LayerForge: ComfyUI node for image compositing
LayerForge is a ComfyUI node for compositing images with multiple layers, masks, blend modes, and transformations.
Verified
Core facts
Read by a script from the official API, not rewritten by a model.
- License
- MIT
- Languages
- JavaScript
- Maintainer
- Azornes
- Verified
What it is
LayerForge is a ComfyUI node for compositing images with multiple layers, masks, blend modes, and transformations. LayerForge stores canvas state in the browser's IndexedDB and returns an IMAGE plus a MASK to downstream nodes. LayerForge is based on the original Comfyui-Ycanvas by yichengup. LayerForge is licensed under the MIT License.
Main features
LayerForge stores layers, positions, masks, and other canvas data in the browser's IndexedDB so the state survives a page reload.
LayerForge can add, reorder, move, scale, and rotate multiple image layers.
LayerForge can paint masks with adjustable brush size, strength, and softness.
LayerForge offers 12 blend modes, including Overlay and Multiply, and sets opacity for each layer from the context menu.
LayerForge can add files by drag and drop, paste images or internal layer selections from the clipboard, or import the latest ComfyUI output with one click.
In its optional matting feature, LayerForge can generate a background-removal mask for a selected layer with ComfyUI's native BiRefNet loader or local BRIA RMBG 2.0.
Getting started
To install, search for Comfyui-LayerForge in ComfyUI-Manager and click the Install button.
For a manual install, clone this repo into custom_nodes.
In the polygonal lasso inpainting workflow, enable auto_refresh_after_generation on the LayerForge node.
LayerForge's polygonal inpainting selection lets you draw a closed shape for an inpainting area.
Hold Shift, press S, and left-click to place the first point.
Click the first point or click near it to close the shape.
cd ComfyUI/custom_nodes/
git clone https://github.com/Azornes/Comfyui-LayerForge.gitWho it is for
Connecting a ComfyUI Batch Image node imports multiple images as separate layers. LayerForge has an optional MASK input. The IMAGE output is the flattened composite from the visible layer stack.
The MASK output is a combined alpha mask for the visible layers. LayerForge outputs standard ComfyUI IMAGE and MASK values. The matting feature is optional and requires a model.
The BRIA RMBG 2.0 model requires the transformers package in the active ComfyUI environment. LayerForge uses ComfyUI's native loader for BiRefNet. The lite-* variants do not work with this loader.
The mask threshold in the matting settings is set from 0 to 1. With the Expand/Contract mask option enabled, the boundary is set from -300 to +300 px. With the Feather edges option enabled, the feather amount is set from 0 to 300 px.
The Extend output area option extends the output area by up to 500 px on each side without changing the custom shape. The Flux Inpainting workflow combines LayerForge with Flux fill inpainting. The simple test workflow tests the node without a model-based generation step.
If LayerForge produces a black or empty output, check the node_id.
Related tools
Related tools listed on this site.
即梦AI
An AI creative platform combining image generation, video generation, and canvas editing, starting from text or images.
PixPix
Image/video creation platform for commerce and creative teams. Its official site describes product-image sets, A+ detail pages, model try-on assets, image/video generation and editing, and an Agent workspace that breaks down creative tasks.
PixTV
AI-video and canvas-creation platform. Its primary description presents text-to-image, image-to-video, character consistency, storyboards and editing; the homepage also shows audio and text-creation entries.
DeepFloyd IF
DeepFloyd IF’s README describes cascaded text-to-image and super-resolution models, with Diffusers and notebook directions and separate code and weight licenses.
Cleanup.pictures
Online inpainting editor that removes selected objects, people, text and defects, with stated workflows for product photos and real-estate imagery.
LiblibAI·哩布哩布AI
A creative community centered on AI image models and workflows, with model sharing, online generation, and training entry points.
RunningHub
An online creative platform that brings together ComfyUI workflows, AI apps, and a canvas for generating and processing images and videos.
LiblibAI
AI image creation platform and model-sharing community whose site lists online drawing tools, downloadable models and online model training.
Genmo
The site says Genmo is developing open video world models; Mochi 1 is its open-source text-to-video model, usable online in the Playground or run locally via the open-source repository or ComfyUI.
Sources
This page is written from the official sources below. Open them to check the original text.
- GitHub READMEhttps://github.com/Azornes/Comfyui-LayerForgeFetched
Verified ·
This page is written by AI from the official sources above and checked automatically. This site has not tested it. Found a mistake? Tell us.