Instructions to use zw121/SMFSR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use zw121/SMFSR with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("zw121/SMFSR", 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
| license: apache-2.0 | |
| <div align="center"> | |
| <h2>Noise-Started One-Step Real-World Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement</h2> | |
| <p> | |
| Wei Zhu<sup>1</sup> | |
| Kai Zhang<sup>2,*</sup> | |
| Yu Zheng<sup>1</sup> | |
| Lei Luo<sup>1</sup> | |
| Yong Guo<sup>3</sup> | |
| Jian Yang<sup>1,2,*</sup> | |
| </p> | |
| <p> | |
| <sup>1</sup>Nanjing University of Science and Technology | |
| <sup>2</sup>Nanjing University | |
| <sup>3</sup>Huawei | |
| </p> | |
| </div> | |
| <p align="center"> | |
| <br> | |
| <a href="https://arxiv.org/abs/2605.09328"> | |
| <img src="https://img.shields.io/badge/arXiv-2605.09328-b31b1b.svg"> | |
| </a> | |
| | |
| <a href="https://github.com/wzhu121/SMFSR"> | |
| <img src="https://img.shields.io/badge/GitHub-Code-black.svg"> | |
| </a> | |
| </p> |