Icons and flat graphics
choose low complexity for a restrained result.
Image generation & editing
Generate a fixed 1K image or a text-only GIF with adjustable scene detail.
Loading model settings…
Your prompt, settings, and references stay together in a new Canvas.
01 / Meet the model
GPT Image 2.6 is a fixed 1K image model with two output modes. PNG supports a chosen aspect ratio and up to sixteen references, while GIF is text-only and uses automatic sizing. Complexity steers how much scene detail the prompt is rendered with and does not change the price, which makes it useful for comparing a clean icon against a richer illustration without changing the model.
02 / Choose it for
choose low complexity for a restrained result.
use high complexity when the scene needs more detail.
produce a GIF from a prompt without any references.
03 / Before you create
Model settings. Availability, input mode, and references can narrow the choices offered in Canvas.
04 / A closer look
Choose GIF only for a text-only animated asset that does not need references or a chosen aspect ratio. PNG is the default for still images, supports sixteen references, and lets you pick a ratio; switching to GIF discards those controls rather than combining them.
Text prompt · optional reference images. The input controls above show the options available for your selected mode.
1:1 · 3:2 · 2:3 · 4:3 · 3:4 · 5:4 · 4:5 · 16:9 · 9:16 · 21:9. 1K.
Start with the format you intend to publish, then choose the available output settings. Changing inputs can change the choices. Review the current Gem estimate before Generate; availability and cost can vary.