Text-to-image on FLUX.1 Krea [dev], Black Forest Labs' 12-billion-parameter photographic model made with Krea, with up to three of your own LoRAs per request. Nine aspect ratios, a guidance control, JPEG, PNG or WebP, and no filter on prompts, 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.
Outputink-after-hours No LoRA: one paragraph naming the person, the dress, the desk lamp and the film look. The grain and muted colour are the model on its own.
- 2026
- 2:3
Outputlistening-booth No LoRA, 16:9. The light sources named in the prompt, a wall lamp and wood panelling, set the warm palette.
- 8
- 16:9
Outputpeony-forearm-illustrated The Frosting Lane illustration LoRA for FLUX.1 [dev] at 1.8 with its trigger phrase "frstingln illustration" first. At scale 1 it barely changed the photo.
- 7
- 3:4
Outputladder-between-shelves The same illustration LoRA at 1.8 on a record-shop scene, 3:4, with the clothing and lighting written out.
- 9
- 3:4
This example starts at $0.024 per image. The Playground updates the estimate when you change the settings.