Improve model card: Add `library_name` and structure content (#1)

- Improve model card: Add `library_name` and structure content (ecb2bd440cd8aadeb3fc9b02ab35bcb068b35c55)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

README.md

@@ -1,12 +1,28 @@
 ---
-license: apache-2.0
 base_model:
 - stabilityai/stable-diffusion-2-1
+license: apache-2.0
 pipeline_tag: image-to-image
+library_name: diffusers
 ---
 
-**Abstract:** Pretrained latent diffusion models have shown strong potential for lossy image compression, owing to their powerful generative priors. Most existing diffusion-based methods reconstruct images by iteratively denoising from random noise, guided by compressed latent representations. While these approaches have achieved high reconstruction quality, their multi-step sampling process incurs substantial computational overhead. Moreover, they typically require training separate models for different compression bit-rates, leading to significant training and storage costs. To address these challenges, we propose a **o**ne-**s**tep diffusion **c**odec **a**cross multiple bit-**r**ates. termed OSCAR. Specifically, our method views compressed latents as noisy variants of the original latents, where the level of distortion depends on the bit-rate. This perspective allows them to be modeled as intermediate states along a diffusion trajectory. By establishing a mapping from the compression bit-rate to a pseudo diffusion timestep, we condition a single generative model to support reconstructions at multiple bit-rates. Meanwhile, we argue that the compressed latents retain rich structural information, thereby making one-step denoising feasible. Thus, OSCAR replaces iterative sampling with a single denoising pass, significantly improving inference efficiency. Extensive experiments demonstrate that OSCAR achieves superior performance in both quantitative and visual quality metrics.
+# OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates
+
+## Abstract
+Pretrained latent diffusion models have shown strong potential for lossy image compression, owing to their powerful generative priors. Most existing diffusion-based methods reconstruct images by iteratively denoising from random noise, guided by compressed latent representations. While these approaches have achieved high reconstruction quality, their multi-step sampling process incurs substantial computational overhead. Moreover, they typically require training separate models for different compression bit-rates, leading to significant training and storage costs. To address these challenges, we propose a one-step diffusion codec across multiple bit-rates. termed OSCAR. Specifically, our method views compressed latents as noisy variants of the original latents, where the level of distortion depends on the bit-rate. This perspective allows them to be modeled as intermediate states along a diffusion trajectory. By establishing a mapping from the compression bit-rate to a pseudo diffusion timestep, we condition a single generative model to support reconstructions at multiple bit-rates. Meanwhile, we argue that the compressed latents retain rich structural information, thereby making one-step denoising feasible. Thus, OSCAR replaces iterative sampling with a single denoising pass, significantly improving inference efficiency. Extensive experiments demonstrate that OSCAR achieves superior performance in both quantitative and visual quality metrics.
+
+## Paper
+[OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates](https://arxiv.org/pdf/2505.16091)
 
-Github: https://github.com/jp-guo/OSCAR
+## Code
+The code is available on GitHub: [https://github.com/jp-guo/OSCAR](https://github.com/jp-guo/OSCAR)
 
-Paper: https://arxiv.org/pdf/2505.16091
+## Citation
+```bibtex
+@article{guo2025oscar,
+    title={OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates},
+    author={Guo, Jinpei and Ji, Yifei and Chen, Zheng and Liu, Kai and Liu, Min and Rao, Wang and Li, Wenbo and Guo, Yong and Zhang, Yulun},
+    journal={arXiv preprint arXiv:2505.16091},
+    year={2025}
+}
+```