Start building
SandBase

Appearance

FLUX.1 [dev] with Controlnets and Loras

POST/v1/run

Flux General Differential Diffusion 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/differential-diffusion.

Default: bfl/flux-general/differential-diffusion

stringpromptrequired

The prompt to generate an image from.

stringimagerequired

URL of image to use as initial image.

Optional<number>strength

The strength to use for differential diffusion. 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<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>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.

Maximum: 1

Default: 0.25

Optional<string>change_map_image_url

URL of change map.

Optional<boolean>use_beta_schedule

Specifies whether beta sigmas ought to be used.

Default: false

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>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>max_shift

Max shift for the scheduled timesteps

Range: 0.01 to 5

Default: 1.15

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.

Maximum: 1

Default: 0.25

Optional<number>base_shift

Base shift for the scheduled timesteps

Range: 0.01 to 5

Default: 0.5

Optional<number>nag_scale

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

Maximum: 10

Default: 3

Optional<string>reference_image_url

URL of Image for Reference-Only

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<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>fill_image

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

Optional<string>sigma_schedule

Sigmas schedule for the denoising process.

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>>ip_adapters

IP-Adapter to use for image generation.

Default:

Optional<array<object>>easycontrols

EasyControl Inputs to use for image generation.

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<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.

Optional<integer>num_inference_steps

Number of denoising or inference steps to run when supported.

Range: 1 to 50

Default: 28

Optional<number>guidance_scale

Request parameter supported by this model.

Range: 0 to 20

Default: 3.5

Optional<array>loras

LoRA adapters applied to the generation. At most three items are accepted.

Default:

Response Schema

The submit endpoint returns a run response. If its status is pending or running, poll GET /v1/run/{id} with the returned opaque ID until it reaches a terminal state.

stringidrequired

Opaque SandBase run identifier. Use it exactly as returned; no prefix is guaranteed.

stringstatusrequired

Current public run status.

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

Optional<string>model

Public SandBase model name used for this run.

Optional<array<object>>outputs

Present only for completed runs. Each object is capability-specific; inspect the selected model schema for its fields.

Optional<object>error

Present only for failed or timeout runs. Contains a public error type and sanitized message.

Optional<string>error.type

Stable public error category.

Optional<string>error.message

Sanitized error message safe to show to clients.

Optional<object>usage

Usage details when available.

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