Skip to main content

FLUX.2 [dev] text-to-image from Black Forest Labs' open-weights model. It writes readable text inside the picture, follows hex colour codes, and renders at about one megapixel or up to 2048 pixels on the long side, in nine aspect ratios.

From $0.012/image

Workbench

These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.

  • motel-neon-slipOutput
    motel-neon-slip

    A portrait at 2:3 and 1k lit by two hex colours from a neon sign. The room took on the magenta and blue mix, and the quoted word VACANCY is spelled correctly.

    • 7714
    • 1k
    • 2:3
  • record-store-closingOutput
    record-store-closing

    Two women in a record store after hours at 3:2 and 2k. The clothing is described piece by piece, the sign text is quoted and the lamp colour is a hex code; the sign came back reading CLOSED.

    • 6164
    • 2k
    • 3:2
  • sailboat-golden-hourOutput
    sailboat-golden-hour

    Two men on a sailboat at 16:9 and 2k. The prompt gives their clothes, what each one does and the colour of the sea, and the low golden sun comes through the sail.

    • 8822
    • 2k
    • 16:9

This example starts at $0.012 per image. The Playground updates the estimate when you change the settings.