fermatresearch/sdxl-controlnet-lora-inpaint – Run with an API on Replicate

fermatresearch / sdxl-controlnet-lora-inpaint

Good old controlnet + inpaint + lora

Cold

Public
1.6K runs
L40S

Iterate in the playground

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

Input Prompt

Default: "Medium shot, Adorable blue creature with big reflective eyes"

negative_prompt

string

Shift + Return to add a new line

Input Negative Prompt

Default: "worst quality, low quality"

image

file

Preview

Input image for img2img or inpaint mode

mask

file

Preview

Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.

prompt_strength

number

(minimum: 0, maximum: 1)

Strength of the given prompt. 1 means total destruction of input image.

Default: 0.8

condition_scale

number

(minimum: 0, maximum: 1)

The bigger this number is, the more ControlNet interferes

Default: 0.5

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

scheduler

string

scheduler

Default: "DDIM"

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 35

guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 7

seed

integer

Random seed. Leave blank to randomize the seed

lora_scale

number

(minimum: 0, maximum: 1)

LoRA additive scale. Only applicable on trained models.

Default: 0.6

lora_weights

string

Shift + Return to add a new line

Replicate LoRA weights to use. Leave blank to use the default weights.

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

npx create-replicate --model=fermatresearch/sdxl-controlnet-lora-inpaint

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

const output = await replicate.run(
  "fermatresearch/sdxl-controlnet-lora-inpaint:35c927ab69062f7cc3fdd0ad4367832b08fdd98c60e5907651a6e03f4bb5d927",
  {
    input: {
      mask: "https://replicate.delivery/pbxt/KeDO2hmJs2QCyQjUpz7UNmuC8vTuILV4d9pZEhEgvyXzbvK3/dog2%20mask.png",
      image: "https://replicate.delivery/pbxt/KeDO2j9Xbw1LHuXU4jqAfh2WUpKji1AlfR5dFkSkLPiGqYWN/dog2.png",
      prompt: "a dog with a red collar",
      scheduler: "DDIM",
      lora_scale: 0.6,
      num_outputs: 1,
      guidance_scale: 7,
      condition_scale: 0.5,
      negative_prompt: "worst quality, low quality",
      prompt_strength: 0.8,
      num_inference_steps: 35
    }
  }
);

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

output = replicate.run(
    "fermatresearch/sdxl-controlnet-lora-inpaint:35c927ab69062f7cc3fdd0ad4367832b08fdd98c60e5907651a6e03f4bb5d927",
    input={
        "mask": "https://replicate.delivery/pbxt/KeDO2hmJs2QCyQjUpz7UNmuC8vTuILV4d9pZEhEgvyXzbvK3/dog2%20mask.png",
        "image": "https://replicate.delivery/pbxt/KeDO2j9Xbw1LHuXU4jqAfh2WUpKji1AlfR5dFkSkLPiGqYWN/dog2.png",
        "prompt": "a dog with a red collar",
        "scheduler": "DDIM",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "guidance_scale": 7,
        "condition_scale": 0.5,
        "negative_prompt": "worst quality, low quality",
        "prompt_strength": 0.8,
        "num_inference_steps": 35
    }
)
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 fermatresearch/sdxl-controlnet-lora-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": "fermatresearch/sdxl-controlnet-lora-inpaint:35c927ab69062f7cc3fdd0ad4367832b08fdd98c60e5907651a6e03f4bb5d927",
    "input": {
      "mask": "https://replicate.delivery/pbxt/KeDO2hmJs2QCyQjUpz7UNmuC8vTuILV4d9pZEhEgvyXzbvK3/dog2%20mask.png",
      "image": "https://replicate.delivery/pbxt/KeDO2j9Xbw1LHuXU4jqAfh2WUpKji1AlfR5dFkSkLPiGqYWN/dog2.png",
      "prompt": "a dog with a red collar",
      "scheduler": "DDIM",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidance_scale": 7,
      "condition_scale": 0.5,
      "negative_prompt": "worst quality, low quality",
      "prompt_strength": 0.8,
      "num_inference_steps": 35
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-03-28T09:25:14.574965Z",
  "created_at": "2024-03-28T09:20:56.644443Z",
  "data_removed": false,
  "error": null,
  "id": "pj64fk3bquejd7edypyrsl63bm",
  "input": {
    "mask": "https://replicate.delivery/pbxt/KeDO2hmJs2QCyQjUpz7UNmuC8vTuILV4d9pZEhEgvyXzbvK3/dog2%20mask.png",
    "image": "https://replicate.delivery/pbxt/KeDO2j9Xbw1LHuXU4jqAfh2WUpKji1AlfR5dFkSkLPiGqYWN/dog2.png",
    "prompt": "a dog with a red collar",
    "scheduler": "DDIM",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "guidance_scale": 7,
    "condition_scale": 0.5,
    "negative_prompt": "worst quality, low quality",
    "prompt_strength": 0.8,
    "num_inference_steps": 35
  },
  "logs": "Using seed: 34850\nPrompt: a dog with a red collar\nOriginal width:1024, height:1024\nAspect Ratio: 1.00\nnew_width:1024, new_height:1024\nOriginal width:1024, height:1024\nAspect Ratio: 1.00\nnew_width:1024, new_height:1024\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:09,  2.77it/s]\n  7%|▋         | 2/28 [00:00<00:08,  3.10it/s]\n 11%|█         | 3/28 [00:00<00:07,  3.22it/s]\n 14%|█▍        | 4/28 [00:01<00:07,  3.27it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.30it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.32it/s]\n 25%|██▌       | 7/28 [00:02<00:06,  3.34it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.34it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.34it/s]\n 36%|███▌      | 10/28 [00:03<00:05,  3.34it/s]\n 39%|███▉      | 11/28 [00:03<00:05,  3.35it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.35it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.35it/s]\n 50%|█████     | 14/28 [00:04<00:04,  3.35it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.35it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.36it/s]\n 61%|██████    | 17/28 [00:05<00:03,  3.37it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.37it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.38it/s]\n 71%|███████▏  | 20/28 [00:06<00:02,  3.38it/s]\n 75%|███████▌  | 21/28 [00:06<00:02,  3.38it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.38it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.37it/s]\n 86%|████████▌ | 24/28 [00:07<00:01,  3.37it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.37it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.37it/s]\n 96%|█████████▋| 27/28 [00:08<00:00,  3.37it/s]\n100%|██████████| 28/28 [00:08<00:00,  3.37it/s]\n100%|██████████| 28/28 [00:08<00:00,  3.34it/s]",
  "metrics": {
    "predict_time": 12.222418,
    "total_time": 257.930522
  },
  "output": [
    "https://replicate.delivery/pbxt/6nYFmW4FYlo6O9SbngCZ1u1HoBF4QlWnvpKpHa3MnAUeSXSJA/out-0.png"
  ],
  "started_at": "2024-03-28T09:25:02.352547Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/pj64fk3bquejd7edypyrsl63bm",
    "cancel": "https://api.replicate.com/v1/predictions/pj64fk3bquejd7edypyrsl63bm/cancel"
  },
  "version": "35c927ab69062f7cc3fdd0ad4367832b08fdd98c60e5907651a6e03f4bb5d927"
}

Generated in

12.2 seconds

Tweak itReport

Using seed: 34850
Prompt: a dog with a red collar
Original width:1024, height:1024
Aspect Ratio: 1.00
new_width:1024, new_height:1024
Original width:1024, height:1024
Aspect Ratio: 1.00
new_width:1024, new_height:1024
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:09,  2.77it/s]
  7%|▋         | 2/28 [00:00<00:08,  3.10it/s]
 11%|█         | 3/28 [00:00<00:07,  3.22it/s]
 14%|█▍        | 4/28 [00:01<00:07,  3.27it/s]
 18%|█▊        | 5/28 [00:01<00:06,  3.30it/s]
 21%|██▏       | 6/28 [00:01<00:06,  3.32it/s]
 25%|██▌       | 7/28 [00:02<00:06,  3.34it/s]
 29%|██▊       | 8/28 [00:02<00:05,  3.34it/s]
 32%|███▏      | 9/28 [00:02<00:05,  3.34it/s]
 36%|███▌      | 10/28 [00:03<00:05,  3.34it/s]
 39%|███▉      | 11/28 [00:03<00:05,  3.35it/s]
 43%|████▎     | 12/28 [00:03<00:04,  3.35it/s]
 46%|████▋     | 13/28 [00:03<00:04,  3.35it/s]
 50%|█████     | 14/28 [00:04<00:04,  3.35it/s]
 54%|█████▎    | 15/28 [00:04<00:03,  3.35it/s]
 57%|█████▋    | 16/28 [00:04<00:03,  3.36it/s]
 61%|██████    | 17/28 [00:05<00:03,  3.37it/s]
 64%|██████▍   | 18/28 [00:05<00:02,  3.37it/s]
 68%|██████▊   | 19/28 [00:05<00:02,  3.38it/s]
 71%|███████▏  | 20/28 [00:06<00:02,  3.38it/s]
 75%|███████▌  | 21/28 [00:06<00:02,  3.38it/s]
 79%|███████▊  | 22/28 [00:06<00:01,  3.38it/s]
 82%|████████▏ | 23/28 [00:06<00:01,  3.37it/s]
 86%|████████▌ | 24/28 [00:07<00:01,  3.37it/s]
 89%|████████▉ | 25/28 [00:07<00:00,  3.37it/s]
 93%|█████████▎| 26/28 [00:07<00:00,  3.37it/s]
 96%|█████████▋| 27/28 [00:08<00:00,  3.37it/s]
100%|██████████| 28/28 [00:08<00:00,  3.37it/s]
100%|██████████| 28/28 [00:08<00:00,  3.34it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.24 to run on Replicate, or 4 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 5 minutes. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.