Official

black-forest-labs / flux-fill-dev

Open-weight inpainting model for editing and extending images. Guidance-distilled from FLUX.1 Fill [pro].

Warm

Public
187.4K runs
$0.04 per image
Commercial use
Weights
License

Run with an API

This model uses a mask. Visit the new playground to try this model with our mask editing tool.

Playground API Examples README

Input

prompt

*string

Shift + Return to add a new line

Prompt for generated image

image

*file

Preview

The image to inpaint. Can contain alpha mask. If the image width or height are not multiples of 32, they will be scaled to the closest multiple of 32. If the image dimensions don't fit within 1440x1440, it will be scaled down to fit.

mask

file

Preview

A black-and-white image that describes the part of the image to inpaint. Black areas will be preserved while white areas will be inpainted.

num_outputs

integer

(minimum: 1, maximum: 4)

Number of outputs to generate

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 50)

Number of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster.

Default: 28

guidance

number

(minimum: 0, maximum: 100)

Guidance for generated image

Default: 30

seed

integer

Random seed. Set for reproducible generation

megapixels

string

Approximate number of megapixels for generated image. Use match_input to match the size of the input (with an upper limit of 1440x1440 pixels)

Default: "1"

output_format

string

Format of the output images

Default: "webp"

output_quality

integer

(minimum: 0, maximum: 100)

Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs

Default: 80

lora_weights

string

Shift + Return to add a new line

Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'

lora_scale

number

(minimum: -1, maximum: 3)

Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.

Default: 1

disable_safety_checker

boolean

Disable safety checker for generated images.

Default: false

Run this model in Node.js with one line of code:

npx create-replicate --model=black-forest-labs/flux-fill-dev

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run black-forest-labs/flux-fill-dev using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  mask: "https://replicate.delivery/pbxt/M0hxLu8a1YBcybWuumSsfoEec8ooer6JZ2fR28vuM1U0CN9m/74b40bb1-364a-461a-bec5-200a38c7bc87.png",
  image: "https://replicate.delivery/pbxt/M0hxMJeO7wFCMr7QYNZsjRxzHhz6ntlLllMteRQNsRD7f3Nf/flux-fill-dev.webp",
  prompt: "a spaceship",
  guidance: 30,
  lora_scale: 1,
  megapixels: "1",
  num_outputs: 1,
  output_format: "webp",
  output_quality: 80,
  num_inference_steps: 28
};

const output = await replicate.run("black-forest-labs/flux-fill-dev", { input });
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run black-forest-labs/flux-fill-dev using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "black-forest-labs/flux-fill-dev",
    input={
        "mask": "https://replicate.delivery/pbxt/M0hxLu8a1YBcybWuumSsfoEec8ooer6JZ2fR28vuM1U0CN9m/74b40bb1-364a-461a-bec5-200a38c7bc87.png",
        "image": "https://replicate.delivery/pbxt/M0hxMJeO7wFCMr7QYNZsjRxzHhz6ntlLllMteRQNsRD7f3Nf/flux-fill-dev.webp",
        "prompt": "a spaceship",
        "guidance": 30,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "output_format": "webp",
        "output_quality": 80,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run black-forest-labs/flux-fill-dev using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "input": {
      "mask": "https://replicate.delivery/pbxt/M0hxLu8a1YBcybWuumSsfoEec8ooer6JZ2fR28vuM1U0CN9m/74b40bb1-364a-461a-bec5-200a38c7bc87.png",
      "image": "https://replicate.delivery/pbxt/M0hxMJeO7wFCMr7QYNZsjRxzHhz6ntlLllMteRQNsRD7f3Nf/flux-fill-dev.webp",
      "prompt": "a spaceship",
      "guidance": 30,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "output_format": "webp",
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/models/black-forest-labs/flux-fill-dev/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2024-11-21T10:15:39.656881Z",
  "created_at": "2024-11-21T10:15:30.102000Z",
  "data_removed": false,
  "error": null,
  "id": "nbhx3kj26srm80ck9rwbscz1q0",
  "input": {
    "mask": "https://replicate.delivery/pbxt/M0hxLu8a1YBcybWuumSsfoEec8ooer6JZ2fR28vuM1U0CN9m/74b40bb1-364a-461a-bec5-200a38c7bc87.png",
    "image": "https://replicate.delivery/pbxt/M0hxMJeO7wFCMr7QYNZsjRxzHhz6ntlLllMteRQNsRD7f3Nf/flux-fill-dev.webp",
    "prompt": "a spaceship",
    "guidance": 30,
    "num_outputs": 1,
    "output_format": "webp",
    "output_quality": 80,
    "num_inference_steps": 28
  },
  "logs": "running bf16 model, fp8 disabled\nUsing seed: 12554\nInput image size: 1024x1024\nInput image size set to: 1024x1024\n0it [00:00, ?it/s]\n1it [00:00,  6.43it/s]\n2it [00:00,  5.21it/s]\n3it [00:00,  4.91it/s]\n4it [00:00,  4.78it/s]\n5it [00:01,  4.71it/s]\n6it [00:01,  4.67it/s]\n7it [00:01,  4.63it/s]\n8it [00:01,  4.62it/s]\n9it [00:01,  4.61it/s]\n10it [00:02,  4.60it/s]\n11it [00:02,  4.60it/s]\n12it [00:02,  4.60it/s]\n13it [00:02,  4.59it/s]\n14it [00:02,  4.59it/s]\n15it [00:03,  4.59it/s]\n16it [00:03,  4.59it/s]\n17it [00:03,  4.58it/s]\n18it [00:03,  4.58it/s]\n19it [00:04,  4.57it/s]\n20it [00:04,  4.57it/s]\n21it [00:04,  4.57it/s]\n22it [00:04,  4.57it/s]\n23it [00:04,  4.57it/s]\n24it [00:05,  4.57it/s]\n25it [00:05,  4.58it/s]\n26it [00:05,  4.58it/s]\n27it [00:05,  4.58it/s]\n28it [00:06,  4.57it/s]\n28it [00:06,  4.63it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "image_count": 1,
    "predict_time": 9.544116396,
    "total_time": 9.554881
  },
  "output": [
    "https://replicate.delivery/xezq/XAOCdYKsGYZ9FNTeeEQPbl8DM9eoDf050jLfSAZMuWVYJdZeE/out-0.webp"
  ],
  "started_at": "2024-11-21T10:15:30.112765Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-ocdi6wafsezivgg6gtokmxu4rhvv4bhdhbx6vsomy7p2s5jxrq5q",
    "get": "https://api.replicate.com/v1/predictions/nbhx3kj26srm80ck9rwbscz1q0",
    "cancel": "https://api.replicate.com/v1/predictions/nbhx3kj26srm80ck9rwbscz1q0/cancel"
  },
  "version": "hidden"
}

Generated in

9.6 seconds

Tweak it ShareReport

Examples

View more examples

Pricing

This model is priced by how many images are generated.

Type	Per unit	Per $1
Output	$0.04 / image or 25 images / $1

For example, generating 100 images should cost around $4.00.

Check out our docs for more information about how per-image pricing works on Replicate.

Readme

FLUX.1 Fill [dev]

FLUX.1 Fill [dev] brings professional-quality inpainting to open development. Paint over any part of an image, describe what you want to see instead, and get natural results that respect the original context.

This is the same technology that powers flux-fill-pro optimized for developers building creative tools.

License

If you generate images on Replicate with FLUX.1 models and their fine-tunes, then you can use the images commercially.

If you download the weights off Replicate and generate images on your own computer, you can’t use the images commercially.