BFL modelsimage generation api

bfl/flux-2/kontext/dev

Name: FLUX.1 Kontext [dev]
Author: BFL

Flux 2 Kontext Dev by BFL - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortlessly.

Input

Prompt(string)

The prompt to edit the image.

Image URL or upload(string)

Upload

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

The URL of the image to edit. Max width: 14142px, Max height: 14142px, Timeout: 20s

This field is required.

Guidance scale (CFG)(number)

120

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: 1 to 20.

Num Inference Steps(integer)

1050

The number of inference steps to perform. Range: 10 to 50.

Output Format(string)

Output format Allowed values: jpeg, png.

Resolution Mode(string)

Determines how the output resolution is set for image editing. - `auto`: The model selects an optimal resolution from a predefined set that best matches the input image's aspect ratio. This is the recommended setting for most use cases as it's what the model was trained on. - `match_input`: The model will attempt to use the same resolution as the input image. The resolution will be adjusted to be compatible with the model's requirements (e.g. dimensions must be multiples of 16 and within supported limits). Apart from these, a few aspect ratios are also supported. Allowed values: auto, match_input, 1:1, 16:9, 21:9, 3:2, 2:3, 4:5, 5:4, 3:4, 4:3, 9:16, 9:21.

Seed(integer)

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

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-2/kontext/dev

Input Schema

7 parameters · 2 required · 5 optional

Parameter	Type	Required	Description
`image`	string	Required	The URL of the image to edit. Max width: 14142px, Max height: 14142px, Timeout: 20s
`prompt`	string	Required	The prompt to edit the image.
`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.
`output_format`	string	Optional	Output format · Options: jpeg, png · Default: "jpeg" jpegpng
`guidance_scale`	number	Optional	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. · Min: 1 · Max: 20 · Default: 2.5
`resolution_mode`	string	Optional	Determines how the output resolution is set for image editing. - `auto`: The model selects an optimal resolution from a predefined set that best matches the input image's aspect ratio. This is the recommended setting for most use cases as it's what the model was trained on. - `match_input`: The model will attempt to use the same resolution as the input image. The resolution will be adjusted to be compatible with the model's requirements (e.g. dimensions must be multiples of 16 and within supported limits). Apart from these, a few aspect ratios are also supported. · Options: auto, match_input, 1:1, 16:9, 21:9, 3:2, 2:3, 4:5, 5:4, 3:4, 4:3, 9:16, 9:21 · Default: "match_input" automatch_input1:116:921:93:22:34:55:43:44:39:169:21
`num_inference_steps`	integer	Optional	The number of inference steps to perform. · Min: 10 · Max: 50 · Default: 28

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-2/kontext/dev",
  "image": "https://static.sandbase.ai/examples/bfl/flux-2/kontext/dev/input_image_0.webp",
  "prompt": "Change the setting to a day time, add a lot of people walking the sidewalk while maintaining the same style of the painting",
  "output_format": "jpeg",
  "guidance_scale": 2.5,
  "resolution_mode": "match_input",
  "num_inference_steps": 28
}'

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

← Back to FLUX.1 Kontext [dev]

API README

FLUX.1 Kontext [dev]

FLUX.1 Kontext [dev] edits and enhances photos from natural-language instructions. A required image supplies the visual foundation and a required prompt communicates the revision, creating a direct path from an existing asset to an updated one.

Guidance can be adjusted from 1 to 20 and inference steps from 10 to 50. The model also offers resolution modes including automatic, input-matched, square, landscape, and portrait choices, plus JPEG or PNG export and seed control.

Highlights

Photo-first revision. Begin with a required image so the edit remains connected to an existing asset.

Written creative direction. Use a required prompt to describe the change or enhancement in natural language.

Broad refinement controls. Tune guidance from 1–20 and inference steps from 10–50 for the intended generation pass.

Resolution and export choices. Select an automatic, input-matched, or fixed resolution mode, then export JPEG or PNG with an optional seed.

Pricing

Billing unit	Price
Per request	$0.00125

When to Use

✅ Good fit	❌ Consider alternatives
The model's named workflow matches the source material and intended output	A different input modality or model route is required
A managed asynchronous result is suitable for the production pipeline	A synchronous, interactive editor is essential
The documented controls cover the required duration, framing, or format	The project needs controls outside this endpoint's schema
Creative iteration benefits from a repeatable request structure	Exact deterministic pixels, frames, geometry, or samples are mandatory
A finished downloadable media asset is the desired deliverable	Editable source layers or a native project file are required

Prompt Guide

For image-conditioned generation, state the intended result first, then add the subject or source treatment, progression, style, and delivery constraints. Keep one creative variable per phrase, use the documented field names for controls, and change one setting at a time when comparing results.

{
  "image": "https://example.com/start-frame.png",
  "output_format": "jpeg",
  "prompt": "Change the setting to a day time, add a lot of people walking the sidewalk while maintaining the same style of the painting"
}

Technical Specs

Spec	Value
Model ID	`bfl/flux-2/kontext/dev`
Inputs	guidance_scale, image, num_inference_steps, output_format, prompt, resolution_mode, seed
Required inputs	prompt, image
Output fields	content_type, url
Execution	Async (submit, then poll for result)
Output Format	jpeg / png

Related Models

bfl/flux-2/kontext/max/multi — Compare this concrete local family route.
bfl/flux-2/kontext/max/text-to-image — Compare this concrete local family route.
bfl/flux-2/kontext/pro/multi — Compare this concrete local family route.