--- title: "GPT Image 2.5 Flare Prompts: 6 Tested Examples | Made" description: "Copy 6 tested GPT Image 2.5 Flare prompts with the actual outputs they produced in Made, plus how to write your own: settings, strengths, and pitfalls." url: https://www.made.app/models/gpt-image-2-5-flare/prompts --- [Models](https://www.made.app/models) / [GPT Image 2.5 Flare](https://www.made.app/models/gpt-image-2-5-flare) / Prompts # GPT Image 2.5 Flare prompts that actually ran Every prompt below was generated with GPT Image 2.5 Flare in Made, and the output next to it is what came back — not a curated stock image. Copy a prompt as a starting point, then use the guide underneath to adapt it. [Try GPT Image 2.5 Flare](https://www.made.app/models/gpt-image-2-5-flare) [GPT Image 2.5 Flare pricing: 1–42 credits / image](https://www.made.app/price-sheet/gpt-image-2-5-flare) Original results ## GPT Image 2.5 Flare prompts and their outputs These examples use media produced for Made. Prompts are included when the production record allows them. ![streetwear lookbook shot on a city rooftop generated with GPT Image 2.5 Flare in Made](https://www.made.app/images/models/gpt-image-2-5-flare/rooftop-lookbook.jpg) ### GPT Image 2.5 Flare: Rooftop lookbook “Model in an oversized olive bomber jacket and cargo trousers standing on a city rooftop at golden hour, haze over the skyline. 35mm film still, soft natural light, muted earth tones with one lime accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.” ![unbranded sneaker on a concrete plinth generated with GPT Image 2.5 Flare in Made](https://www.made.app/images/models/gpt-image-2-5-flare/sneaker-plinth.jpg) ### GPT Image 2.5 Flare: Product on plinth “Unbranded white-and-sage sneaker on a raw concrete plinth, hard side light, a single lime lace detail, clean studio backdrop. 35mm film still, soft natural light, muted earth tones with one lime accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.” ![woven clothing tag reading CAPSULE 07 generated with GPT Image 2.5 Flare in Made](https://www.made.app/images/models/gpt-image-2-5-flare/garment-tag.jpg) ### GPT Image 2.5 Flare: Woven tag “Macro of a woven clothing tag stitched into a heavyweight hoodie, the tag reading exactly "CAPSULE 07" above a smaller line "MADE IN SMALL BATCHES". Clean editorial design, muted earth tones with one lime accent, subtle paper texture, sharp legible type, no other words or logos.” ![boutique window display at dusk generated with GPT Image 2.5 Flare in Made](https://www.made.app/images/models/gpt-image-2-5-flare/store-window.jpg) ### GPT Image 2.5 Flare: Store window “Boutique storefront window at dusk with a single mannequin in a tailored coat, warm interior glow, reflections of passing traffic on the glass. 35mm film still, soft natural light, muted earth tones with one amber accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.” ![fabric swatches and tailoring tools flat lay generated with GPT Image 2.5 Flare in Made](https://www.made.app/images/models/gpt-image-2-5-flare/fabric-swatches.jpg) ### GPT Image 2.5 Flare: Studio flat lay “Flat lay of fabric swatches, tailor's chalk, scissors and a measuring tape on a wooden cutting table. 35mm film still, soft natural light, muted earth tones with one rust accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.” ![skater resting at an empty skatepark generated with GPT Image 2.5 Flare in Made](https://www.made.app/images/models/gpt-image-2-5-flare/skatepark-rest.jpg) ### GPT Image 2.5 Flare: Skatepark portrait “Candid portrait of a skater resting on a board at an empty concrete skatepark, plain black canvas sneakers with no stripes, late sun flaring behind him. 35mm film still, soft natural light, muted earth tones with one orange accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.” ## How to write a GPT Image 2.5 Flare prompt 1. **Write the brief** Describe the subject, composition, and light. Put any words that must appear in the image in quotes. 2. **Add references to edit** Upload up to 16 images and say what should change; Made routes the request to the edit endpoint. 3. **Pick size and quality** Choose one of nine sizes up to 4K and a quality tier. Made starts at low, the cheapest; move up for the final. 4. **Check the price and run** Made shows the exact price for your settings before you generate, and refunds failed generations. ## What GPT Image 2.5 Flare responds well to ### Prompt for these jobs - Edits that change only what you ask and keep the rest of the photo - Posters and graphics with readable headlines - Up to 4K output in 16:9 or 9:16 - Combining several reference images in one edit ### Check the output for - Price scales with size and quality: from 1 credit for a 1024×1024 image at low, up to 41 credits at 4K max. Each reference image adds about 2 credits. - There is no automatic size or quality, because the price has to be known before the job runs. Pick the size closest to your input. - For the cheapest text-only drafts, GPT Image 2.5 Fast batches requests and costs less. Iteration is cheap here: GPT Image 2.5 Flare costs 1–42 credits / image, so rewriting a prompt and rerunning it is a normal part of the workflow, not a budget decision. See the [full GPT Image 2.5 Flare pricing breakdown](https://www.made.app/price-sheet/gpt-image-2-5-flare). Questions, answered ## GPT Image 2.5 Flare prompts FAQ Need a specific answer? [Contact support](mailto:support@made.app) ### What is GPT Image 2.5 Flare? It is OpenAI’s GPT Image 2.5 Flare, run unbatched in Made, for fast, high-quality generation and edits that change only what you ask. ### How much does GPT Image 2.5 Flare cost in Made? A 1024×1024 image is 1 credit at low quality, the default, and 2 credits at medium. Larger sizes and higher tiers cost more. Each reference image adds about 2 credits. The exact price appears before you generate. ### Can it edit my photos? Yes. Add up to 16 reference images and describe the change. It is built to change only what you ask and keep the rest of the image. ### Which sizes and quality tiers are there? Nine sizes from 1024×768 up to 4K (3840×2160 and 2160×3840), and five quality tiers: low, medium, high, xhigh, and max. There is no automatic size. ### How does Flare compare to Sunburst? Both are the original GPT Image 2.5 and cost the same in Made. Flare is the fast, general-purpose pick; Sunburst is tuned for maximum detail and tighter control in demanding edits. ### When should I choose another model? Choose GPT Image 2.5 Fast for the cheapest text-only drafts, Nano Banana Pro for 4K images with strong identity, or GPT Image 2 for OpenAI’s previous generation. More tested prompts across all models live in the [prompt library](https://www.made.app/prompts), and the full GPT Image 2.5 Flare capability rundown is on the [model page](https://www.made.app/models/gpt-image-2-5-flare). --- Markdown version of https://www.made.app/models/gpt-image-2-5-flare/prompts. Every public Made page has one at its URL plus .md (https://www.made.app/models/gpt-image-2-5-flare/prompts.md). Site summary for AI assistants: https://www.made.app/llms.txt