fermatresearch / flux-controlnet-inpaint

Run inpainting with Flux, compatible with Canny ControlNet, LoRAs and HyperFlux_8step

Cold

Public
16.6K runs
A100 (80GB)
GitHub

Run with an API

Playground API Examples README Versions

Prediction

fermatresearch/flux-controlnet-inpaint:46ae77d1d148dca1bd61c1215e99ee692c4cf01289a2bba681b14a58c04bda8f

Model

fermatresearch/flux-controlnet-inpaint:46ae77d1

9gv8ma1xzxrj60cj0jdrjsgp9c

Status

Succeeded

Source

Web

Hardware

A100 (80GB)

Total duration

1m 32s

Created

8 months ago

Input

mask
image
prompt: Professional photography of a fox sitting on a bench
strength: 0.8
lora_scale: 0.8
control_image
output_format: jpg
guidance_scale: 3.5
output_quality: 100
conditioning_scale: 0.5
num_inference_steps: 8
enable_hyper_flux_8_step

{
  "mask": "https://replicate.delivery/pbxt/LdzOC0eYgmiQxsZntL8aUwyQlLjtXQuhmMrXrOUbpMESw11v/output%20%282%29.png",
  "image": "https://replicate.delivery/pbxt/LdzOC2USRj4omEK2igawxoYUPG6hJ2RfRZS2TZXiqSEkybYs/output%20%283%29.png",
  "prompt": "Professional photography of a fox sitting on a bench",
  "strength": 0.8,
  "lora_scale": 0.8,
  "control_image": "https://replicate.delivery/pbxt/LdzOBqGI9FyIIPZOyOBYToYndRLXelYBSqOP1XJlE5Tq5up9/output%20%283%29.png",
  "output_format": "jpg",
  "guidance_scale": 3.5,
  "output_quality": 100,
  "conditioning_scale": 0.5,
  "num_inference_steps": 8,
  "enable_hyper_flux_8_step": true
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

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

Run fermatresearch/flux-controlnet-inpaint using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "fermatresearch/flux-controlnet-inpaint:46ae77d1d148dca1bd61c1215e99ee692c4cf01289a2bba681b14a58c04bda8f",
  {
    input: {
      mask: "https://replicate.delivery/pbxt/LdzOC0eYgmiQxsZntL8aUwyQlLjtXQuhmMrXrOUbpMESw11v/output%20%282%29.png",
      image: "https://replicate.delivery/pbxt/LdzOC2USRj4omEK2igawxoYUPG6hJ2RfRZS2TZXiqSEkybYs/output%20%283%29.png",
      prompt: "Professional photography of a fox sitting on a bench",
      strength: 0.8,
      lora_scale: 0.8,
      control_image: "https://replicate.delivery/pbxt/LdzOBqGI9FyIIPZOyOBYToYndRLXelYBSqOP1XJlE5Tq5up9/output%20%283%29.png",
      output_format: "jpg",
      guidance_scale: 3.5,
      output_quality: 100,
      conditioning_scale: 0.5,
      num_inference_steps: 8,
      enable_hyper_flux_8_step: true
    }
  }
);

// 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

Import the client:

import replicate

Run fermatresearch/flux-controlnet-inpaint using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fermatresearch/flux-controlnet-inpaint:46ae77d1d148dca1bd61c1215e99ee692c4cf01289a2bba681b14a58c04bda8f",
    input={
        "mask": "https://replicate.delivery/pbxt/LdzOC0eYgmiQxsZntL8aUwyQlLjtXQuhmMrXrOUbpMESw11v/output%20%282%29.png",
        "image": "https://replicate.delivery/pbxt/LdzOC2USRj4omEK2igawxoYUPG6hJ2RfRZS2TZXiqSEkybYs/output%20%283%29.png",
        "prompt": "Professional photography of a fox sitting on a bench",
        "strength": 0.8,
        "lora_scale": 0.8,
        "control_image": "https://replicate.delivery/pbxt/LdzOBqGI9FyIIPZOyOBYToYndRLXelYBSqOP1XJlE5Tq5up9/output%20%283%29.png",
        "output_format": "jpg",
        "guidance_scale": 3.5,
        "output_quality": 100,
        "conditioning_scale": 0.5,
        "num_inference_steps": 8,
        "enable_hyper_flux_8_step": True
    }
)
print(output)

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

Run fermatresearch/flux-controlnet-inpaint 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": "46ae77d1d148dca1bd61c1215e99ee692c4cf01289a2bba681b14a58c04bda8f",
    "input": {
      "mask": "https://replicate.delivery/pbxt/LdzOC0eYgmiQxsZntL8aUwyQlLjtXQuhmMrXrOUbpMESw11v/output%20%282%29.png",
      "image": "https://replicate.delivery/pbxt/LdzOC2USRj4omEK2igawxoYUPG6hJ2RfRZS2TZXiqSEkybYs/output%20%283%29.png",
      "prompt": "Professional photography of a fox sitting on a bench",
      "strength": 0.8,
      "lora_scale": 0.8,
      "control_image": "https://replicate.delivery/pbxt/LdzOBqGI9FyIIPZOyOBYToYndRLXelYBSqOP1XJlE5Tq5up9/output%20%283%29.png",
      "output_format": "jpg",
      "guidance_scale": 3.5,
      "output_quality": 100,
      "conditioning_scale": 0.5,
      "num_inference_steps": 8,
      "enable_hyper_flux_8_step": true
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

10.9 seconds

Tweak it ShareReport

Prediction

fermatresearch/flux-controlnet-inpaint:46ae77d1d148dca1bd61c1215e99ee692c4cf01289a2bba681b14a58c04bda8f

Model

fermatresearch/flux-controlnet-inpaint:46ae77d1

an7n0term9rj40cj0jnr0p4g1r

Status

Succeeded

Source

Web

Hardware

A100 (80GB)

Total duration

24.2s

Created

8 months ago

Input

mask
image
prompt: Product photography of a puffy jacket with a logo of a high quality red flower in the chest.
strength: 0.99
lora_scale: 0.8
control_image
output_format: jpg
guidance_scale: 2.5
output_quality: 100
conditioning_scale: 0.4
num_inference_steps: 28
enable_hyper_flux_8_step

{
  "mask": "https://replicate.delivery/pbxt/LdzfKF7Xj9JJnOjnEwx6DpOPQ6ZwIGlopaGAe2xCwWUYafak/output%202.png",
  "image": "https://replicate.delivery/pbxt/LdzfJhIScoFTFBGfXNZbO6e7zuBJnZFn0YSs0Kd17BuyhHc4/test.png",
  "prompt": "Product photography of a puffy jacket with a logo of a high quality red flower in the chest.",
  "strength": 0.99,
  "lora_scale": 0.8,
  "control_image": "https://replicate.delivery/pbxt/LdzfJozitU8Ldhv0ELr2mvJw9UlYSbs1pwpnRh9Z6c8RXMna/test.png",
  "output_format": "jpg",
  "guidance_scale": 2.5,
  "output_quality": 100,
  "conditioning_scale": 0.4,
  "num_inference_steps": 28,
  "enable_hyper_flux_8_step": false
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

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

Run fermatresearch/flux-controlnet-inpaint using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "fermatresearch/flux-controlnet-inpaint:46ae77d1d148dca1bd61c1215e99ee692c4cf01289a2bba681b14a58c04bda8f",
  {
    input: {
      mask: "https://replicate.delivery/pbxt/LdzfKF7Xj9JJnOjnEwx6DpOPQ6ZwIGlopaGAe2xCwWUYafak/output%202.png",
      image: "https://replicate.delivery/pbxt/LdzfJhIScoFTFBGfXNZbO6e7zuBJnZFn0YSs0Kd17BuyhHc4/test.png",
      prompt: "Product photography of a puffy jacket with a logo of a high quality red flower in the chest.",
      strength: 0.99,
      lora_scale: 0.8,
      control_image: "https://replicate.delivery/pbxt/LdzfJozitU8Ldhv0ELr2mvJw9UlYSbs1pwpnRh9Z6c8RXMna/test.png",
      output_format: "jpg",
      guidance_scale: 2.5,
      output_quality: 100,
      conditioning_scale: 0.4,
      num_inference_steps: 28,
      enable_hyper_flux_8_step: false
    }
  }
);

// 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

Import the client:

import replicate

Run fermatresearch/flux-controlnet-inpaint using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fermatresearch/flux-controlnet-inpaint:46ae77d1d148dca1bd61c1215e99ee692c4cf01289a2bba681b14a58c04bda8f",
    input={
        "mask": "https://replicate.delivery/pbxt/LdzfKF7Xj9JJnOjnEwx6DpOPQ6ZwIGlopaGAe2xCwWUYafak/output%202.png",
        "image": "https://replicate.delivery/pbxt/LdzfJhIScoFTFBGfXNZbO6e7zuBJnZFn0YSs0Kd17BuyhHc4/test.png",
        "prompt": "Product photography of a puffy jacket with a logo of a high quality red flower in the chest.",
        "strength": 0.99,
        "lora_scale": 0.8,
        "control_image": "https://replicate.delivery/pbxt/LdzfJozitU8Ldhv0ELr2mvJw9UlYSbs1pwpnRh9Z6c8RXMna/test.png",
        "output_format": "jpg",
        "guidance_scale": 2.5,
        "output_quality": 100,
        "conditioning_scale": 0.4,
        "num_inference_steps": 28,
        "enable_hyper_flux_8_step": False
    }
)
print(output)

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

Run fermatresearch/flux-controlnet-inpaint 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": "46ae77d1d148dca1bd61c1215e99ee692c4cf01289a2bba681b14a58c04bda8f",
    "input": {
      "mask": "https://replicate.delivery/pbxt/LdzfKF7Xj9JJnOjnEwx6DpOPQ6ZwIGlopaGAe2xCwWUYafak/output%202.png",
      "image": "https://replicate.delivery/pbxt/LdzfJhIScoFTFBGfXNZbO6e7zuBJnZFn0YSs0Kd17BuyhHc4/test.png",
      "prompt": "Product photography of a puffy jacket with a logo of a high quality red flower in the chest.",
      "strength": 0.99,
      "lora_scale": 0.8,
      "control_image": "https://replicate.delivery/pbxt/LdzfJozitU8Ldhv0ELr2mvJw9UlYSbs1pwpnRh9Z6c8RXMna/test.png",
      "output_format": "jpg",
      "guidance_scale": 2.5,
      "output_quality": 100,
      "conditioning_scale": 0.4,
      "num_inference_steps": 28,
      "enable_hyper_flux_8_step": false
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-09-18T10:27:28.191020Z",
  "created_at": "2024-09-18T10:27:03.970000Z",
  "data_removed": false,
  "error": null,
  "id": "an7n0term9rj40cj0jnr0p4g1r",
  "input": {
    "mask": "https://replicate.delivery/pbxt/LdzfKF7Xj9JJnOjnEwx6DpOPQ6ZwIGlopaGAe2xCwWUYafak/output%202.png",
    "image": "https://replicate.delivery/pbxt/LdzfJhIScoFTFBGfXNZbO6e7zuBJnZFn0YSs0Kd17BuyhHc4/test.png",
    "prompt": "Product photography of a puffy jacket with a logo of a high quality red flower in the chest.",
    "strength": 0.99,
    "lora_scale": 0.8,
    "control_image": "https://replicate.delivery/pbxt/LdzfJozitU8Ldhv0ELr2mvJw9UlYSbs1pwpnRh9Z6c8RXMna/test.png",
    "output_format": "jpg",
    "guidance_scale": 2.5,
    "output_quality": 100,
    "conditioning_scale": 0.4,
    "num_inference_steps": 28,
    "enable_hyper_flux_8_step": false
  },
  "logs": "Using seed: 23149\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:18,  1.44it/s]\n  7%|▋         | 2/28 [00:01<00:16,  1.57it/s]\n 11%|█         | 3/28 [00:01<00:15,  1.61it/s]\n 14%|█▍        | 4/28 [00:02<00:14,  1.64it/s]\n 18%|█▊        | 5/28 [00:03<00:13,  1.65it/s]\n 21%|██▏       | 6/28 [00:03<00:13,  1.66it/s]\n 25%|██▌       | 7/28 [00:04<00:12,  1.66it/s]\n 29%|██▊       | 8/28 [00:04<00:12,  1.66it/s]\n 32%|███▏      | 9/28 [00:05<00:11,  1.66it/s]\n 36%|███▌      | 10/28 [00:06<00:10,  1.67it/s]\n 39%|███▉      | 11/28 [00:06<00:10,  1.67it/s]\n 43%|████▎     | 12/28 [00:07<00:09,  1.67it/s]\n 46%|████▋     | 13/28 [00:07<00:09,  1.67it/s]\n 50%|█████     | 14/28 [00:08<00:08,  1.67it/s]\n 54%|█████▎    | 15/28 [00:09<00:07,  1.67it/s]\n 57%|█████▋    | 16/28 [00:09<00:07,  1.67it/s]\n 61%|██████    | 17/28 [00:10<00:06,  1.67it/s]\n 64%|██████▍   | 18/28 [00:10<00:06,  1.66it/s]\n 68%|██████▊   | 19/28 [00:11<00:05,  1.66it/s]\n 71%|███████▏  | 20/28 [00:12<00:04,  1.66it/s]\n 75%|███████▌  | 21/28 [00:12<00:04,  1.67it/s]\n 79%|███████▊  | 22/28 [00:13<00:03,  1.66it/s]\n 82%|████████▏ | 23/28 [00:13<00:03,  1.66it/s]\n 86%|████████▌ | 24/28 [00:14<00:02,  1.66it/s]\n 89%|████████▉ | 25/28 [00:15<00:01,  1.66it/s]\n 93%|█████████▎| 26/28 [00:15<00:01,  1.66it/s]\n 96%|█████████▋| 27/28 [00:16<00:00,  1.66it/s]\n100%|██████████| 28/28 [00:16<00:00,  1.76it/s]\n100%|██████████| 28/28 [00:16<00:00,  1.67it/s]",
  "metrics": {
    "predict_time": 24.212186638,
    "total_time": 24.22102
  },
  "output": [
    "https://replicate.delivery/yhqm/kxUBwVQewGUe30e0Lzf4JfNxrz2rtzKn3RHa2O1uVgx7huwbC/out-0.jpg"
  ],
  "started_at": "2024-09-18T10:27:03.978834Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/an7n0term9rj40cj0jnr0p4g1r",
    "cancel": "https://api.replicate.com/v1/predictions/an7n0term9rj40cj0jnr0p4g1r/cancel"
  },
  "version": "46ae77d1d148dca1bd61c1215e99ee692c4cf01289a2bba681b14a58c04bda8f"
}

Generated in

24.2 seconds

Tweak it ShareReport

Want to make some of these yourself?

Run this model

fermatresearch / flux-controlnet-inpaint

Prediction

Input

Output

Prediction

Input

Output

Logs (9gv8ma1xzxrj60cj0jdrjsgp9c)

Logs (an7n0term9rj40cj0jnr0p4g1r)