We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
训练了一版Lora权重,但是加载或是不加载这个权重,生成的图片是完全一样的,这是为什么,触发词也加了 pipe=FluxPipeline.from_pretrained("XXX") pipe.load_lora_weights("XXX“) image=pipe(XXX)
The text was updated successfully, but these errors were encountered:
同问!非常严重的问题
Sorry, something went wrong.
我的损失是nan,我觉得是这里的问题,你们的训练损失如何
我也是一样的问题,设置了触发词也没用,LoRA没有效果
之前1.09版本的时候 我拯救者7745HX4060训练,图片用的少,20分钟训练完效果很不错,现在1.11版本,用13900HX4070,同样图片训练设置要一两个小时,训练出来的还没有什么效果,晕死,不知道什么原因
No branches or pull requests
训练了一版Lora权重,但是加载或是不加载这个权重,生成的图片是完全一样的,这是为什么,触发词也加了
pipe=FluxPipeline.from_pretrained("XXX")
pipe.load_lora_weights("XXX“)
image=pipe(XXX)
The text was updated successfully, but these errors were encountered: