Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

能请教一下如何训练style模型吗? #103

Open
CQxiaocaimi opened this issue Oct 25, 2023 · 1 comment
Open

能请教一下如何训练style模型吗? #103

CQxiaocaimi opened this issue Oct 25, 2023 · 1 comment

Comments

@CQxiaocaimi
Copy link

我下载了t2iadapter_style_sd14v1模型和1.4基础模型,训练时是不是也要先加载基础模型然后加载style_sd14v1,我想问一问具体训练细节,例如训练代码如何修改、数据集格式是怎样的、训练生成的样本是否能和数据集中的目标图像对应,目前我在尝试用controlnet-ip2p训练,比如说想训练真人图象到青铜人像,但发现训练样本是混乱的,生成的不是对应的目标图像(第二个epoch的生成图应该对应2epoch的目标图),我在尝试寻找一些方法,就像pix2pix-gan那样。
所以……能透露一下秘密吗?
为什么只有一个sketch的训练脚本。

@fan84sunny
Copy link

我在猜你需要的東西在 SD branch 裡面有

我也是翻了很久才看懂他的文件,如果有誤,歡迎討論

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants