--- title: "GPT Image 2 Prompts: 6 Tested Examples | Made" description: "Copy 6 tested GPT Image 2 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/prompts --- [Models](https://www.made.app/models) / [GPT Image 2](https://www.made.app/models/gpt-image-2) / Prompts # GPT Image 2 prompts that actually ran Every prompt below was generated with GPT Image 2 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](https://www.made.app/models/gpt-image-2) [GPT Image 2 pricing: 1–22 credits / image](https://www.made.app/price-sheet/gpt-image-2) Original results ## GPT Image 2 prompts and their outputs These examples use media produced for Made. Prompts are included when the production record allows them. ![candid portrait of a coffee roaster at a drum roaster generated with GPT Image 2 in Made](https://www.made.app/images/models/gpt-image-2/roaster-portrait.jpg) ### GPT Image 2: Roaster portrait “Candid portrait of a coffee roaster in her thirties checking beans at a vintage drum roaster, steam and warm tungsten light, charcoal apron. 35mm film still, soft natural light, muted earth tones with one copper accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.” ![kraft coffee bag with a legible SLOW MORNING label generated with GPT Image 2 in Made](https://www.made.app/images/models/gpt-image-2/coffee-bag-label.jpg) ### GPT Image 2: Label typography “Product photo of a matte kraft coffee bag on a walnut counter, printed label reading exactly "SLOW MORNING" with a smaller line "Ethiopia Guji · Light Roast". Clean editorial design, muted earth tones with one cobalt accent, subtle paper texture, sharp legible type, no other words or logos.” ![hand-lettered café chalkboard menu generated with GPT Image 2 in Made](https://www.made.app/images/models/gpt-image-2/menu-board.jpg) ### GPT Image 2: Menu board “Hand-lettered chalkboard menu on a white tiled café wall reading exactly "ESPRESSO 3 / CORTADO 4 / OAT LATTE 5", morning light across the tiles. Clean editorial design, muted earth tones with one sage accent, subtle paper texture, sharp legible type, no other words or logos.” ![overhead pour-over coffee setup on linen generated with GPT Image 2 in Made](https://www.made.app/images/models/gpt-image-2/pour-over.jpg) ### GPT Image 2: Pour-over flat lay “Overhead pour-over setup on natural linen: gooseneck kettle, ceramic dripper, glass carafe, scale, one cobalt cup. 35mm film still, soft natural light, muted earth tones with one cobalt accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.” ![small coffee roastery interior at dawn generated with GPT Image 2 in Made](https://www.made.app/images/models/gpt-image-2/roastery-dawn.jpg) ### GPT Image 2: Roastery interior “Wide shot of a small coffee roastery at dawn, burlap sacks stacked by the wall, copper cooling tray, dust floating in light beams. 35mm film still, soft natural light, muted earth tones with one copper accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.” ![cargo bike with coffee sacks on a cobblestone street generated with GPT Image 2 in Made](https://www.made.app/images/models/gpt-image-2/cargo-bike.jpg) ### GPT Image 2: Street scene “Cargo bike loaded with coffee sacks parked on a cobblestone street at golden hour, empty sidewalk, long shadows. 35mm film still, soft natural light, muted earth tones with one mustard accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.” ## How to write a GPT Image 2 prompt 1. **Write a precise brief** Describe the subject, composition, materials, lighting, and any exact display text in quotes. 2. **Pick size and quality** Choose square HD or 4:3 landscape. Made starts at low quality, the cheapest; raise it for the final. 3. **Add a reference for edits** Upload one image and describe the change when you are editing rather than generating. 4. **Review and refine** Inspect typography, hands, and fine detail, then adjust one constraint at a time or switch to high quality for the final. ## What GPT Image 2 responds well to ### Prompt for these jobs - Photorealistic product and editorial concepts - Layouts and graphics with readable typography - Prompts with several precise constraints - Instruction-based edits from one reference image ### Check the output for - The high quality tier is noticeably slower and more expensive than low or medium, so iterate at low or medium first. - Made currently exposes two output sizes (square HD and 4:3 landscape); other shapes need a resize step. Iteration is cheap here: GPT Image 2 costs 1–22 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 pricing breakdown](https://www.made.app/price-sheet/gpt-image-2). Questions, answered ## GPT Image 2 prompts FAQ Need a specific answer? [Contact support](mailto:support@made.app) ### What is GPT Image 2 best for? It excels at photorealism, exact prompt adherence, complex multi-element layouts, and high-quality typography — the demanding briefs where cheaper models drift. ### Can GPT Image 2 edit an existing image? Yes. Add one reference image and describe the change; Made routes the request to the model’s editing endpoint. ### What do the quality tiers change? Low, medium, and high trade generation time and cost for detail. Low is the default, the cheapest; use high for final assets where fine detail matters. ### Which sizes does Made expose? The current Made configuration offers square HD (1024×1024) and 4:3 landscape output in PNG. ### Is it good at rendering text? Typography is one of its documented strengths, and our benchmark headline rendered correctly. Dense small copy should still be reviewed before use. ### When should I choose another model? Use Nano Banana Pro or Flux 1.1 Pro when you want lower cost per image, or a Kontext model when strict source-image preservation is the priority. More tested prompts across all models live in the [prompt library](https://www.made.app/prompts), and the full GPT Image 2 capability rundown is on the [model page](https://www.made.app/models/gpt-image-2). --- Markdown version of https://www.made.app/models/gpt-image-2/prompts. Every public Made page has one at its URL plus .md (https://www.made.app/models/gpt-image-2/prompts.md). Site summary for AI assistants: https://www.made.app/llms.txt