Mean Flow Distillation: Robust and Stable Distillation for Flow Matching Models
Paper • 2606.11155 • Published
How to use congruency/MOSS-Image-Turbo-MFD with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("congruency/MOSS-Image-Turbo-MFD", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Unofficial Research Turbo LoRA for MOSS-Image using Mean Flow Distillation
MOSS-Image-Base-Turbo-MFD-v0.1 - 50 aux/20 student, 4-6 steps inference
MOSS-Image-SFT-Turbo-MFD-v0.1 - 50 aux/20 student, 4-6 steps inference
ComfyUI version is .comfy.safetensors
Apache 2.0 License
Thank you HuggingFace, OpenMOSS Team, and An Zhao and Shengyuan Zhang and Zhongjian Sun and Yixiang Zhou and Zejian Li and Ling Yang and Tianrun Chen and Lingyun Sun
@misc{mossimage2026,
title = {MOSS-Image},
author = {{OpenMOSS Team}},
year = {2026},
howpublished = {\url{https://github.com/OpenMOSS/MOSS-Image}}
}
@misc{zhao2026MeanFlowDistillation,
title={Mean Flow Distillation: Robust and Stable Distillation for Flow Matching Models},
author={An Zhao and Shengyuan Zhang and Zhongjian Sun and Yixiang Zhou and Zejian Li and Ling Yang and Tianrun Chen and Lingyun Sun},
year={2026},
eprint={2606.11155},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2606.11155},
}
Base model
OpenMOSS-Team/MOSS-Image-Base