Flux Pro Erase

Name: Flux Pro Erase
Author: BFL

bfl/flux-pro/1.0/erase

Flux Pro 1.0 Erase by BFL - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortlessly.

Use in agent Get API key

Base price: $0.03USD / run
Execution: async
Model type: image
Input fields: 4

Try the model

Playground

Open playground

Input

Image URL or upload(string)

Upload

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

The URL of the input image to erase content from.

This field is required.

Image URL or upload(string)

Upload

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

The URL of a black/white mask image where white (255) marks pixels to erase and black (0) marks pixels to keep. Needs to match the dimensions of the input image.

Output Format(string)

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

Dilate Pixels(integer)

0100

Number of pixels to expand the mask edges by. Higher values produce cleaner erase results around the masked region. Range: 0 to 100.

OutputReady

Your output will appear here

Complete the inputs, then click Run.

Specifications

Pricing

Base price: $0.03 / run

Context & modalities

Input: Schema-defined
Output: image

Capabilities

Chat: Not supported
Vision: Not supported
Reasoning: Not supported
Structured output: Not supported
Function calling: Not supported
Audio input: Not supported

Access

Provider: BFL
Model ID: bfl/flux-pro/1.0/erase
Execution: async
API: Unified Run API
Endpoint: /v1/run

API README

Flux Pro Erase

Flux Pro Erase is a image generation and editing workflow in the FLUX family. Flux Pro 1.0 Erase by BFL - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortlessly. 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 clean object removal and background recovery. 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

Object removal. Eliminates the masked subject or region identified in a supplied image.
Context-aware fill. Reconstructs the revealed background so it agrees with surrounding texture, perspective, and lighting.
Mask-directed precision. Confines removal to the intended region while preserving unrelated content.
Natural boundary recovery. Blends the regenerated area into neighboring pixels without leaving a conspicuous cutout.

Pricing

Configuration	Billing unit	Price
Base generation	Per request	$0.03

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.

{
  "image": "https://example.com/reference.png",
  "mask": "https://example.com/reference.png",
  "dilate_pixels": 10,
  "output_format": "jpeg"
}

Technical Specs

Spec	Value
Model ID	`bfl/flux-pro/1.0/erase`
Input fields	`mask` (string)<br>`image` (string)<br>`dilate_pixels` (integer; 0–100)<br>`output_format` (string; `jpeg`, `png`)
Required input	`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

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API

Unified Run API endpoint

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

Model ID

bfl/flux-pro/1.0/erase

# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/run" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "bfl/flux-pro/1.0/erase",
  "mask": "https://static.sandbase.ai/examples/bfl/flux-pro/1.0/erase/input_mask_1.jpeg",
  "image": "https://static.sandbase.ai/examples/bfl/flux-pro/1.0/erase/input_image_0.jpeg",
  "dilate_pixels": 10,
  "output_format": "jpeg"
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All language models

Model	Context	Input / 1M	Output / 1M	Released
Flux Pro EraseThis model `BFL`	—	—	—	May 21, 2026
FLUX Virtual Try-On `BFL`	—	—	—	May 28, 2026
Flux 2 Pro `BFL`	—	—	—	May 14, 2026
FLUX.2 [klein] 9B LoRA `BFL`	—	—	—	Mar 17, 2026
FLUX.2 [klein] 9B LoRA `BFL`	—	—	—	Mar 17, 2026
FLUX.2 [klein] 4B LoRA `BFL`	—	—	—	Mar 17, 2026