| --- |
| tags: |
| - diffusion |
| - image-decomposition |
| - rgba |
| - layered-image-editing |
| --- |
| |
| # SynLayers Stage 2 |
|
|
| This repository contains the Stage 2 checkpoints and runtime assets for SynLayers, our real-world image layer decomposition system. |
|
|
| The main assets in this repo are: |
|
|
| - `SynLayers_checkpoints/FLUX.1-dev` |
| - `SynLayers_checkpoints/FLUX.1-dev-Controlnet-Inpainting-Alpha` |
| - `SynLayers_ckpt/step_120000` |
| - `ckpt/trans_vae/0008000.pt` |
| - `ckpt/pre_trained_LoRA` |
| - `ckpt/prism_ft_LoRA` |
|
|
| These assets are used by the public SynLayers demo: |
| [SynLayers/synlayers](https://huggingface.co/spaces/SynLayers/synlayers) |
|
|
| The full pipeline uses: |
|
|
| 1. Stage 1 bbox + whole-caption prediction from [`SynLayers/Bbox-caption-8b`](https://huggingface.co/SynLayers/Bbox-caption-8b) |
| 2. Stage 2 layer decomposition from this repository |
|
|
| This repo is intended for the SynLayers decomposition pipeline rather than a single generic `DiffusionPipeline(prompt)` model. |
|
|
| If you want to see more details of our implementation, please check our paper: |
| [https://arxiv.org/abs/2605.15167](https://arxiv.org/abs/2605.15167) |
|
|
| If you find our work useful, please consider citing: |
|
|
| ```bibtex |
| @misc{wu2026doessyntheticlayereddesign, |
| title={Does Synthetic Layered Design Data Benefit Layered Design Decomposition?}, |
| author={Kam Man Wu and Haolin Yang and Qingyu Chen and Yihu Tang and Jingye Chen and Qifeng Chen}, |
| year={2026}, |
| eprint={2605.15167}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.CV}, |
| url={https://arxiv.org/abs/2605.15167}, |
| } |
| ``` |
|
|
