layerdifforg/seethroughv0.0.1_marigold

See-through: Marigold Depth

The pseudo-depth model of See-through, fine-tuned from Marigold Depth v1.1 for anime characters. It is used together with the LayerDiff 3D model to order the decomposed layers. Read our GitHub repository for usage and details.

A 4-bit NF4 version for GPUs with less memory is available at 24yearsold/seethroughv0.0.1_marigold_nf4.

Licence

The See-through code is licensed under Apache-2.0. These weights are released under Apache-2.0 for our own contributions, and they also inherit the licences of the models they are derived from:

• Marigold Depth v1.1 (PRS, ETH Zürich): Open RAIL++-M License
• Stable Diffusion 2 (Stability AI), the base model of Marigold: CreativeML Open RAIL++-M License. The use restrictions in its Attachment A are the ones that apply to these weights, since the Open RAIL++-M text published for Marigold leaves its own list as a placeholder.

Commercial use is permitted. The use-based restrictions in paragraph 5 and Attachment A of the Open RAIL licences apply to every use of these weights. If you distribute the weights or a derivative of them, or host them as a service, you must include those restrictions as an enforceable provision in the terms that govern that use, and tell your users about them.

The license field above reads openrail++ because that licence sets the conditions of use; our Apache-2.0 grant applies on top of it. See LICENSE for the full terms and NOTICE for attributions and the changes we made.

Citation

If you find this work useful, please cite:

@inproceedings{lin2026seethrough,
  author={Lin, Jian and Li, Chengze and Qin, Haoyun and Chan, Kwun Wang and Jin, Yanghua and Liu, Hanyuan and Choy, Stephen Chun Wang and Liu, Xueting},
  title={See-through: Single-image Layer Decomposition for Anime Characters},
  booktitle={Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers},
  series={SIGGRAPH Conference Papers '26},
  publisher={Association for Computing Machinery},
  address={New York, NY, USA},
  year={2026},
  pages={1--11},
  doi={10.1145/3799902.3811209},
  url={https://doi.org/10.1145/3799902.3811209}
}