Appearance

FLUX.1 [dev] with Controlnets and Loras

POST/v1/run

Flux General Inpainting is BFL's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to bfl/flux-general/inpainting.

Default: bfl/flux-general/inpainting

stringpromptrequired

The prompt to generate an image from.

stringimagerequired

URL of image to use for inpainting. or img2img

Optional<string>mask

The mask to area to Inpaint in.

Optional<number>guidance_scale

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.

Range: 0 to 20

Default: 3.5

Optional<integer>num_inference_steps

The number of inference steps to perform.

Range: 1 to 50

Default: 28

Optional<number>strength

The 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.

Range: 0.01 to 1

Default: 0.85

Optional<string>output_format

The format of the generated image.

Allowed values: jpeg, png

Default: png

Optional<array<object>>easycontrols

EasyControl Inputs to use for image generation.

Default:

Optional<string>sigma_schedule

Sigmas schedule for the denoising process.

Optional<number>nag_tau

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.

Default: 2.5

Optional<number>nag_alpha

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 where lower values will result in considering the positive prompt guidance more.

Range: −∞ to 1

Default: 0.25

Optional<array<object>>ip_adapters

IP-Adapter to use for image generation.

Default:

Optional<boolean>use_beta_schedule

Specifies whether beta sigmas ought to be used.

Default: false

Optional<number>reference_end

The percentage of the total timesteps when the reference guidance is to be ended.

Range: 0 to 1

Default: 1

Optional<array<object>>control_loras

The LoRAs to use for the image generation which use a control image. You can use any number of LoRAs and they will be merged together to generate the final image.

Default:

Optional<array<object>>controlnet_unions

The controlnet unions to use for the image generation. Only one controlnet is supported at the moment.

Default:

Optional<array<object>>controlnets

The controlnets to use for the image generation. Only one controlnet is supported at the moment.

Default:

Optional<array<object>>loras

The LoRAs to use for the image generation. You can use any number of LoRAs and they will be merged together to generate the final image.

Default:

Optional<number>reference_start

The percentage of the total timesteps when the reference guidance is to bestarted.

Range: 0 to 1

Default: 0

Optional<number>reference_strength

Strength of reference_only generation. Only used if a reference image is provided.

Range: -3 to 3

Default: 0.65

Optional<number>base_shift

Base shift for the scheduled timesteps

Range: 0.01 to 5

Default: 0.5

Optional<string>reference_image_url

URL of Image for Reference-Only

Optional<number>nag_end

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.

Range: −∞ to 1

Default: 0.25

Optional<number>real_cfg_scale

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.

Range: 0 to 5

Default: 3.5

Optional<number>max_shift

Max shift for the scheduled timesteps

Range: 0.01 to 5

Default: 1.15

Optional<number>nag_scale

The scale for NAG. Higher values will result in a image that is more distant to the negative prompt.

Range: −∞ to 10

Default: 3

Optional<boolean>use_cfg_zero

Uses CFG-zero init sampling as in https://arxiv.org/abs/2503.18886.

Default: false

Optional<string>fill_image

Use an image input to influence the generation. Can be used to fill images in masked areas.

Optional<string>scheduler

Scheduler for the denoising process.

Allowed values: euler, dpmpp_2m

Default: euler

Optional<boolean>use_real_cfg

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!.

Default: false

Optional<string>aspect_ratio

The aspect ratio of the generated image.

Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16

Optional<integer>seed

The same seed and the same prompt given to the same version of the model will output the same image every time.

Response Schema

The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.

Optional<string>error

Error message if the task failed. Empty on success.

stringidrequired

Unique identifier for the generation task.

Optional<string>model

Model ID used for the prediction.

Optional<array>outputs

Array of generated content. Empty when status is not completed.

stringstatusrequired

Status of the task: pending, running, completed, failed, or timeout.

Allowed values: pending, running, completed, failed, timeout

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: image-to-image

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async