FLUX.1 [dev] with Controlnets and Loras | Image to Image

fal-ai/flux-general/inpainting

FLUX General Inpainting is a versatile endpoint that enables precise image editing and completion, supporting multiple AI extensions including LoRA, ControlNet, and IP-Adapter for enhanced control over inpainting results and sophisticated image modifications.

Inference

Commercial use

Schema

LLMs

Playground API Examples

1. Calling the API

2. Authentication

API Key

3. Queue

4. Files

5. Schema

About

FLUX.1 [dev], next generation text-to-image model.

1. Calling the API#

Install the client#

The client provides a convenient way to interact with the model API.

npm install --save @fal-ai/client

Migrate to @fal-ai/client

The @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Please check the migration guide for more information.

Setup your API Key#

Set FAL_KEY as an environment variable in your runtime.

export FAL_KEY="YOUR_API_KEY"

Submit a request#

The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/flux-general/inpainting", {
  input: {
    prompt: "A photo of a lion sitting on a stone bench",
    image_url: "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png",
    mask_url: "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

2. Authentication#

The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.

API Key#

In case your app is running in an environment where you cannot set environment variables, you can set the API Key manually as a client configuration.

import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

Protect your API Key

When running code on the client-side (e.g. in a browser, mobile app or GUI applications), make sure to not expose your FAL_KEY. Instead, use a server-side proxy to make requests to the API. For more information, check out our server-side integration guide.

3. Queue#

Long-running requests

For long-running requests, such as training jobs or models with slower inference times, it is recommended to check the Queue status and rely on Webhooks instead of blocking while waiting for the result.

Submit a request#

The client API provides a convenient way to submit requests to the model.

import { fal } from "@fal-ai/client";

const { request_id } = await fal.queue.submit("fal-ai/flux-general/inpainting", {
  input: {
    prompt: "A photo of a lion sitting on a stone bench",
    image_url: "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png",
    mask_url: "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"
  },
  webhookUrl: "https://optional.webhook.url/for/results",
});

Fetch request status#

You can fetch the status of a request to check if it is completed or still in progress.

import { fal } from "@fal-ai/client";

const status = await fal.queue.status("fal-ai/flux-general/inpainting", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
  logs: true,
});

Get the result#

Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.

import { fal } from "@fal-ai/client";

const result = await fal.queue.result("fal-ai/flux-general/inpainting", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);

4. Files#

Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.

Data URI (base64)#

You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.

Hosted files (URL)#

You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.

Uploading files#

We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.

import { fal } from "@fal-ai/client";

const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);

Auto uploads

The client will auto-upload the file for you if you pass a binary object (e.g. File, Data).

Read more about file handling in our file upload guide.

5. Schema#

Input#

prompt string* required

The prompt to generate an image from.

image_size ImageSize | Enum

The size of the generated image.

Possible enum values: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9

Note: For custom image sizes, you can pass the width and height as an object:

"image_size": {
  "width": 1280,
  "height": 720
}

num_inference_steps integer

The number of inference steps to perform. Default value: 28

seed integer

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

loras list<LoraWeight>

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.

control_loras list<ControlLoraWeight>

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.

controlnets list<ControlNet>

The controlnets to use for the image generation. Only one controlnet is supported at the moment.

controlnet_unions list<ControlNetUnion>

The controlnet unions to use for the image generation. Only one controlnet is supported at the moment.

ip_adapters list<IPAdapter>

IP-Adapter to use for image generation.

easycontrols list<EasyControlWeight>

EasyControl Inputs to use for image generation.

fill_image ImageFillInput

Use an image input to influence the generation. Can be used to fill images in masked areas.

guidance_scale float

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. Default value: 3.5

real_cfg_scale float

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. Default value: 3.5

use_real_cfg boolean

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!.

use_cfg_zero boolean

Uses CFG-zero init sampling as in https://arxiv.org/abs/2503.18886.

sync_mode boolean

If True, the media will be returned as a data URI and the output data won't be available in the request history.

num_images integer

The number of images to generate. This is always set to 1 for streaming output. Default value: 1

enable_safety_checker boolean

If set to true, the safety checker will be enabled. Default value: true

reference_image_url string

URL of Image for Reference-Only

reference_strength float

Strength of reference_only generation. Only used if a reference image is provided. Default value: 0.65

reference_start float

The percentage of the total timesteps when the reference guidance is to bestarted.

reference_end float

The percentage of the total timesteps when the reference guidance is to be ended. Default value: 1

base_shift float

Base shift for the scheduled timesteps Default value: 0.5

max_shift float

Max shift for the scheduled timesteps Default value: 1.15

output_format OutputFormatEnum

The format of the generated image. Default value: "png"

Possible enum values: jpeg, png

use_beta_schedule boolean

Specifies whether beta sigmas ought to be used.

sigma_schedule SigmaScheduleEnum

Sigmas schedule for the denoising process.

Possible enum values: sgm_uniform

scheduler SchedulerEnum

Scheduler for the denoising process. Default value: "euler"

Possible enum values: euler, dpmpp_2m

negative_prompt string

Negative prompt to steer the image generation away from unwanted features. By default, we will be using NAG for processing the negative prompt. Default value: ""

nag_scale float

The scale for NAG. Higher values will result in a image that is more distant to the negative prompt. Default value: 3

nag_tau float

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 value: 2.5

nag_alpha float

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. Default value: 0.25

nag_end float

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. Default value: 0.25

image_url string* required

URL of image to use for inpainting. or img2img

strength float

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. Default value: 0.85

mask_url string* required

The mask to area to Inpaint in.

{
  "prompt": "A photo of a lion sitting on a stone bench",
  "num_inference_steps": 28,
  "controlnets": [],
  "controlnet_unions": [],
  "ip_adapters": [],
  "easycontrols": [],
  "guidance_scale": 3.5,
  "real_cfg_scale": 3.5,
  "num_images": 1,
  "enable_safety_checker": true,
  "reference_strength": 0.65,
  "reference_end": 1,
  "base_shift": 0.5,
  "max_shift": 1.15,
  "output_format": "png",
  "scheduler": "euler",
  "nag_scale": 3,
  "nag_tau": 2.5,
  "nag_alpha": 0.25,
  "nag_end": 0.25,
  "image_url": "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png",
  "strength": 0.85,
  "mask_url": "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"
}

Output#

images list<Image>* required

The generated image files info.

timings Timings* required

seed integer* required

Seed of the generated Image. It will be the same value of the one passed in the input or the randomly generated that was used in case none was passed.

has_nsfw_concepts list<boolean>* required

Whether the generated images contain NSFW concepts.

prompt string* required

The prompt used for generating the image.

{
  "images": [
    {
      "url": "",
      "content_type": "image/jpeg"
    }
  ],
  "prompt": ""
}

Other types#

LoraWeight#

path string* required

URL or the path to the LoRA weights.

scale object | float

The scale of the LoRA weight. This is used to scale the LoRA weight before merging it with the base model. Providing a dictionary as {"layer_name":layer_scale} allows per-layer lora scale settings. Layers with no scale provided will have scale 1.0. Default value: 1

EasyControlWeight#

control_method_url string* required

URL to safetensor weights of control method to be applied. Can also be one of canny, depth, hedsketch, inpainting, pose, seg, subject, ghibli

scale float

Scale for the control method. Default value: 1

image_url string* required

URL of an image to use as a control

image_control_type ImageControlTypeEnum* required

Control type of the image. Must be one of spatial or subject.

Possible enum values: subject, spatial

Image#

url string* required

width integer* required

height integer* required

content_type string

Default value: "image/jpeg"

IPAdapter#

path string* required

Hugging Face path to the IP-Adapter

subfolder string

Subfolder in which the ip_adapter weights exist

weight_name string

Name of the safetensors file containing the ip-adapter weights

image_encoder_path string* required

Path to the Image Encoder for the IP-Adapter, for example 'openai/clip-vit-large-patch14'

image_encoder_subfolder string

Subfolder in which the image encoder weights exist.

image_encoder_weight_name string

Name of the image encoder.

image_url string* required

URL of Image for IP-Adapter conditioning.

mask_image_url string

URL of the mask for the control image.

mask_threshold float

Threshold for mask. Default value: 0.5

scale float* required

Scale for ip adapter.

ImageSize#

width integer

The width of the generated image. Default value: 512

height integer

The height of the generated image. Default value: 512

ControlNetUnion#

path string* required

URL or the path to the control net weights.

config_url string

optional URL to the controlnet config.json file.

variant string

The optional variant if a Hugging Face repo key is used.

controls list<ControlNetUnionInput>* required

The control images and modes to use for the control net.

ControlLoraWeight#

path string* required

URL or the path to the LoRA weights.

scale object | float

control_image_url string* required

URL of the image to be used as the control image.

preprocess PreprocessEnum

Type of preprocessing to apply to the input image. Default value: "None"

Possible enum values: canny, depth, None

ControlNet#

path string* required

URL or the path to the control net weights.

config_url string

optional URL to the controlnet config.json file.

variant string

The optional variant if a Hugging Face repo key is used.

control_image_url string* required

URL of the image to be used as the control image.

mask_image_url string

URL of the mask for the control image.

mask_threshold float

Threshold for mask. Default value: 0.5

conditioning_scale float

The scale of the control net weight. This is used to scale the control net weight before merging it with the base model. Default value: 1

start_percentage float

The percentage of the image to start applying the controlnet in terms of the total timesteps.

end_percentage float

The percentage of the image to end applying the controlnet in terms of the total timesteps. Default value: 1

Table of contents

1. Calling the API

2. Authentication

3. Queue

4. Files

5. Schema

About

1. Calling the API#

Install the client#

Migrate to @fal-ai/client

Setup your API Key#

Submit a request#

2. Authentication#

API Key#

Protect your API Key

3. Queue#

Long-running requests

Submit a request#

Fetch request status#

Get the result#

4. Files#

Data URI (base64)#

Hosted files (URL)#

Uploading files#

Auto uploads

5. Schema#

Input#

Output#

Other types#

LoraWeight#

EasyControlWeight#

Image#

IPAdapter#

ImageSize#

ControlNetUnion#

ControlLoraWeight#

ControlNet#

Related Models

FLUX.1 [dev] with Controlnets and Loras Image to Image

Table of contents

1. Calling the API

2. Authentication

3. Queue

4. Files

5. Schema

About

1. Calling the API#

Install the client#

Migrate to @fal-ai/client

Setup your API Key#

Submit a request#

2. Authentication#

API Key#

Protect your API Key

3. Queue#

Long-running requests

Submit a request#

Fetch request status#

Get the result#

4. Files#

Data URI (base64)#

Hosted files (URL)#

Uploading files#

Auto uploads

5. Schema#

Input#

Output#

Other types#

LoraWeight#

EasyControlWeight#

Image#

IPAdapter#

ImageSize#

ControlNetUnion#

ControlLoraWeight#

ControlNet#

Related Models