Skip to main content

Softened — This model returns a result instead of an error, but requests beyond its own limits come back toned down. The call still succeeds and is still billed, so check the output rather than the status code.Browse every model at this filtering level
black-forest-labs/flux-3-klein-base-lora/text-to-image

FLUX 3 Klein Base LoRA text to image runs Black Forest Labs' undistilled FLUX 3 Image Klein with up to three of your own LoRA files. Fifteen aspect ratios at 1k or 2k, JPEG, PNG or WebP.

From $0.042/image
Run model

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.

  • fennec-cabin-stoveOutput
    fennec-cabin-stove

    A community character LoRA trained on Klein Base at 0.6, trigger "fennec girl" first. The LoRA sets the ears and the face; at 1 the same LoRA also added a painted finish and a stray signature, so 0.5 to 0.6 keeps it photographic.

    • 401
    • 1k
    • 3:4
  • fennec-sauna-collarOutput
    fennec-sauna-collar

    The same character LoRA at 0.5 in a two-person scene: only the woman takes the LoRA look, the man stays as described.

    • 402
    • 1k
    • 4:5
  • woodshed-doorwayOutput
    woodshed-doorway

    No LoRA, for comparison: the base model alone, 2:3 at 1k.

    • 413
    • 1k
    • 2:3

This example starts at $0.042 per image. The Playground updates the estimate when you change the settings.