Image editing on FLUX.2 [dev], Black Forest Labs' 32-billion-parameter open-weights model, with up to three of your own LoRAs. One to three photos in, one image out at the first photo's shape or a ratio you choose at 1k or 2k, and no filter on sources, weights or results.
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.
Outputtwo-travellers-one-berth Two separate portraits as image 1 and image 2, one shared scene at 16:9 and 2k. Both faces carry over.
- 4303
- 2k
- 16:9
Outputplatform-to-dining-car One photo of a man on a foggy platform in, a dining car at night out: coat off, shirt open at the collar, same face. 3:4 at 1k, no LoRA.
- 4301
- 1k
- 3:4
Outputcompartment-day-to-night A vintage colour-photo LoRA at 0.9 on an edit: daytime coat to burgundy velvet at night, with the shape left on auto.
- 4302
- 1k
- auto
Outputcorridor-suit-to-shirtsleeves A painted-interior LoRA at 1 turns a corridor photo into a muted painting while the suit comes off to shirtsleeves; auto keeps the 4:3 shape.
- 4304
- 1k
- auto
This example starts at $0.036 per image. The Playground updates the estimate when you change the settings.