BFL modelsimage generation api

bfl/flux-general/rf-inversion

Name: FLUX.1 [dev] with Controlnets and Loras
Author: BFL

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

Input

Prompt(string)

The prompt to edit the image with

Image URL or upload(string)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum

URL of image to be edited

This field is required.

Output Format(string)

The format of the generated image. Allowed values: jpeg, png.

Sigma Schedule(string)

Sigmas schedule for the denoising process.

Control Loras(array)

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.

Use Beta Schedule(boolean)

Specifies whether beta sigmas ought to be used.

Image URL or upload(string)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum

URL of Image for Reference-Only

Reverse Guidance End(integer)

Timestep to stop guidance during reverse process.

NAG scale(number)

The scale for NAG. Higher values will result in a image that is more distant to the negative prompt. Maximum: 10.

Controller Guidance Forward(number)

0.013

The controller guidance (gamma) used in the creation of structured noise. Range: 0.01 to 3.

Proportion of steps to apply NAG(number)

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.

Reference Strength(number)

-33

Strength of reference_only generation. Only used if a reference image is provided. Range: -3 to 3.

NAG Tau(number)

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.

Reference Start(number)

The percentage of the total timesteps when the reference guidance is to bestarted. Range: 0 to 1.

Reverse Guidance Start(integer)

Timestep to start guidance during reverse process.

Reference End(number)

The percentage of the total timesteps when the reference guidance is to be ended. Range: 0 to 1.

Max Shift(number)

0.015

Max shift for the scheduled timesteps Range: 0.01 to 5.

Reverse Guidance Schedule(string)

Scheduler for applying reverse guidance. Allowed values: constant, linear_increase, linear_decrease.

Base Shift(number)

0.015

Base shift for the scheduled timesteps Range: 0.01 to 5.

NAG alpha(number)

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.

Fill Image(string)

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

Easycontrols(array)

EasyControl Inputs to use for image generation.

Controller Guidance Reverse(number)

0.013

The controller guidance (eta) used in the denoising process.Using values closer to 1 will result in an image closer to input. Range: 0.01 to 3.

Aspect Ratio(string)

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.

Seed(integer)

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

Loras(array)

Enter a JSON array.

Guidance Scale(number)

020

Range: 0 to 20.

Num Inference Steps(integer)

150

Range: 1 to 50.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDbfl/flux-general/rf-inversion

Input Schema

28 parameters · 2 required · 26 optional

Parameter	Type	Required	Description
`image`	string	Required	URL of image to be edited
`prompt`	string	Required	The prompt to edit the image with
`seed`	integer	Optional	The same seed and the same prompt given to the same version of the model will output the same image every time.
`loras`	array	Optional	Default: []
`nag_end`	number	Optional	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. · Max: 1 · Default: 0.25
`nag_tau`	number	Optional	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
`max_shift`	number	Optional	Max shift for the scheduled timesteps · Min: 0.01 · Max: 5 · Default: 1.15
`nag_alpha`	number	Optional	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. · Max: 1 · Default: 0.25
`nag_scale`	number	Optional	The scale for NAG. Higher values will result in a image that is more distant to the negative prompt. · Max: 10 · Default: 3
`base_shift`	number	Optional	Base shift for the scheduled timesteps · Min: 0.01 · Max: 5 · Default: 0.5
`fill_image`	string	Optional	Use an image input to influence the generation. Can be used to fill images in masked areas.
`aspect_ratio`	string	Optional	The aspect ratio of the generated image. · Options: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 21:916:93:24:35:41:14:53:42:39:16
`easycontrols`	object[]	Optional	EasyControl Inputs to use for image generation. · Default: []
`control_loras`	object[]	Optional	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: []
`output_format`	string	Optional	The format of the generated image. · Options: jpeg, png · Default: "png" jpegpng
`reference_end`	number	Optional	The percentage of the total timesteps when the reference guidance is to be ended. · Min: 0 · Max: 1 · Default: 1
`guidance_scale`	number	Optional	Min: 0 · Max: 20 · Default: 3.5
`sigma_schedule`	string	Optional	Sigmas schedule for the denoising process.
`reference_start`	number	Optional	The percentage of the total timesteps when the reference guidance is to bestarted. · Min: 0 · Max: 1 · Default: 0
`use_beta_schedule`	boolean	Optional	Specifies whether beta sigmas ought to be used. · Default: false
`reference_strength`	number	Optional	Strength of reference_only generation. Only used if a reference image is provided. · Min: -3 · Max: 3 · Default: 0.65
`num_inference_steps`	integer	Optional	Min: 1 · Max: 50 · Default: 28
`reference_image_url`	string	Optional	URL of Image for Reference-Only
`reverse_guidance_end`	integer	Optional	Timestep to stop guidance during reverse process. · Default: 8
`reverse_guidance_start`	integer	Optional	Timestep to start guidance during reverse process. · Default: 0
`reverse_guidance_schedule`	string	Optional	Scheduler for applying reverse guidance. · Options: constant, linear_increase, linear_decrease · Default: "constant" constantlinear_increaselinear_decrease
`controller_guidance_forward`	number	Optional	The controller guidance (gamma) used in the creation of structured noise. · Min: 0.01 · Max: 3 · Default: 0.6
`controller_guidance_reverse`	number	Optional	The controller guidance (eta) used in the denoising process.Using values closer to 1 will result in an image closer to input. · Min: 0.01 · Max: 3 · Default: 0.75

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "bfl/flux-general/rf-inversion",
  "image": "https://static.sandbase.ai/examples/bfl/flux-general/rf-inversion/input_image_0.png",
  "loras": [],
  "prompt": "Wearing glasses",
  "nag_end": 0.25,
  "nag_tau": 2.5,
  "max_shift": 1.15,
  "nag_alpha": 0.25,
  "nag_scale": 3,
  "base_shift": 0.5,
  "easycontrols": [],
  "control_loras": [],
  "output_format": "png",
  "reference_end": 1,
  "guidance_scale": 3.5,
  "reference_start": 0,
  "use_beta_schedule": false,
  "reference_strength": 0.65,
  "num_inference_steps": 28,
  "reverse_guidance_end": 8,
  "reverse_guidance_start": 0,
  "reverse_guidance_schedule": "constant",
  "controller_guidance_forward": 0.6,
  "controller_guidance_reverse": 0.75
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to FLUX.1 [dev] with Controlnets and Loras

API README

FLUX.1 [dev] with Controlnets and Loras

FLUX.1 [dev] with Controlnets and Loras is a image generation and editing workflow in the FLUX family. Flux General Rf Inversion is BFL's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion. It is designed to translate deliberate creative direction and supplied reference material into a coherent production asset, with attention to subject identity, composition, visual detail, and the specific transformation implied by this exact route.

Use this route when the project needs a controlled visual generation or revision. Describe the intended result, what must remain recognizable, and the required composition, lighting, materials, atmosphere, and finish; keep technical delivery choices in the schema fields below.

Highlights

Reversible image representation. Maps a source image into a model-compatible representation for controlled reconstruction and editing.
Source-faithful recovery. Retains recognizable composition and visual detail before applying the requested transformation.
Prompt-guided modification. Uses written direction to change style, background, objects, or atmosphere from the inverted source.
Controlled variation. Supports edits that remain more tightly connected to the original than unconstrained regeneration.

Pricing

Configuration	Billing unit	Price
Base generation	Per request	$0.00125

When to Use

✅ Good fit	❌ Consider alternatives
The project needs this exact FLUX capability	The intended task belongs to a different media workflow
Required source and control media are available	Necessary assets or usage rights are unavailable
Creative direction can state change and preservation goals	Output must be deterministic at pixel or frame level
Supported dimensions and formats match final delivery	Placement requires unsupported specifications
An asynchronous generated result fits production	A live frame-synchronous response is mandatory

Prompt Guide

Lead with the main subject and action, then specify composition, context, lighting, materials, style, typography, and atmosphere. For editing, identify each source and clearly separate the requested transformation from the subjects, regions, geometry, or identity that must remain unchanged.

{
  "prompt": "A cinematic, precisely composed result with a clear subject, controlled camera or viewpoint, realistic lighting, exact materials, and intentional atmosphere",
  "image": "https://example.com/reference.png",
  "seed": 1,
  "loras": [],
  "nag_end": 0.25
}

Technical Specs

Spec	Value
Model ID	`bfl/flux-general/rf-inversion`
Input fields	`seed` (integer)<br>`image` (string)<br>`loras` (array)<br>`prompt` (string)<br>`nag_end` (number; …–1)<br>`nag_tau` (number)<br>`max_shift` (number; 0.01–5)<br>`nag_alpha` (number; …–1)<br>`nag_scale` (number; …–10)<br>`base_shift` (number; 0.01–5)<br>`fill_image` (string)<br>`aspect_ratio` (string; `21:9`, `16:9`, `3:2`, `4:3`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16`)<br>`easycontrols` (array)<br>`control_loras` (array)<br>`output_format` (string; `jpeg`, `png`)<br>`reference_end` (number; 0–1)<br>`guidance_scale` (number; 0–20)<br>`sigma_schedule` (string)<br>`reference_start` (number; 0–1)<br>`use_beta_schedule` (boolean)<br>`reference_strength` (number; -3–3)<br>`num_inference_steps` (integer; 1–50)<br>`reference_image_url` (string)<br>`reverse_guidance_end` (integer)<br>`reverse_guidance_start` (integer)<br>`reverse_guidance_schedule` (string; `constant`, `linear_increase`, `linear_decrease`)<br>`controller_guidance_forward` (number; 0.01–3)<br>`controller_guidance_reverse` (number; 0.01–3)
Required input	`prompt`, `image`
Output fields	`url`, `content_type`
Execution	Asynchronous job

Related Models

bfl/flux-1/dev/edit
bfl/flux-1/dev/image-to-image
bfl/flux-1/dev