Qwen-Image-Layered is an open-weight image model from the Qwen team that decomposes one image into several RGBA layers, so each part can be moved, resized or recoloured on its own. Its weights were released on December 19, 2025 under the Apache 2.0 licence, and it runs on your own GPU.
Disclosure: this page is published by LayerGrab, a hosted tool that also splits images into layers. Facts about the model come from its own documentation, linked at the bottom and checked on 2026-09-29.
Last updated 2026-09-29
It is easy to assume you can type “separate the logo” and get the logo. The README says otherwise: the prompt describes the whole image, including parts that may be hidden, and is not meant to control which content ends up on which layer.
What you control is the number of layers. If you need one particular element out of a picture, a tool that takes an instruction, such as separating one named object, fits better.
| Qwen-Image-Layered | LayerGrab | |
|---|---|---|
| Cost | Free weights; you pay for your own GPU time | Credits per layer returned; samples free without an account |
| Setup | Python, a CUDA GPU with enough memory for a 20B model | Browser, or the Photoshop, Figma, Sketch and Chrome plugins |
| How many layers | You set the number before running | The model decides from the picture, up to 17 including the background |
| Choosing what to separate | Not what the prompt is for (see README) | Name it, e.g. "only the price tag", and get just that |
| Layer names and positions | Not documented | Each layer named in English, with its position in the image |
| Output | RGBA images, PPTX export | PNG, ZIP, layered PSD, or layers placed straight into your design |
| Where it runs | On your machine; images never leave it | On LayerGrab servers; results kept 30 days |
You have a suitable GPU, want images to stay on your own machine, are building layer decomposition into your own pipeline, or are doing research. It costs nothing per image once it runs.
You want layers without setting up a model, need to name the one element you want, or want the layers placed in Photoshop, Figma or Sketch. It is not the right choice if images must never leave your machine.
The weights are free to download under Apache 2.0, which allows commercial use. Running the model is not free in practice: it has 20B parameters and needs a CUDA GPU, so you pay for the hardware or cloud GPU time. The free online demo has a daily GPU quota; the free options page compares each way to run it.
Not directly. Its README says the text prompt describes the overall content of the image and is not designed to control what goes into each layer. You choose how many layers to produce instead.
The main LayerGrab tool runs a different hosted model; this page compares the two. LayerGrab also runs Qwen-Image-Layered itself on its free-to-try page, where a 2-layer split is free once per account.
Yes. The README links an online demo on Hugging Face Spaces and ModelScope Studio, available since December 22, 2025.