Flux 2 Pro

bfl/flux-2-pro/outpaint

Flux 2 Pro Outpaint is BFL's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.

Base price
$0.03USD / run
Execution
async
Model type
image
Input fields
7

Try the model

Playground

Open playground
Input

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

The image URL to expand using outpainting.
The format of the generated image. Allowed values: jpeg, png.
Whether to automatically crop the reference image when the expanded canvas does not fully contain it.
02048
Pixels to expand at the bottom of the image. Range: 0 to 2048.
02048
Pixels to expand on the right of the image. Range: 0 to 2048.
02048
Pixels to expand on the left of the image. Range: 0 to 2048.
02048
Pixels to expand at the top of the image. Range: 0 to 2048.
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-2-pro/outpaint
Execution
async
API
Unified Run API
Endpoint
/v1/run

API README

Flux 2 Pro

Flux 2 Pro extends a source image beyond its original boundaries with FLUX.2 Pro. The model uses visible context to infer continuing architecture, landscape, objects, perspective, illumination, and texture, creating a wider or taller composition that feels like part of the same captured scene rather than a separately pasted border.

Use it to adapt an approved asset to a new aspect ratio, reveal additional environment, add copy space, or repair an overly tight crop. Describe what should plausibly exist outside each edge and what must remain unchanged inside the source; consistent horizon, camera perspective, light direction, and material continuity are more important than adding unrelated detail.

Highlights

  • Contextual canvas extension. Generates plausible scene content outside the source image boundaries.
  • Perspective continuation. Extends geometry, horizon, scale, and camera relationships into the added area.
  • Lighting and texture continuity. Matches illumination, color, material, and detail across the original edge.
  • Composition-aware expansion. Creates useful wider or taller framing while preserving the source’s main subject and visual intent.

Pricing

ConfigurationBilling unitPrice
Base generationPer request$0.03

When to Use

✅ Good fit❌ Consider alternatives
The project needs this exact generation or editing routeThe intended task belongs to video, audio, or 3D media
Available references match every required local fieldRequired source assets or rights are unavailable
The brief can specify composition, color, and finishOutput must be deterministic at pixel level
Supported dimensions and formats fit final placementDelivery requires unsupported canvas specifications
An asynchronous generated image fits productionA live frame-synchronous response is mandatory

Prompt Guide

Write a complete visual brief: identify the subject and references, define composition and viewpoint, describe lighting, palette, materials, typography, and finish, then list exact preservation constraints. FLUX.2 Klein does not rely on prompt upsampling, so use clear descriptive sentences rather than sparse keywords.

{
  "image": "https://example.com/reference.jpg",
  "auto_crop": false,
  "expand_top": 0,
  "expand_left": 0
}

Technical Specs

SpecValue
Model IDbfl/flux-2-pro/outpaint
Input fieldsimage (string)<br>auto_crop (boolean)<br>expand_top (integer; 0–2048)<br>expand_left (integer; 0–2048)<br>expand_right (integer; 0–2048)<br>expand_bottom (integer; 0–2048)<br>output_format (string; jpeg, png)
Required inputimage
Output fieldsurl, content_type
ExecutionAsynchronous job

Related Models

  • bfl/flux-2-lora-gallery/apartment-staging
  • bfl/flux-2-lora-gallery/face-to-full-portrait
  • bfl/flux-2-lora-gallery/multiple-angles

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-2-pro/outpaint
# 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 $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "bfl/flux-2-pro/outpaint",
  "image": "https://static.sandbase.ai/examples/bfl/flux-2-pro/outpaint/input_image_0.png",
  "auto_crop": false,
  "expand_top": 0,
  "expand_left": 200,
  "expand_right": 200,
  "expand_bottom": 200,
  "output_format": "jpeg"
}
SANDBASE_JSON
)
run_id=$(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
ModelContextInput / 1MOutput / 1MReleased
Flux 2 ProThis model
BFL
———May 14, 2026
BFL———May 28, 2026
BFL———May 21, 2026
BFL———Mar 17, 2026
BFL———Mar 17, 2026
BFL———Mar 17, 2026