pytorch-diffusion

基于mnist手写数字数据集的stable diffusion模型复现

可以输入引导数字，生成对应数字的图片

模型效果

引导生成10张图片，分别对应数字0~9

python train.py

python lora_finetune.py

Name		Name	Last commit message	Last commit date
Latest commit History 39 Commits
refs		refs
README.md		README.md
config.py		config.py
conv_block.py		conv_block.py
cross_attn.py		cross_attn.py
dataset.py		dataset.py
denoise.py		denoise.py
diffusion.py		diffusion.py
lora.py		lora.py
lora_finetune.py		lora_finetune.py
stable-inference.png		stable-inference.png
time_position_emb.py		time_position_emb.py
train.py		train.py
unet.py		unet.py