OpenAI · image model
1–42 credits / image · every plan · price breakdown · API playground
Made with GPT Image 2.5 Sunburst · Watch movement macro
GPT Image 2.5 Sunburst is the original, unbatched OpenAI GPT Image 2.5 tuned for maximum detail and tighter control across demanding edits, in nine sizes up to 4K.
Original results
These examples use media produced for Made. Prompts are included when the production record allows them.
“Macro photograph of an open mechanical watch movement, ruby jewels, blued screws and brushed gears, specular highlights. 35mm film still, soft natural light, muted earth tones with one gold accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
“Jeweler wearing a loupe working at a cluttered bench under a warm lamp, tiny files and pliers, focused expression. 35mm film still, soft natural light, muted earth tones with one brass accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
“Gold signet ring engraved with a single serif letter "M" resting on wet dark slate, water droplets catching light. 35mm film still, soft natural light, muted earth tones with one gold accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
“Detailed vintage botanical illustration of a fern frond and a moth on aged paper, fine ink linework, small caption reading exactly "Polypodium vulgare". Clean editorial design, muted earth tones with one moss green accent, subtle paper texture, sharp legible type, no other words or logos.”
“Luthier's workshop wall with unfinished violin bodies hanging in rows, curled wood shavings, dust in window light. 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.”
“Macro of handmade bobbin lace draped over dark velvet, individual threads and knots sharply resolved. 35mm film still, soft natural light, muted earth tones with one ivory accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
These are the controls exposed by Made, which may be narrower than a provider’s full API.
Spell out the subject, materials, and light, and list every constraint the image must keep.
Upload up to 16 images and describe exactly what should change; Made routes the request to the edit endpoint.
Choose one of nine sizes up to 4K. Made starts at low, the cheapest; raise the quality tier for the final.
Made shows the exact price for your settings before you generate, and refunds failed generations.
image
GPT Image 2.5 Flare is the original, unbatched OpenAI GPT Image 2.5 in Made: fast, high-quality generation and precise edits that change only what you ask, in nine sizes up to 4K.
Explore model →image
GPT Image 2 is OpenAI’s flagship image model in Made, strong at photorealism, exact prompt adherence, complex layouts, and readable typography, with instruction-based editing from a reference image.
Explore model →image
Seedream 5 Pro is ByteDance’s flagship image model, pairing the family’s signature photorealism with strong typography, complex layouts, and reference-guided consistency across up to 10 input images.
Explore model →Create scroll-stopping product photos and marketing visuals in seconds. Describe your shot, pick your style, and get professional images ready for your store, social feed, or ad campaign.
Open tool →Skip the complex menus and toolbars. Edit Images With Text Prompts. Our AI photo editor understands what you want. Type "remove the background" or "make it brighter" and watch it happen instantly.
Open tool →Upload an image, pick a size or type exact pixels, and choose whether Made crops it to fill, fits it inside, or stretches it.
Open tool →It is OpenAI’s GPT Image 2.5 Sunburst, run unbatched in Made, tuned for maximum detail and tighter control across demanding edits.