To further improve the lora, you could post original image, edited image on the gralley which I could download the images and add those to the training set.
This lora is to adjust pixels shift and color shift from removal task.
Due to the training set limitation, the alpha version might have less strength on some remove task than original qwen edit 2509.
Adjust the lora strength if original model perform better than added lora.
It is recommanded to use with strength between 0.5 ~1.0
RH workflow:
qwen edit simple remover
Online link：https://www.runninghub.ai/post/1977359768337698818/?inviteCode=rh-v1279
Contact
Wechat ID: fkdeai
QQ Group: 866612947
Email: [email protected]