kevin51jiang/ic-light:c5089f92 – Run with an API on Replicate

Version

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

kevin51jiang /ic-light:c5089f92

Playground API Setup logs

Input

subject_image

*file

The main foreground image to be relighted

prompt

*string

Shift + Return to add a new line

Woman, detailed face, sci-fi RGB glowing, cyberpunkWoman, detailed face, sci-fi RGB glowing, cyberpunk

A text description guiding the relighting and generation process

appended_prompt

string

Shift + Return to add a new line

Additional text to be appended to the main prompt, enhancing image quality

Default: "best quality"

negative_prompt

string

Shift + Return to add a new line

lowres, bad anatomy, bad hands, cropped, worst qualitylowres, bad anatomy, bad hands, cropped, worst quality

A text description of attributes to avoid in the generated images

Default: "lowres, bad anatomy, bad hands, cropped, worst quality"

width

integer

(minimum: 100, maximum: 1024)

The width of the generated images in pixels

Default: 512

height

integer

(minimum: 100, maximum: 1024)

The height of the generated images in pixels

Default: 640

steps

integer

(minimum: 1, maximum: 100)

The number of diffusion steps to perform during generation (more steps generally improves image quality but increases processing time)

Default: 25

cfg

number

(minimum: 1, maximum: 32)

Classifier-Free Guidance scale - higher values encourage adherence to prompt, lower values encourage more creative interpretation

Default: 2

highres_scale

number

(minimum: 1, maximum: 3)

The multiplier for the final output resolution relative to the initial latent resolution

Default: 1.5

highres_denoise

number

(minimum: 0.1, maximum: 1)

Controls the amount of denoising applied when refining the high resolution output (higher = more adherence to the upscaled latent, lower = more creative details added)

Default: 0.5

lowres_denoise

number

(minimum: 0.1, maximum: 1)

Controls the amount of denoising applied when generating the initial latent from the background image (higher = more adherence to the background, lower = more creative interpretation)

Default: 0.9

light_source

string

The type and position of lighting to apply to the initial background latent

Default: "None"

seed

integer

A fixed random seed for reproducible results (omit this parameter for a randomized seed)

number_of_images

integer

(minimum: 1, maximum: 12)

The number of unique images to generate from the given input and settings

Default: 1

output_format

string

The image file format of the generated output images

Default: "webp"

output_quality

integer

(minimum: 0, maximum: 100)

The image compression quality (for lossy formats like JPEG and WebP). 100 = best quality, 0 = lowest quality.

Default: 80

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

npx create-replicate --model=kevin51jiang/ic-light

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 kevin51jiang/ic-light using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "kevin51jiang/ic-light:c5089f92aa1ecf8cd879e8348cb6a4825decdca7d637b158871011c01cf48b06",
  {
    input: {
      cfg: 2,
      steps: 25,
      width: 512,
      height: 640,
      prompt: "Woman, detailed face, sci-fi RGB glowing, cyberpunk",
      light_source: "None",
      highres_scale: 1.5,
      output_format: "webp",
      subject_image: "https://replicate.delivery/pbxt/LKArbc3pT7J4HBp4avXse2pa7bLbSBjweKjCPGx2CRc7KOZn/i3.png",
      lowres_denoise: 0.9,
      output_quality: 100,
      appended_prompt: "best quality",
      highres_denoise: 0.5,
      negative_prompt: "lowres, bad anatomy, bad hands, cropped, worst quality",
      number_of_images: 1
    }
  }
);

// 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 kevin51jiang/ic-light using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "kevin51jiang/ic-light:c5089f92aa1ecf8cd879e8348cb6a4825decdca7d637b158871011c01cf48b06",
    input={
        "cfg": 2,
        "steps": 25,
        "width": 512,
        "height": 640,
        "prompt": "Woman, detailed face, sci-fi RGB glowing, cyberpunk",
        "light_source": "None",
        "highres_scale": 1.5,
        "output_format": "webp",
        "subject_image": "https://replicate.delivery/pbxt/LKArbc3pT7J4HBp4avXse2pa7bLbSBjweKjCPGx2CRc7KOZn/i3.png",
        "lowres_denoise": 0.9,
        "output_quality": 100,
        "appended_prompt": "best quality",
        "highres_denoise": 0.5,
        "negative_prompt": "lowres, bad anatomy, bad hands, cropped, worst quality",
        "number_of_images": 1
    }
)
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 kevin51jiang/ic-light 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": "kevin51jiang/ic-light:c5089f92aa1ecf8cd879e8348cb6a4825decdca7d637b158871011c01cf48b06",
    "input": {
      "cfg": 2,
      "steps": 25,
      "width": 512,
      "height": 640,
      "prompt": "Woman, detailed face, sci-fi RGB glowing, cyberpunk",
      "light_source": "None",
      "highres_scale": 1.5,
      "output_format": "webp",
      "subject_image": "https://replicate.delivery/pbxt/LKArbc3pT7J4HBp4avXse2pa7bLbSBjweKjCPGx2CRc7KOZn/i3.png",
      "lowres_denoise": 0.9,
      "output_quality": 100,
      "appended_prompt": "best quality",
      "highres_denoise": 0.5,
      "negative_prompt": "lowres, bad anatomy, bad hands, cropped, worst quality",
      "number_of_images": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-07-24T14:23:05.646901Z",
  "created_at": "2024-07-24T14:22:59.376000Z",
  "data_removed": false,
  "error": null,
  "id": "t95ckx5q61rgj0cgwmfrqvte7r",
  "input": {
    "cfg": 2,
    "steps": 25,
    "width": 512,
    "height": 640,
    "prompt": "Woman, detailed face, sci-fi RGB glowing, cyberpunk",
    "light_source": "None",
    "highres_scale": 1.5,
    "output_format": "webp",
    "subject_image": "https://replicate.delivery/pbxt/LKArbc3pT7J4HBp4avXse2pa7bLbSBjweKjCPGx2CRc7KOZn/i3.png",
    "lowres_denoise": 0.9,
    "output_quality": 100,
    "appended_prompt": "best quality",
    "highres_denoise": 0.5,
    "negative_prompt": "lowres, bad anatomy, bad hands, cropped, worst quality",
    "number_of_images": 1
  },
  "logs": "Using seed: 6885\n[!] (<class 'cog.types.Path'>) input_fg=/tmp/tmp3lwup1pxi3.png\n[!] (<class 'str'>) prompt=Woman, detailed face, sci-fi RGB glowing, cyberpunk\n[!] (<class 'int'>) image_width=512\n[!] (<class 'int'>) image_height=640\n[!] (<class 'int'>) num_samples=1\n[!] (<class 'int'>) seed=6885\n[!] (<class 'int'>) steps=25\n[!] (<class 'str'>) a_prompt=best quality\n[!] (<class 'str'>) n_prompt=lowres, bad anatomy, bad hands, cropped, worst quality\n[!] (<class 'float'>) cfg=2.0\n[!] (<class 'float'>) highres_scale=1.5\n[!] (<class 'float'>) highres_denoise=0.5\n[!] (<class 'float'>) lowres_denoise=0.9\n[!] (<class 'str'>) bg_source=None\n  0%|          | 0/25 [00:00<?, ?it/s]\n 12%|█▏        | 3/25 [00:00<00:00, 25.66it/s]\n 24%|██▍       | 6/25 [00:00<00:00, 23.99it/s]\n 36%|███▌      | 9/25 [00:00<00:00, 23.09it/s]\n 48%|████▊     | 12/25 [00:00<00:00, 22.67it/s]\n 60%|██████    | 15/25 [00:00<00:00, 22.47it/s]\n 72%|███████▏  | 18/25 [00:00<00:00, 22.32it/s]\n 84%|████████▍ | 21/25 [00:00<00:00, 22.23it/s]\n 96%|█████████▌| 24/25 [00:01<00:00, 22.18it/s]\n100%|██████████| 25/25 [00:01<00:00, 22.55it/s]\n  0%|          | 0/25 [00:00<?, ?it/s]\n  8%|▊         | 2/25 [00:00<00:01, 15.14it/s]\n 16%|█▌        | 4/25 [00:00<00:01, 11.09it/s]\n 24%|██▍       | 6/25 [00:00<00:01, 10.20it/s]\n 32%|███▏      | 8/25 [00:00<00:01,  9.83it/s]\n 40%|████      | 10/25 [00:00<00:01,  9.67it/s]\n 44%|████▍     | 11/25 [00:01<00:01,  9.61it/s]\n 48%|████▊     | 12/25 [00:01<00:01,  9.56it/s]\n 52%|█████▏    | 13/25 [00:01<00:01,  9.52it/s]\n 56%|█████▌    | 14/25 [00:01<00:01,  9.49it/s]\n 60%|██████    | 15/25 [00:01<00:01,  9.46it/s]\n 64%|██████▍   | 16/25 [00:01<00:00,  9.45it/s]\n 68%|██████▊   | 17/25 [00:01<00:00,  9.42it/s]\n 72%|███████▏  | 18/25 [00:01<00:00,  9.41it/s]\n 76%|███████▌  | 19/25 [00:01<00:00,  9.40it/s]\n 80%|████████  | 20/25 [00:02<00:00,  9.40it/s]\n 84%|████████▍ | 21/25 [00:02<00:00,  9.39it/s]\n 88%|████████▊ | 22/25 [00:02<00:00,  9.39it/s]\n 92%|█████████▏| 23/25 [00:02<00:00,  9.38it/s]\n 96%|█████████▌| 24/25 [00:02<00:00,  9.37it/s]\n100%|██████████| 25/25 [00:02<00:00,  9.39it/s]\n100%|██████████| 25/25 [00:02<00:00,  9.66it/s]\n[~] Saving to output_images/generated_0.webp...\n[~] Output format: WEBP\n[~] Output quality: 100",
  "metrics": {
    "predict_time": 6.174926,
    "total_time": 6.270901
  },
  "output": [
    "https://replicate.delivery/pbxt/kXQmQxQdCvpsJNKEXMiD1u9Z0qWY4thbfakFNtarQ5bkA2lJA/generated_0.webp"
  ],
  "started_at": "2024-07-24T14:22:59.471975Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/t95ckx5q61rgj0cgwmfrqvte7r",
    "cancel": "https://api.replicate.com/v1/predictions/t95ckx5q61rgj0cgwmfrqvte7r/cancel"
  },
  "version": "c5089f92aa1ecf8cd879e8348cb6a4825decdca7d637b158871011c01cf48b06"
}

Generated in

6.2 seconds

Tweak it ShareReport

Using seed: 6885
[!] (<class 'cog.types.Path'>) input_fg=/tmp/tmp3lwup1pxi3.png
[!] (<class 'str'>) prompt=Woman, detailed face, sci-fi RGB glowing, cyberpunk
[!] (<class 'int'>) image_width=512
[!] (<class 'int'>) image_height=640
[!] (<class 'int'>) num_samples=1
[!] (<class 'int'>) seed=6885
[!] (<class 'int'>) steps=25
[!] (<class 'str'>) a_prompt=best quality
[!] (<class 'str'>) n_prompt=lowres, bad anatomy, bad hands, cropped, worst quality
[!] (<class 'float'>) cfg=2.0
[!] (<class 'float'>) highres_scale=1.5
[!] (<class 'float'>) highres_denoise=0.5
[!] (<class 'float'>) lowres_denoise=0.9
[!] (<class 'str'>) bg_source=None
  0%|          | 0/25 [00:00<?, ?it/s]
 12%|█▏        | 3/25 [00:00<00:00, 25.66it/s]
 24%|██▍       | 6/25 [00:00<00:00, 23.99it/s]
 36%|███▌      | 9/25 [00:00<00:00, 23.09it/s]
 48%|████▊     | 12/25 [00:00<00:00, 22.67it/s]
 60%|██████    | 15/25 [00:00<00:00, 22.47it/s]
 72%|███████▏  | 18/25 [00:00<00:00, 22.32it/s]
 84%|████████▍ | 21/25 [00:00<00:00, 22.23it/s]
 96%|█████████▌| 24/25 [00:01<00:00, 22.18it/s]
100%|██████████| 25/25 [00:01<00:00, 22.55it/s]
  0%|          | 0/25 [00:00<?, ?it/s]
  8%|▊         | 2/25 [00:00<00:01, 15.14it/s]
 16%|█▌        | 4/25 [00:00<00:01, 11.09it/s]
 24%|██▍       | 6/25 [00:00<00:01, 10.20it/s]
 32%|███▏      | 8/25 [00:00<00:01,  9.83it/s]
 40%|████      | 10/25 [00:00<00:01,  9.67it/s]
 44%|████▍     | 11/25 [00:01<00:01,  9.61it/s]
 48%|████▊     | 12/25 [00:01<00:01,  9.56it/s]
 52%|█████▏    | 13/25 [00:01<00:01,  9.52it/s]
 56%|█████▌    | 14/25 [00:01<00:01,  9.49it/s]
 60%|██████    | 15/25 [00:01<00:01,  9.46it/s]
 64%|██████▍   | 16/25 [00:01<00:00,  9.45it/s]
 68%|██████▊   | 17/25 [00:01<00:00,  9.42it/s]
 72%|███████▏  | 18/25 [00:01<00:00,  9.41it/s]
 76%|███████▌  | 19/25 [00:01<00:00,  9.40it/s]
 80%|████████  | 20/25 [00:02<00:00,  9.40it/s]
 84%|████████▍ | 21/25 [00:02<00:00,  9.39it/s]
 88%|████████▊ | 22/25 [00:02<00:00,  9.39it/s]
 92%|█████████▏| 23/25 [00:02<00:00,  9.38it/s]
 96%|█████████▌| 24/25 [00:02<00:00,  9.37it/s]
100%|██████████| 25/25 [00:02<00:00,  9.39it/s]
100%|██████████| 25/25 [00:02<00:00,  9.66it/s]
[~] Saving to output_images/generated_0.webp...
[~] Output format: WEBP
[~] Output quality: 100