fishwowater/flux-dev-controlnet-inpainting-beta:27d3ff35

Version

You're looking at a specific version of this model. Jump to the model overview.

fishwowater /flux-dev-controlnet-inpainting-beta:27d3ff35

Playground API

Input

image

*file

Preview

Upload an image for inpainting. This will be the base image that will be partially modified.

mask

*file

Preview

Upload a mask image for inpainting. White areas (255) indicate regions to be inpainted, while black areas (0) will be preserved from the original image.

prompt

string

Shift + Return to add a new line

a person wearing a white shoe, carrying a white bucket with text 'REPLICATE FLUX INPAINTING CONTROLNET' on ita person wearing a white shoe, carrying a white bucket with text 'REPLICATE FLUX INPAINTING CONTROLNET' on it

Enter a text description to guide the image generation process.

Default: "A colorful hot air balloon floating over a serene landscape."

negative_prompt

string

Shift + Return to add a new line

Negative text prompt. Used to reduce or avoid certain aspects in the generated image.

Default: ""

controlnet_conditioning_scale

number

(minimum: 0, maximum: 2)

ControlNet conditioning scale.

Default: 0.9

num_inference_steps

integer

(minimum: 1, maximum: 100)

Set the number of denoising steps. More steps generally result in higher quality but slower generation.

Default: 28

guidance_scale

number

(minimum: 0, maximum: 20)

Guidance scale for classifier-free guidance. Higher values encourage the model to generate images that are closer to the text prompt.

Default: 3.5

true_guidance_scale

number

(minimum: 0, maximum: 20)

True guidance scale for the transformer model.

Default: 3.5

num_outputs

integer

(minimum: 1, maximum: 10)

Number of images to generate.

Default: 1

seed

integer

Set a seed for reproducible generation. Leave as None for random results.

output_format

string

Choose the file format for the output images.

Default: "webp"

output_quality

integer

(minimum: 1, maximum: 100)

Quality of the output images (applicable for 'jpg' and 'webp'). Value between 1 (lowest quality) and 100 (highest quality). Ignored for 'png'.

Default: 80

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

npx create-replicate --model=fishwowater/flux-dev-controlnet-inpainting-beta

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 fishwowater/flux-dev-controlnet-inpainting-beta using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "fishwowater/flux-dev-controlnet-inpainting-beta:27d3ff35f58b4409775de5a0b36e99b4c6d2d7fc7fe772b35170951db678ec63",
  {
    input: {
      mask: "https://replicate.delivery/pbxt/Le6GAg8i6DrhZxvjibNmzKy4jPYEKIhH8DBZnUp2WAioguXI/bucket_mask.jpeg",
      image: "https://replicate.delivery/pbxt/Le6GAdIHbCc7u5RAFQ09dqJoROHEayxjWQbg9Hx16aY2fa9L/bucket.png",
      prompt: "a person wearing a white shoe, carrying a white bucket with text 'REPLICATE FLUX INPAINTING CONTROLNET' on it",
      num_outputs: 1,
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      negative_prompt: "",
      num_inference_steps: 28,
      true_guidance_scale: 3.5,
      controlnet_conditioning_scale: 0.9
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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 fishwowater/flux-dev-controlnet-inpainting-beta using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fishwowater/flux-dev-controlnet-inpainting-beta:27d3ff35f58b4409775de5a0b36e99b4c6d2d7fc7fe772b35170951db678ec63",
    input={
        "mask": "https://replicate.delivery/pbxt/Le6GAg8i6DrhZxvjibNmzKy4jPYEKIhH8DBZnUp2WAioguXI/bucket_mask.jpeg",
        "image": "https://replicate.delivery/pbxt/Le6GAdIHbCc7u5RAFQ09dqJoROHEayxjWQbg9Hx16aY2fa9L/bucket.png",
        "prompt": "a person wearing a white shoe, carrying a white bucket with text 'REPLICATE FLUX INPAINTING CONTROLNET' on it",
        "num_outputs": 1,
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "negative_prompt": "",
        "num_inference_steps": 28,
        "true_guidance_scale": 3.5,
        "controlnet_conditioning_scale": 0.9
    }
)
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 fishwowater/flux-dev-controlnet-inpainting-beta 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 $'{
    "version": "fishwowater/flux-dev-controlnet-inpainting-beta:27d3ff35f58b4409775de5a0b36e99b4c6d2d7fc7fe772b35170951db678ec63",
    "input": {
      "mask": "https://replicate.delivery/pbxt/Le6GAg8i6DrhZxvjibNmzKy4jPYEKIhH8DBZnUp2WAioguXI/bucket_mask.jpeg",
      "image": "https://replicate.delivery/pbxt/Le6GAdIHbCc7u5RAFQ09dqJoROHEayxjWQbg9Hx16aY2fa9L/bucket.png",
      "prompt": "a person wearing a white shoe, carrying a white bucket with text \'REPLICATE FLUX INPAINTING CONTROLNET\' on it",
      "num_outputs": 1,
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "negative_prompt": "",
      "num_inference_steps": 28,
      "true_guidance_scale": 3.5,
      "controlnet_conditioning_scale": 0.9
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2025-04-22T03:45:37.288960Z",
  "created_at": "2025-04-22T03:42:52.009000Z",
  "data_removed": false,
  "error": null,
  "id": "qr90vk3ad5rj20cpbebtct4d60",
  "input": {
    "mask": "https://replicate.delivery/pbxt/Le6GAg8i6DrhZxvjibNmzKy4jPYEKIhH8DBZnUp2WAioguXI/bucket_mask.jpeg",
    "image": "https://replicate.delivery/pbxt/Le6GAdIHbCc7u5RAFQ09dqJoROHEayxjWQbg9Hx16aY2fa9L/bucket.png",
    "prompt": "a person wearing a white shoe, carrying a white bucket with text 'REPLICATE FLUX INPAINTING CONTROLNET' on it",
    "num_outputs": 1,
    "output_format": "webp",
    "guidance_scale": 3.5,
    "output_quality": 80,
    "negative_prompt": "",
    "num_inference_steps": 28,
    "true_guidance_scale": 3.5,
    "controlnet_conditioning_scale": 0.9
  },
  "logs": "Using seeds: [2222903277]\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:18,  1.46it/s]\n  7%|▋         | 2/28 [00:01<00:13,  1.89it/s]\n 11%|█         | 3/28 [00:01<00:14,  1.69it/s]\n 14%|█▍        | 4/28 [00:02<00:14,  1.62it/s]\n 18%|█▊        | 5/28 [00:03<00:14,  1.58it/s]\n 21%|██▏       | 6/28 [00:03<00:14,  1.55it/s]\n 25%|██▌       | 7/28 [00:04<00:13,  1.54it/s]\n 29%|██▊       | 8/28 [00:05<00:13,  1.53it/s]\n 32%|███▏      | 9/28 [00:05<00:12,  1.52it/s]\n 36%|███▌      | 10/28 [00:06<00:11,  1.52it/s]\n 39%|███▉      | 11/28 [00:07<00:11,  1.51it/s]\n 43%|████▎     | 12/28 [00:07<00:10,  1.51it/s]\n 46%|████▋     | 13/28 [00:08<00:09,  1.51it/s]\n 50%|█████     | 14/28 [00:09<00:09,  1.51it/s]\n 54%|█████▎    | 15/28 [00:09<00:08,  1.51it/s]\n 57%|█████▋    | 16/28 [00:10<00:07,  1.50it/s]\n 61%|██████    | 17/28 [00:11<00:07,  1.50it/s]\n 64%|██████▍   | 18/28 [00:11<00:06,  1.50it/s]\n 68%|██████▊   | 19/28 [00:12<00:05,  1.50it/s]\n 71%|███████▏  | 20/28 [00:13<00:05,  1.50it/s]\n 75%|███████▌  | 21/28 [00:13<00:04,  1.50it/s]\n 79%|███████▊  | 22/28 [00:14<00:03,  1.50it/s]\n 82%|████████▏ | 23/28 [00:15<00:03,  1.50it/s]\n 86%|████████▌ | 24/28 [00:15<00:02,  1.50it/s]\n 89%|████████▉ | 25/28 [00:16<00:01,  1.50it/s]\n 93%|█████████▎| 26/28 [00:17<00:01,  1.50it/s]\n 96%|█████████▋| 27/28 [00:17<00:00,  1.50it/s]\n100%|██████████| 28/28 [00:18<00:00,  1.50it/s]\n100%|██████████| 28/28 [00:18<00:00,  1.52it/s]\n[~] Saving to /tmp/output_0.webp...\n[~] Output format: WEBP\n[~] Output quality: 80",
  "metrics": {
    "predict_time": 20.163079449,
    "total_time": 165.27996
  },
  "output": [
    "https://replicate.delivery/yhqm/3WhkfI7t6eoCQ0fi7qNtznimZcRfVnPajAgzCfV0kBtJchpkC/output_0.webp"
  ],
  "started_at": "2025-04-22T03:45:17.125880Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/yswh-6k3ia3l4mvzeteo42aw3dfrxnfkseecfq3gktzrtjaciqcu7fs4a",
    "get": "https://api.replicate.com/v1/predictions/qr90vk3ad5rj20cpbebtct4d60",
    "cancel": "https://api.replicate.com/v1/predictions/qr90vk3ad5rj20cpbebtct4d60/cancel"
  },
  "version": "27d3ff35f58b4409775de5a0b36e99b4c6d2d7fc7fe772b35170951db678ec63"
}

Generated in

20.2 seconds

Tweak it ShareReport