---
license: other
library_name: diffusers
pipeline_tag: image-to-image
base_model: stabilityai/sd-turbo
tags:
  - image-restoration
  - novel-view-synthesis
  - 3d-gaussian-splatting
  - dualdiff3d
---

# DualDiff

Official DualDiff repair checkpoint for
[DualDiff3D](https://github.com/Akaneqwq/DualDiff3D).

DualDiff repairs a degraded novel-view rendering using its structure together
with the appearance of a nearby reference image.

## Usage

The DualDiff3D code downloads this checkpoint automatically:

```bash
python -m DualDiff.hub
```

Run image-pair inference:

```bash
python DualDiff/infer.py \
  --input_image /path/to/degraded_render.png \
  --ref_image /path/to/reference.png \
  --output_dir outputs/repair
```

The checkpoint contains the complete structure and appearance U-Net state
dictionaries plus the trained VAE LoRA and skip-connection parameters. It does
not contain optimizer state. The SD-Turbo VAE, text encoder, tokenizer,
scheduler, and base configuration are loaded separately by the code.

## Citation

```bibtex
@inproceedings{wang2026dualdiff3d,
  title     = {DualDiff3D: Dual Structure-Appearance Diffusion
               Priors for Reliability-Enhanced 3D Gaussian Splatting},
  author    = {Qian Wang and Yu Wang and Weiqi Li and Xinhua Cheng
               and Xiandong Meng and Ronggang Wang and Jian Zhang},
  booktitle = {European Conference on Computer Vision (ECCV)},
  year      = {2026}
}
```

## License

The DualDiff code is released under Apache-2.0. This checkpoint is derived from
[SD-Turbo](https://huggingface.co/stabilityai/sd-turbo); use of the checkpoint
is also subject to the applicable SD-Turbo model license.