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:

from iscene.inference.inferencer import ISceneInferencer

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

For local testing before uploading to Hugging Face:

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.