库名称: diffusers
流程标签: 文本生成图像

该模型已通过Diffusers库推送至Hub平台：

• 代码库: https://github.com/Huage001/LinFusion
• 论文: https://huggingface.co/papers/2409.02097

• LinFusion基础用法:

from diffusers import AutoPipelineForText2Image  
import torch  

from src.linfusion import LinFusion  
from src.tools import seed_everything  

sd_repo = "Lykon/dreamshaper-8"  

pipeline = AutoPipelineForText2Image.from_pretrained(  
    sd_repo, torch_dtype=torch.float16, variant="fp16"  
).to(torch.device("cuda"))  

linfusion = LinFusion.construct_for(pipeline)  

seed_everything(123)  
image = pipeline(  
    "一名宇航员漂浮在太空中。背景是繁星与宇宙的壮丽景象。"  
).images[0]