Split an image into editable foreground and background layers
Open this ready-to-run workflow on Floyo. No install needed.
HOW IT WORKS
Step 1. Upload your image. A photo with a clear subject in front of a readable background gives the cleanest split. Works great with: portraits · product shots · characters · scenes with obvious depth
Step 2. Hit run. No prompt needed. Qwen Image Layered reads the scene and pulls it apart on its own. The default is a two-layer split, one foreground and one background.
Step 3. Download your layers. You get three images back: the original, the background on its own, and the foreground on its own. Preview them in the workflow, then download. Ready for: Photoshop · After Effects · Figma · any editor
First time? Leave every setting as-is. The defaults (two layers · speed LoRA loaded · square working size) are the right starting point for almost any image. Want more pieces? Raise the layer count and step the layer index to pull each one out.
Overview
This workflow takes a flat image and splits it into separate, editable layers using Qwen Image Layered. You upload one photo and get three images back: the original composite, the background by itself, and the foreground by itself. The background comes back filled in where the subject used to be, so you get a clean plate to reuse, not an image with a hole in it. No prompt needed. A speed LoRA keeps runs quick, so each split comes back in about 80 seconds. No setup, no nodes to wire.
Who it's for: creators, VFX artists, and product teams who want true separated layers in ComfyUI without wiring the nodes from scratch. Not for: a quick one-off cutout. A plain background remover is faster if all you want is a transparent PNG. This earns its place when you want layers you can keep editing.
Why Floyo
Floyo is the only ComfyUI platform built for teams in the browser.
Made for teams. Share run history, files, and models across your whole team. A teammate opens your exact run and picks up where you left off. No file handoffs, no version confusion.
No install, no setup. Every workflow and model is preloaded. Open it in your browser and run. Nothing to download, nothing to configure.
No local hardware. Workflows run on H100 NVL GPUs, so heavy models run fast without a card of your own. Your VRAM stops being the limit.
Open and closed models in one place. Floyo runs open-source workflows and API models side by side.
How to use (in your browser on Floyo)
Upload the image you want to split.
Hit run. No prompt needed. Raise the layer count first if you want more than two layers.
Download the foreground, background, and original, ready for any editor.
Expectations The models are preloaded, so there is nothing to download. Running it needs a free Floyo account. Each split comes back in about 80 seconds. The default two-layer split gives you a foreground and a background automatically. For more layers, raise the count and change the layer index to pull each one out. One limit to know: images with a clear front and back separate cleanly, while flat scenes with no obvious depth are harder for the model to pull apart.
Use Cases
Background Swaps. Lift the subject off its background and drop it onto a new one, no manual masking.
Product & E-commerce. Put one product shot on five different backdrops from a single upload.
VFX & Compositing. Get real layers to relight, blur for depth, or paint behind the subject.
Concept & Scene Rebuilds. Take a scene apart and reassemble it piece by piece, front to back.
What can Qwen Image Layered pull apart?