Noise-Started One-Step Real-World Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement
Paper • 2605.09328 • Published
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]Noise-Started One-Step Real-World Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement
Wei Zhu1 Kai Zhang2,* Yu Zheng1 Lei Luo1 Yong Guo3 Jian Yang1,2,*
1Nanjing University of Science and Technology 2Nanjing University 3Huawei
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support