Instructions to use W-Shuoyan/OSDEnhancer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use W-Shuoyan/OSDEnhancer with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("W-Shuoyan/OSDEnhancer", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# [OSDEnhancer] Taming Real-World Space-Time Video Super-Resolution with One-Step Diffusion (arXiv 2026)
|
| 2 |
|
| 3 |
**Authors**: [Shuoyan Wei](https://github.com/W-Shuoyan)<sup>1</sup>, [Feng Li](https://lifengcs.github.io/)<sup>2,\*</sup>, Chen Zhou<sup>1</sup>, [Runmin Cong](https://rmcong.github.io)<sup>3</sup>, [Yao Zhao](https://scholar.google.com/citations?user=474TbQYAAAAJ&hl=en&oi=ao)<sup>1</sup>, [Huihui Bai](https://scholar.google.com/citations?user=iXuCUcQAAAAJ&hl=en&oi=ao)<sup>1</sup>
|
|
@@ -98,4 +105,4 @@ If you find this work useful for your research, please consider citing our paper
|
|
| 98 |
|
| 99 |
## 📕 License & Acknowledgement
|
| 100 |
|
| 101 |
-
This project is released under the Apache License 2.0. OSDEnhancer is built upon [CogVideoX](https://github.com/zai-org/CogVideo). We also sincerely thank the authors of [DOVE](https://github.com/zhengchen1999/DOVE), [EvEnhancer](https://github.com/W-Shuoyan/EvEnhancer), and [RealBasicVSR](https://github.com/ckkelvinchan/realbasicvsr) for their excellent open-source implementations, which provided valuable references for this project.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model:
|
| 4 |
+
- zai-org/CogVideoX1.5-5B
|
| 5 |
+
pipeline_tag: video-to-video
|
| 6 |
+
library_name: diffusers
|
| 7 |
+
---
|
| 8 |
# [OSDEnhancer] Taming Real-World Space-Time Video Super-Resolution with One-Step Diffusion (arXiv 2026)
|
| 9 |
|
| 10 |
**Authors**: [Shuoyan Wei](https://github.com/W-Shuoyan)<sup>1</sup>, [Feng Li](https://lifengcs.github.io/)<sup>2,\*</sup>, Chen Zhou<sup>1</sup>, [Runmin Cong](https://rmcong.github.io)<sup>3</sup>, [Yao Zhao](https://scholar.google.com/citations?user=474TbQYAAAAJ&hl=en&oi=ao)<sup>1</sup>, [Huihui Bai](https://scholar.google.com/citations?user=iXuCUcQAAAAJ&hl=en&oi=ao)<sup>1</sup>
|
|
|
|
| 105 |
|
| 106 |
## 📕 License & Acknowledgement
|
| 107 |
|
| 108 |
+
This project is released under the Apache License 2.0. OSDEnhancer is built upon [CogVideoX](https://github.com/zai-org/CogVideo). We also sincerely thank the authors of [DOVE](https://github.com/zhengchen1999/DOVE), [EvEnhancer](https://github.com/W-Shuoyan/EvEnhancer), and [RealBasicVSR](https://github.com/ckkelvinchan/realbasicvsr) for their excellent open-source implementations, which provided valuable references for this project.
|