---
license: other
license_name: license
license_link: LICENSE
pipeline_tag: image-to-image
tags:
- Image Super-resolution
- Diffusion Inversion
---

# InvSR Model Card
This model card focuses on the models associated with the InvSR project, which is available [here](https://github.com/zsyOAOA/InvSR).

## Model Details
- **Developed by:** Zongsheng Yue
- **Model type:** Arbitrary-steps Image Super-resolution via Diffusion Inversion
- **Model Description:** This is the model used in [Paper](https://arxiv.org/abs/2412.09013).
- **Resources for more information:** [GitHub Repository](https://github.com/zsyOAOA/InvSR).
- **Cite as:**

      @article{yue2024invSR,
        author    = {Zongsheng Yue, Kang Liao, Chen Change Loy},
        title     = {Arbitrary-steps Image Super-resolution via Diffusion Inversion},
        journal   = {arXiv preprint arXiv:2412.09013},
        year      = {2024},
      }

## Limitations and Bias

### Limitations

- InvSR requires a tiled operation for generating a high-resolution image, which would largely increase the inference time.
- InvSR sometimes cannot keep 100% fidelity due to its generative nature.
- InvSR sometimes cannot generate perfect details under complex real-world scenarios.

### Bias
While our model is based on a pre-trained SD-Turbo model, currently we do not observe obvious bias in generated results.

## Training

**Training Data**
The model developer used the following dataset for training the model:

- Our model is finetuned on [LSDIR](https://data.vision.ee.ethz.ch/yawli/index.html) + 20K samples from FFHQ datasets.

**Training Procedure**
InvSR achieves the goal of image super-resolution via diffusion inversion technique on [SD-Turbo](https://huggingface.co/stabilityai/sd-turbo), detailed training pipelines can be found in our GitHub [repo](https://github.com/zsyOAOA/InvSR).

We currently provide the following checkpoints:

- [noise_predictor_sd_turbo_v5.pth](https://huggingface.co/OAOA/InvSR/blob/main/noise_predictor_sd_turbo_v5.pth): Noise estimation network trained for [SD-Turbo](https://huggingface.co/stabilityai/sd-turbo).

## Evaluation Results 
See [Paper](https://arxiv.org/abs/2412.09013) for details.