mindspore-lab / mindone

one for all, Optimal generator with No Exception
https://mindspore-lab.github.io/mindone/
Apache License 2.0
352 stars 66 forks source link

[SDXL] 训练初始化慢,推理加载模型慢 #148

Open boomfh opened 12 months ago

boomfh commented 12 months ago

Thanks for sending an issue! Here are some tips for you:

If this is your first time, please read our contributor guidelines: https://github.com/mindspore-ai/mindspore/blob/master/CONTRIBUTING.md

Hardware Environment | 硬件环境

Software Environment | 软件环境

Describe the current behavior | 目前输出

e.g. the current output is xxx/ the error is xxx/ 目前的输出是xx 、 目前的报错是关于xx

训练的train.py卡在loss = train_step_fn(data)一个小时

Describe the expected behavior | 期望输出

please describe expected outputs or functions you want to have: 请告诉我们您期望得到的结果或功能

训练速度加快 在线推理加载的模型时间需要优化一下,会切换模型使用,加载模型时间太久了。【模型加载花了120秒,文本embedding花了46秒,sample花了721秒】

Steps to reproduce the issue | 复现报错的步骤

https://github.com/mindspore-lab/mindone/blob/master/examples/stable_diffusion_xl/GETTING_STARTED.md

Related log / screenshot | 完整日志

Special notes for this issue | 其他信息

zhanghuiyao commented 11 months ago

首次加载需要进行图编译和模型权重加载,可以尝试使用推荐的 streamlit 客户端启动方式进行图像生成,这个可以连续生成图像

HPL123 commented 8 months ago

请问3090显卡可以训练么?

zhanghuiyao commented 7 months ago

请问3090显卡可以训练么?

3090估计会显存不足