---
license: mit
base_model: microsoft/TRELLIS-image-large
pipeline_tag: image-to-3d
tags:
  - image-to-3d
  - 3d-generation
  - scene-generation
  - real-to-sim
---

# IScene

IScene is a segmentation-conditioned 3D scene generation model. This Hugging Face repository hosts the `IScene-v1` checkpoint package for IScene inference.

## Links

- Project: https://luling06.github.io/I-Scene-project/
- Code: https://github.com/LuLing06/I-Scene-project
- Model: https://huggingface.co/LuLing/IScene

## Contents

- `iscene_config.json`: public release metadata and checkpoint layout.
- `config.yml`: inference-only architecture configuration.
- `ckpts/iscene_denoiser.pt`: IScene denoiser checkpoint.
- `ckpts/iscene_image_conditioner.pt`: IScene image-conditioner checkpoint.

## Usage

The public IScene code should load this package with:

```python
from iscene.inference.inferencer import ISceneInferencer

inferencer = ISceneInferencer.from_pretrained("LuLing/IScene")
```

For local testing before uploading to Hugging Face:

```python
inferencer = ISceneInferencer.from_pretrained("release_hf/IScene-v1")
```

## Notes

- This package contains only the IScene release checkpoint files, not historical training logs or experimental checkpoints.
- The IScene code loads the base model from `microsoft/TRELLIS-image-large` unless an equivalent local mirror is provided.

## Attribution

IScene builds on the TRELLIS image-to-3D backbone and uses `microsoft/TRELLIS-image-large` as the base model. Please preserve upstream TRELLIS attribution and license terms when redistributing derived code or model packages.

## License

This model package is prepared for release under the MIT License.