infery
← All models

FLUX.1 [dev] with Controlnets and Loras

flux-general-inpainting

Image editby Black Forest Labs

FLUX General Inpainting is a versatile endpoint that enables precise image editing and completion, supporting multiple AI extensions including LoRA, ControlNet, and IP-Adapter for enhanced control over inpainting results and sophisticated image modifications.

images

Details

Accepts
image

Pricing

Price
9.38 cr / megapixel

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seed The same seed and the same prompt given to the same version of the model will output the same image every time.
lorasarray
promptrequiredstringThe prompt to generate an image from.
nag_endnumber The proportion of steps to apply NAG. After the specified proportion of steps has been iterated, the remaining steps will use original attention processors in FLUX.
nag_taunumber The tau for NAG. Controls the normalization of the hidden state. Higher values will result in a less aggressive normalization, but may also lead to unexpected changes with respect to the original image. Not recommended to change this value.
mask_urlrequiredstring The mask to area to Inpaint in.
strengthnumberThe strength to use for inpainting/image-to-image. Only used if the image_url is provided. 1.0 is completely remakes the image while 0.0 preserves the original.
image_urlrequiredstringURL of image to use for inpainting. or img2img
max_shiftnumberMax shift for the scheduled timesteps
nag_alphanumber The alpha value for NAG. This value is used as a final weighting factor for steering the normalized guidance (positive and negative prompts) in the direction of the positive prompt. Higher values will result in less steering on the normalized guidance…
nag_scalenumber The scale for NAG. Higher values will result in a image that is more distant to the negative prompt.
schedulerstringenum: euler, dpmpp_2mScheduler for the denoising process.
sync_modebooleanIf `True`, the media will be returned as a data URI and the output data won't be available in the request history.
base_shiftnumberBase shift for the scheduled timesteps
fill_imageUse an image input to influence the generation. Can be used to fill images in masked areas.
image_sizeThe size of the generated image.
num_imagesintegerThe number of images to generate. This is always set to 1 for streaming output.
controlnetsarray The controlnets to use for the image generation. Only one controlnet is supported at the moment.
ip_adaptersarray IP-Adapter to use for image generation.
easycontrolsarray EasyControl Inputs to use for image generation.
use_cfg_zeroboolean Uses CFG-zero init sampling as in https://arxiv.org/abs/2503.18886.
use_real_cfgboolean Uses classical CFG as in SD1.5, SDXL, etc. Increases generation times and price when set to be true. If using XLabs IP-Adapter v1, this will be turned on!.
control_lorasarray
output_formatstringenum: jpeg, pngThe format of the generated image.
reference_endnumber The percentage of the total timesteps when the reference guidance is to be ended.
guidance_scalenumber The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.
real_cfg_scalenumber The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.
sigma_scheduleSigmas schedule for the denoising process.
negative_promptstring Negative prompt to steer the image generation away from unwanted features. By default, we will be using NAG for processing the negative prompt.
reference_startnumber The percentage of the total timesteps when the reference guidance is to bestarted.
controlnet_unionsarray The controlnet unions to use for the image generation. Only one controlnet is supported at the moment.
use_beta_schedulebooleanSpecifies whether beta sigmas ought to be used.
reference_strengthnumberStrength of reference_only generation. Only used if a reference image is provided.
num_inference_stepsintegerThe number of inference steps to perform.
reference_image_urlstringURL of Image for Reference-Only
enable_safety_checkerbooleanIf set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked, and images flagged as unsafe are returned as black images.

Output

FieldTypeDescription
seedinteger Seed of the generated Image. It will be the same value of the one passed in the input or the randomly generated that was used in case none was passed.
imagesarrayThe generated image files info.
promptstringThe prompt used for generating the image.
timingsobject
has_nsfw_conceptsarrayWhether the generated images contain NSFW concepts.