One-Step Diffusion Distillation through Score Implicit Matching
Paper • 2410.16794 • Published • 2
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("maple-research-lab/SIM", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]SIM: One-Step Diffusion Distillation through Score Implicit Matching
🚀 Quick Start
please refer to https://github.com/maple-research-lab/SIM for the inference code. We are working on the integration into diffusers.
📄 Citation
@article{luo2024one,
title={One-Step Diffusion Distillation through Score Implicit Matching},
author={Luo, Weijian and Huang, Zemin and Geng, Zhengyang and Kolter, J Zico and Qi, Guo-jun},
journal={arXiv preprint arXiv:2410.16794},
year={2024}
}
- Downloads last month
- -
Model tree for maple-research-lab/SIM
Base model
PixArt-alpha/PixArt-alpha