black-forest-labs/flux-1-dev-controlnet-lora/text-to-imageText-to-image on Black Forest Labs' FLUX.1 [dev] guided by Shakker Labs' ControlNet Union Pro 2.0, with up to three of your own FLUX.1 dev LoRAs. One control image sets the pose or layout, the prompt sets everything else, and nothing is filtered.
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.
Outputstudio-embrace-canny A canny edge map of a 16:9 frame, default strength 0.7 and window 0 to 0.8, no LoRA. The embrace and framing come from the lines; the prompt set the cast and the light.
- 9
Outputatelier-night-grayscale A grayscale photo as the control image at strength 0.9, no LoRA, 1.5k tier (1536 x 1120). The framing, her pose, the lamps and the shelves stay exactly where the photo has them; the prompt supplied the colour: the plum cardigan, the warm lamp pools and the teal night.
- 1012
- 1.5k
- 0.9
Outputbarre-balance-pose A hand-drawn pose skeleton at strength 0.9 with the control window ending at 0.65, and the Frosting Lane illustration LoRA for FLUX.1 [dev] at 1 with its trigger phrase first. The one-legged balance and both arm lines follow the skeleton; the model read it as a back view, and the wrap top came out long-sleeved.
- 1010
- 1.5k
- 0.9
Outputtailor-tape-depth A depth map at strength 0.8 and a pixel-art LoRA at 1 with its trigger word first. The stance, the measuring tape and the shelves follow the depth map, but the result is a painted illustration, not the hard pixel blocks the LoRA and the prompt asked for.
- 1011
- 1k
- 0.8
This example starts at $0.036 per image. The Playground updates the estimate when you change the settings.