The FLUX 3 family product available on this platform: text generation and reference editing at 1K, 2K or 4K, with PNG, JPEG and WebP output.
Klein handles both starting points. Write a description for a fresh image, or upload references for an edit, and pick the tier and shape that match the destination.
Output format is the detail worth noticing: PNG, JPEG and WebP are all selectable, so web-focused work can ship straight to the format it needs.
Choose a quality tier, a shape and an output format. In editing mode the shape list also includes automatic, which follows the reference you uploaded.
Generate from a written description or edit your own images, with up to ten references per edit.
PNG, JPEG and WebP output, selectable per task rather than fixed by the model.
Keep the proportions of the reference automatically, or pick an explicit ratio from the standard list.
Produce WebP directly for pages where file weight matters.
Let the output adopt the reference proportions instead of forcing a ratio.
Everyday image generation across the usual ratio list without specialist options.
Use a button on this page. It opens the right workspace with this model already selected, in the language you are reading now.
Write what should happen in the shot or image. Concrete subjects, framing and action give the model more to work with than short labels.
Choose length or quality tier, shape and sound where offered, then read the credit quote for those exact settings before you generate.
Generation uses account credits. Cost depends on the model, quality and output size or duration. Reference images, video or audio may add charges in some modes. Check the workspace quote for your selected inputs and settings before generating; the pricing page lists credit packages.
See credit packagesYes. Klein is the FLUX 3 family product selectable on this platform today; other family variants are not offered.
Yes. PNG, JPEG and WebP are all selectable before you generate.
Up to ten images per editing task.
No. There is no background control on this model, so use a model with explicit background support for transparent output.
Other models on this platform that do a similar job, or that pair well with this one.
Nano Banana 2.1 covers both workflows on one model: images from a description, or edits driven by up to ten of your own reference images, at 1K, 2K or 4K.
Read the guideThe second selectable GPT Image 2.5 product: the same tiers, shapes, background control and credit prices as Flare, with this guide focused on editing your own images.
Read the guideSeedance 2.5 creates a clip from a written description or from one starting image, with whole-second lengths from 4 to 30 seconds and three quality tiers.
Read the guide