ink texture, slight ink wear, and delicate vintage print misregistration for a convincing screen-printed feel.
Avoid neon colors, glossy 3D rendering, excessive photorealism, modern AI-art aesthetics, and overly saturated colors.
TYPOGRAPHY & LAYOUT
Reserve generous negative space at the bottom for elegant vintage typography.
Main title: "[LOCATION]"
Large, bold, geometric sans-serif lettering.
Add a refined, location-appropriate subtitle beneath it with generous letter spacing.
Place 2026 discreetly at the bottom left and No.01 at the bottom right.
Typography should feel authentic to a premium Japanese railway tourism poster: restrained, elegant, highly legible, and perfectly integrated into the artwork.
FINAL RESULT
Create a timeless, sophisticated Japanese Showa-era travel poster that feels like a rare original screen-printed railway advertisement from the 1960s–1970s, while showcasing the unique identity, beauty, and most recognizable visual characteristics of [LOCATION].
IMPORTANT: Make [LOCATION] immediately recognizable. Prioritize iconic local landmarks, authentic architecture, distinctive landscapes, and culturally characteristic details. Do not invent generic scenery that could represent any destination.
a fashion campaign for an invented label, shot from a camera on the ground with a 24mm lens tilted fifteen degrees. Six people in electric blue, tomato red, lime green, hot pink, butter yellow and lilac, all posed differently, against plain cobalt sky.
Create a minimalist 16:9 launch graphic on a pure warm-white background with enormous amounts of clean negative space.
Centered composition.
Top line: the exact word "ChatGPT" in very large, clean, black modern sans-serif typography.
Directly underneath it: the exact text "Images 2.5".
Each individual character in "Images 2.5" must be rendered as a completely different physical or artistic medium while still remaining immediately readable as the correct letter.
Despite the wildly different materials, preserve perfect baseline alignment, spacing and legibility.
No extra decorative elements, no additional text.
Create a perfectly aligned 3 x 3 grid of nine mid-century modern motivational posters sharing one limited palette.
Exact headlines: Travel Farther, CREATE, GROW TOGETHER, LISTEN MORE, FIND YOUR BALANCE, DRINK MORE WATER, LEARN SOMETHING NEW, SEE THE BEAUTY, CHOOSE KINDNESS.
Flat printed poster aesthetic, equal gutters, no mockup frames.
A collectible sheet of eight vintage U.S. national park postage stamps in a 4 x 2 grid on black.
Yellowstone, Grand Canyon, Acadia, Zion, Glacier, Great Smoky Mountains, Denali, Everglades.
WPA travel-poster illustration, perforated cream edges, readable type, one series not eight unrelated pictures.
Luxurious editorial flat-lay of an old-world European wedding invitation on ivory cotton paper with gold engraving.
Exact names Amelia Rose and Ethan James, Villa Eterna, Lake Como.
Roses, ribbons, wax seal, velvet ring box. No modern minimalist paper.
Design a vertical vintage Japanese commercial poster advertising a fictional ChatGPT sticker pack.
Bright saturated cobalt-blue background covering the full poster.
Authentic distressed physical print: worn white edges, fold lines, paper scratches, subtle discoloration, screen-print texture.
At the top, small yellow Japanese text. Below it, gigantic two-line yellow headline: ChatGPT Stickers.
Centered white text: New sticker pack, with small decorative yellow rays.
Main subject: an adorable realistic black cat sitting upright against the blue background, huge round golden-yellow eyes, holding a white rectangular sticker sheet with one paw.
Stickers on the sheet: blue speech bubble, pink exclamation bubble, sparkles, orange goldfish, yellow Nice! bubble, blue Wow! bubble, small black cat face, green thumbs-up, pink heart.
Vertical yellow Japanese copy along the left side.
Quirky 1970s-1980s Japanese stationery advertisement, playful retro product packaging, perfectly legible typography, 2:3 vertical format.
A futuristic trading card with a dark, moody neon aesthetic and soft sci-fi lighting. The card features a semi-transparent rounded rectangle with slightly muted glowing edges, appearing as if made of holographic glass. At its center floats the emblem of a fictional AI company: a minimalist geometric owl inside a hexagon, rendered in a cyan-to-violet gradient. The card top reads "NOCTUA LABS", the bottom reads "FOUNDER SERIES · 001". Subtle circuit traces and floating particles decorate the card. 3:2 landscape, ultra-detailed, premium collectible feel.
创作一张超高分辨率的 4:5 竖版旅行海报,主题围绕 TOKYO。所有可见文字必须仅使用英文,拼写完美且排版专业,不得出现字母扭曲、随机符号或 AI 乱码。核心设计:将巨大的单词“TOKYO”醒目地置于中心。使用高大、粗体的无衬线字体,每个字母内包含该地点不同的插画场景。将字母视为“画廊橱窗”,融入可识别的地标、建筑、街道、交通、自然、文化和当地氛围。将各字母间的场景连接起来,形成一幅连贯的视觉全景图。顶部条带:在排版上方添加一条细长的全景条带,根据需要加入简化的当地元素,如天际线、道路、车辆、火车、船只、桥梁、鸟类、云朵、太阳或海岸线。风格:中世纪现代编辑海报、瑞士平面设计、高端旅行品牌感、极简扁平矢量插画、建筑信息图表美学、几何形状、边缘利落、细腻的线条艺术细节、强烈的留白以及精致的构图。色彩:根据 TOKYO 自动提取协调的调色板。仅使用 4–6 种柔和的粉彩色调,呈现优雅、低饱和度的旅行海报质感。
一张印在米色纸张上的科学植物学海报。画面中心是一朵巨大的 勿忘我 水彩画,包含根部,茎和花瓣上带有细小的编号标签。顶部为斜体衬线字体标题:"FORGET-ME-NOT"。副标题:"A FIELD PLATE"。底部:"PLATE VII · 1887"。边缘处有铅笔笔记。米色、靛蓝色、绿色,2:3 纵横比。
1Say what must not change. This is the one habit that separates 2.5 from every earlier model. "Keep the pose, lighting, camera angle and background exactly as they are; change only the jacket" gets you a changed jacket. Leave the lock out and the model re-imagines the whole frame.
2Change one variable at a time. Edits compound badly. Move the lamp, look, then relight — three prompts, three checkpoints. Asking for the move and the relight and a new colour grade in one go is how you lose the face.
3Put exact text in quotation marks. Typography is where 2.5 pulled ahead. Write the words you want rendered inside quotes, spell out the case, and name the type treatment: `the words "FIELD & FLOUR" in a bold condensed sans, centred`. Describing the text instead of quoting it gets you approximate letters.
4Assign every reference a job. With more than one input, say which is which: image 1 is the person, image 2 is the garment, image 3 is the location. Unassigned references get blended, and the blend is never the one you wanted.
5Photoreal comes from camera language. Lens length, distance, light source, time of day, film stock, depth of field. "50mm at eye level, soft coastal daylight, shallow depth of field, fine grain" reads as a photograph; "photorealistic, 8k, ultra detailed" reads as a render.
6For layouts, describe structure before content. Infographics, slides, UI and posters land far better when the prompt gives the grid first — how many panels, what sits where, what the margins do — and only then fills in the words and images.
7Write negatives as concrete objects. "No watermark, no extra fingers, no duplicated logo, no orange colour cast" beats "avoid AI artifacts". Name the artefact you keep getting and it usually goes away.
8Pick the tier on purpose. On apimodels.app every quality tier is priced differently (1K runs $0.008 to $0.18, a 22x spread), so the tier is both a detail and a cost decision. Low is for layout checks and thumbnails — fastest and cheapest. Medium is the sane default for most finished work. High is for skin, fabric, dense type and anything you will print. Ask for 4K only when the detail is really there to resolve — an upscale of a 1K idea looks like an upscale, and 4K is the one axis that does cost more.
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.
Frequently asked questions
What is GPT Image 2.5, and what is the difference between Flare and Sunburst?
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.
Are these prompts free to use?
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.
Where did these prompts come from?
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.
Are the images on this page generated by GPT Image 2.5?
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.
Where can I run GPT Image 2.5?
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.
Do these prompts still work on GPT Image 2 or other image models?
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.
Run these prompts on apimodels.app
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.