Every prompt below was generated with GPT Image 2.5 Fast 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.
Original results
These examples use media produced for Made. Prompts are included when the production record allows them.
“Pastel mint vintage convertible parked on a coastal road at sunrise, empty road curving along the cliffs. 35mm film still, soft natural light, muted earth tones with one mint accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
“Overhead acai bowl with blueberries, banana and granola on a sunny kitchen table. 35mm film still, soft natural light, muted earth tones with one violet accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
“Scruffy terrier sitting on a chair at an outdoor café table, morning light, espresso cup on the table. 35mm film still, soft natural light, muted earth tones with one red accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
“Row of surfboards leaning against a weathered beach shack at golden hour, sand drifts at the base. 35mm film still, soft natural light, muted earth tones with one teal accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
“Steaming bowl of ramen on a wooden counter under warm neon light late at night, chopsticks resting on the bowl. 35mm film still, soft natural light, muted earth tones with one pink neon accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
“Candid portrait of a woman in a rust linen shirt walking through a sunflower field at dusk, looking back over her shoulder. 35mm film still, soft natural light, muted earth tones with one yellow accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
Describe the subject, composition, and light. Fast works from text alone.
Choose square (1024×1024) or 3:4 portrait (768×1024).
Your request joins others for a moment and renders in a shared call; you get back only your image.
Re-run the winning prompt on GPT Image 2.5 Flare or Sunburst for larger sizes, quality control, or edits.
Iteration is cheap here: GPT Image 2.5 Fast costs 1 credit / 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 Fast pricing breakdown.
It is Made’s batched GPT Image 2.5. Compatible requests from different people share one model call, which brings the price down.
More tested prompts across all models live in the prompt library, and the full GPT Image 2.5 Fast capability rundown is on the model page.