bfl/flux-general/inpainting
Flux General Inpainting is BFL's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.
Input
The prompt to generate an image from.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
URL of image to use for inpainting. or img2img
This field is required.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
The mask to area to Inpaint in.
020
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: 0 to 20.
150
The number of inference steps to perform. Range: 1 to 50.
0.011
The strength to use for inpainting/image-to-image. Only used if the image_url is provided. 1.0 is completely remakes the image while 0.0 preserves the original. Range: 0.01 to 1.
The format of the generated image. Allowed values: jpeg, png.
EasyControl Inputs to use for image generation.
Sigmas schedule for the denoising process.
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.
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.
IP-Adapter to use for image generation.
Specifies whether beta sigmas ought to be used.
01
The percentage of the total timesteps when the reference guidance is to be ended. Range: 0 to 1.
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.
The controlnet unions to use for the image generation. Only one controlnet is supported at the moment.
The controlnets to use for the image generation. Only one controlnet is supported at the moment.
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.
01
The percentage of the total timesteps when the reference guidance is to bestarted. Range: 0 to 1.
-33
Strength of reference_only generation. Only used if a reference image is provided. Range: -3 to 3.
0.015
Base shift for the scheduled timesteps Range: 0.01 to 5.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
URL of Image for Reference-Only
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.
05
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: 0 to 5.
0.015
Max shift for the scheduled timesteps Range: 0.01 to 5.
The scale for NAG. Higher values will result in a image that is more distant
to the negative prompt. Maximum: 10.
Uses CFG-zero init sampling as in https://arxiv.org/abs/2503.18886.
Use an image input to influence the generation. Can be used to fill images in masked areas.
Scheduler for the denoising process. Allowed values: euler, dpmpp_2m.
Uses classical CFG as in SD1.5, SDXL, etc. Increases generation times and price when set to be true.
If using XLabs IP-Adapter v1, this will be turned on!.
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.
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.
POST
https://api.sandbase.ai/v1/runModel ID
bfl/flux-general/inpainting01
Input Schema
32 parameters · 2 required · 30 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
image | string | Required | URL of image to use for inpainting. or img2img |
prompt | string | Required | The prompt to generate an image from. |
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: [] |
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 |
strength | number | Optional | The strength to use for inpainting/image-to-image. Only used if the image_url is provided. 1.0 is completely remakes the image while 0.0 preserves the original. · Min: 0.01 · Max: 1 · Default: 0.85 |
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 |
scheduler | string | Optional | Scheduler for the denoising process. · Options: euler, dpmpp_2m · Default: "euler" eulerdpmpp_2m |
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. |
controlnets | object[] | Optional | The controlnets to use for the image generation. Only one controlnet is supported at the moment. · Default: [] |
ip_adapters | object[] | Optional | IP-Adapter to use for image generation. · Default: [] |
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: [] |
use_cfg_zero | boolean | Optional | Uses CFG-zero init sampling as in https://arxiv.org/abs/2503.18886. · Default: false |
use_real_cfg | boolean | Optional | Uses classical CFG as in SD1.5, SDXL, etc. Increases generation times and price when set to be true. If using XLabs IP-Adapter v1, this will be turned on!. · Default: false |
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 | 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: 0 · Max: 20 · Default: 3.5 |
real_cfg_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: 0 · Max: 5 · 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 |
controlnet_unions | object[] | Optional | The controlnet unions to use for the image generation. Only one controlnet is supported at the moment. · Default: [] |
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 | The number of inference steps to perform. · Min: 1 · Max: 50 · Default: 28 |
reference_image_url | string | Optional | URL of Image for Reference-Only |
02
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
03
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/inpainting",
"mask": "https://static.sandbase.ai/examples/bfl/flux-general/inpainting/input_mask_1.png",
"image": "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png",
"loras": [],
"prompt": "A photo of a lion sitting on a stone bench",
"nag_end": 0.25,
"nag_tau": 2.5,
"strength": 0.85,
"max_shift": 1.15,
"nag_alpha": 0.25,
"nag_scale": 3,
"scheduler": "euler",
"base_shift": 0.5,
"controlnets": [],
"ip_adapters": [],
"easycontrols": [],
"use_cfg_zero": false,
"use_real_cfg": false,
"control_loras": [],
"output_format": "png",
"reference_end": 1,
"guidance_scale": 3.5,
"real_cfg_scale": 3.5,
"reference_start": 0,
"controlnet_unions": [],
"use_beta_schedule": false,
"reference_strength": 0.65,
"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 General Inpainting
Flux General Inpainting belongs at the localized repair and replacement in a general workbench 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 team can keep most of an asset approved while reopening only the area that blocks delivery. 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 General Inpainting is object cleanup, missing-content repair, wardrobe or prop replacement, and focused revisions that should not disturb the rest of the composition. 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. The General configuration exposes broad FLUX synthesis behavior for workflows that need explicit control over the selected transformation method.
Pricing
| Configuration | Billing unit | Price |
|---|---|---|
| Base generation | Per request | $0.075 |
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": "A cinematic, precisely composed result with a clear subject, controlled camera or viewpoint, realistic lighting, exact materials, and intentional atmosphere",
"seed": 1
}
Technical Specs
| Spec | Value |
|---|---|
| Model ID | bfl/flux-general/inpainting |
| Input fields | mask (string)<br>seed (integer)<br>image (string)<br>loras (array)<br>prompt (string)<br>nag_end (number; …–1)<br>nag_tau (number)<br>strength (number; 0.01–1)<br>max_shift (number; 0.01–5)<br>nag_alpha (number; …–1)<br>nag_scale (number; …–10)<br>scheduler (string; euler, dpmpp_2m)<br>base_shift (number; 0.01–5)<br>fill_image (string)<br>controlnets (array)<br>ip_adapters (array)<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>use_cfg_zero (boolean)<br>use_real_cfg (boolean)<br>control_loras (array)<br>output_format (string; jpeg, png)<br>reference_end (number; 0–1)<br>guidance_scale (number; 0–20)<br>real_cfg_scale (number; 0–5)<br>sigma_schedule (string)<br>reference_start (number; 0–1)<br>controlnet_unions (array)<br>use_beta_schedule (boolean)<br>reference_strength (number; -3–3)<br>num_inference_steps (integer; 1–50)<br>reference_image_url (string) |
| Required input | prompt, image |
| Output fields | url, content_type |
| Execution | Asynchronous job |
Related Models
bfl/flux-general— Compare this concrete local family route.bfl/flux-general/differential-diffusion— Compare this concrete local family route.bfl/flux-general/image-to-image— Compare this concrete local family route.