ThinkDiffusion and Stable Diffusion's ComfyUI and IC Light create amazingly beautiful and realistic lighting effects.

Achieving exceptional lighting is the key to a stunning shot—just ask any film crew’s lighting department. With IC Light, paired with the robust capabilities of ComfyUI, users can create lighting adjustments with the precision and quality of professional setups.

Unlike typical photo editors, this AI-powered technique applies lighting that realistically interacts with objects, contours, and shapes within the scene, enhancing depth and realism. In this guide, we’ll walk you through how to harness IC Light and ComfyUI for seamless, high-quality lighting effects using a prompt and workflow.

We'd like to credit CGTopTips for their knowledge of the IC Light Workflow!

How to Use IC Light in ComfyUI

One-Time Setup

💡
Download the workflow and drag & drop it into your ComfyUI window, whether locally or on ThinkDiffusion. If you're using ThinkDiffusion, it's necessary to use at minimum the Turbo 24gb machine, but we do recommend the Ultra 48gb machine.

Custom Node

If there are red nodes in the workflow, it means that the workflow lacks the certain required nodes. Install the custom nodes in order for the workflow to work.

  1. Go to ComfyUI Manager  > Click Install Missing Custom Nodes
  1. Check the list below if there's a list of custom nodes that needs to be installed and click the install.

Models

Download the recommended models (see list below) using the ComfyUI manager and go to Install models. Refresh or restart the machine after the files have downloaded.

  1. Go to ComfyUI Manager  > Click Install Models
  1. When you find the exact model that you're looking for, click install and make sure to press refresh when you are finished.

Model Path Source

Use the model path source if you prefer to install the models using model's link address and paste into ThinkDiffusion MyFiles using upload by URL.

Model Name Model Link Address
epicrealism_naturalSin.safetensors
📋 Copy Path
iclight_sd15_fc_unet_ldm.safetensors
📋 Copy Path
model.pth
📋 Copy Path

Guide Table for Upload

Recommended Models

Node’s Value Name

Node

ThinkDiffusion Upload File Directory

epicrealism_naturalSin.safetensors

ckpt_name

Load Checkpoint

…comfyui/models/checkpoint/

iclight_sd15_fc_unet_ldm.safetensors

model_path

Load and Apply IC-Light

…comfyui/models/unet/

model.pth

rmbgmodel

🧹BRIA_RMBG Model Loader

…comfyui/models/rembg/

Reminder
💡
If the /rembg folder doesn't exist in the models directory of ThinkDiffusion, create a new folder and name it with rembg and upload the model.pth in it.

Procedures

Now that the hard work is out of the way, let's get creative. You need to follow the steps from top to bottom. The workflow is a one-click process after everything has been set up.

Steps Default Nodes
Load an Image ThinkDiffusion-StableDiffusion-ComfyUI-IC-Light-load-an-image.png
Set the Image Size ThinkDiffusion-StableDiffusion-ComfyUI-IC-Light-image-resize.png
Set the Relighting Shape and Location ThinkDiffusion-StableDiffusion-ComfyUI-IC-Light-set-the-shape-mask.png
Write a Prompt ThinkDiffusion-StableDiffusion-ComfyUI-IC-Light-write-a-prompt.png
Set the Models ThinkDiffusion-StableDiffusion-ComfyUI-IC-Light-set-the-models.png
Set the Generation Settings ThinkDiffusion-StableDiffusion-ComfyUI-IC-Light-check-the-ksampler.png
Check the Output Image and Adjust your Preferred Lighting Settings ThinkDiffusion-StableDiffusion-ComfyUI-IC-Light-check-the-output.png
💡
location x & y is the position of shape mask. Check the preview map to check the location of mask.
x means horizontal movement
y means vertical movement
💡
After the generation preview appears, you can adjust only the ff:

-blur sigma (default 1)
-ic light multiplier (default 0.182)
-brightness (default 1)
-contrast (default 1)
-saturation (default 1)

IC Light Examples

Detailed Ball

Prompt: orange ball, light from left window, basketball floor

Seed - 113881076738147

steps - 30, cfg - 2, denoise - 1, dpmpp_2m_sde, karras

Blur Sigma - 1.25

Light Multiplier - 0.200

Light location - x - 100 , y - 200

Brightness / Contrast / Saturation - 1.5 / 1.5 / 1

Detailed Book

Prompt: book, light from right, placed at wooden table

Seed - 209876273013979

steps - 30, cfg - 2, denoise - 1, dpmpp_2m_sde, karras

Blur Sigma - 1.25

Light Multiplier - 0.182

Light location - x - 600, y - 200

Brightness / Contrast / Saturation - 1.5 / 1 / 1

Detailed Cat

Prompt: white cat, light from left, city street background

Seed - 780951914447608

steps - 30, cfg - 2, denoise - 1, dpmpp_2m_sde, karras

Blur Sigma - 1.25

Light Multiplier - 0.182

Light location - x - 100, y - 200

Brightness / Contrast / Saturation - 1.5 / 1 / 1

Detailed Shoes

Prompt: shoes, afternoon, forest floor background

Seed - 711521066701579

steps - 30, cfg - 2, denoise - 1, dpmpp_2m_sde, karras

Blur Sigma - 1.25

Light Multiplier - 0.2

Light location - x - 600, y - 200

Brightness / Contrast / Saturation - 1.5 / 1 / 1

Any of our workflows including the above can run on a local version of SD but if you’re having issues with installation or slow hardware, you can try any of these workflows on a more powerful GPU in your browser with ThinkDiffusion.

If you are feeling inspired and want to learn about LoRA's then check out this ultimate guide to LoRA's in ComfyUI Here.