#124 · Primary category: Image Generation
ComfyUI-IC-Light-Native
ComfyUI native implementation of IC-Light
Project last updated:02/25/25
GitHub Stars
648
Forks
35
Contributors
3
License
Apache-2.0
Why we included this project
ComfyUI users who want to relight a subject or drop a foreground object into a new scene with matching light can run IC-Light's models without leaving their node graph. The pack ships two UNet variants, one for generating a background around a given foreground and one for combining a foreground with a supplied background, plus a mask-grey helper that stops masked areas from darkening or washing out the result. The example workflows show the main moves: relighting from a light map, keeping the original object color by guiding generation in latent space, and pulling back high-frequency detail such as text from the source image. Since it is a native ComfyUI implementation, it plugs into the usual masking, background-removal, and resizing nodes instead of forcing you to switch tools. That makes it a practical pick for product shots, portrait relighting, and compositing where you want direct control over light direction and how the subject sits in the scene.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
stable-diffusion-webui
Stable Diffusion web UI
ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
upscayl
🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.
InvokeAI
InvokeAI is a leading open-source creative engine for Stable Diffusion, offering an industry-leading web UI for generating and editing visual media.