bfl/flux-lora-fill
Flux Lora Fill by BFL - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortlessly.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runbfl/flux-lora-fillInput Schema
12 parameters · 2 required · 10 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
image | string | Required | URL of image to use for fill operation |
prompt | string | Required | The prompt to generate an image from. · Default: "" |
mask | string | Optional | The mask to area to Inpaint in. |
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 | object[] | Optional | The LoRAs to use for the image generation. You can use any number of LoRAs and they will be merged together to generate the final image. · Default: [] |
fill_image | string | Optional | Use an image fill input to fill in particular images into the masked area. |
paste_back | boolean | Optional | Specifies whether to paste-back the original image onto to the non-inpainted areas of the output · Default: true |
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 |
output_format | string | Optional | The format of the generated image. · 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: 28 · Max: 35 · Default: 30 |
resize_to_original | boolean | Optional | Resizes the image back to the original size. Use when you wish to preserve the exact image size as the originally provided image. · Default: false |
num_inference_steps | integer | Optional | The number of inference steps to perform. · Min: 1 · 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, ortimeout - Retrieve — Read
outputsfrom 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-lora-fill",
"mask": "https://static.sandbase.ai/examples/bfl/flux-lora-fill/input_mask_1.jpeg",
"image": "https://static.sandbase.ai/examples/bfl/flux-lora-fill/input_image_0.jpeg",
"loras": [],
"prompt": "A knight in shining armour holding a greatshield with 'FAL' on it",
"paste_back": true,
"output_format": "jpeg",
"guidance_scale": 30,
"resize_to_original": false,
"num_inference_steps": 28
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Flux Lora Fill
Flux Lora Fill belongs at the customized repair and canvas completion stage of a visual workflow. Rather than treating the model as an isolated demonstration, teams can place it inside briefing, review, selection, and handoff practices where the adapted visual language remains available when selected content is replaced or when an image must grow beyond its original crop. This positioning clarifies why the model earns a place in a real creative pipeline and what kind of decision it helps people make.
A practical use of Flux Lora Fill is brand-consistent cleanup, character corrections, styled background extension, and production fixes that should not introduce a generic-looking patch. Begin by agreeing on the creative objective and review criteria, prepare only the source material needed for that objective, and compare results against audience, brand, editorial, and production needs. Technical request choices remain documented below so the prose can stay focused on planning and creative value.
Highlights
Context-aware reconstruction. Rebuilds masked content with lighting, perspective, texture, and scale matched to its surroundings.
Semantic replacement. Follows written direction for new objects or materials instead of simply cloning nearby pixels.
Natural boundary blending. Integrates regenerated content across the mask edge without a pasted-on appearance.
Unmasked-area preservation. Concentrates generative change on the intended region while retaining the broader composition. FLUX LoRA Fill applies a learned subject or style specifically while reconstructing masked still-image content.
Pricing
| Configuration | Billing unit | Price |
|---|---|---|
| Base generation | Per request | $0.035 |
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/start-frame.png",
"loras": [],
"mask": "https://example.com/reference.png",
"prompt": "",
"seed": 1
}
Technical Specs
| Spec | Value |
|---|---|
| Model ID | bfl/flux-lora-fill |
| Input fields | mask (string)<br>seed (integer)<br>image (string)<br>loras (array)<br>prompt (string)<br>fill_image (string)<br>paste_back (boolean)<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>output_format (string; jpeg, png)<br>guidance_scale (number; 28–35)<br>resize_to_original (boolean)<br>num_inference_steps (integer; 1–50) |
| Required input | prompt, image |
| Output fields | url, content_type |
| Execution | Asynchronous job |
Related Models
bfl/flux-1.1/pro— Compare this concrete local family route.bfl/flux-1.1/pro-ultra— Compare this concrete local family route.bfl/flux-1.1/ultra/redux— Compare this concrete local family route.