This lora trained with T2ITrainer https://github.com/lrzjason/T2ITrainer
Used 20 pairs data. Cloth image as reference and target is nano-banana generated images.
Caption dropout 0.5. It is quite strong and blended the model image into lora. But it could use it without prompt.
Description
FAQ
Comments (8)
How does it work? is it possible to carry any clothes with this laura, or the ones in the screenshots ?
What is the trigger word to transfer any clothes?
No, just weight 1. If you want to more accurate, you could descript the model and the clothes
@xiaozhijason I don't understand, can I use my own clothes with the help of this laura? or just what 's sewn into it?
@soyv4 Just try it. The input image could be any clothes images with white background. But I am not 100% sure if it could achieve the result you wanted.
It makes my image like pink. Is it not compatible with the lightning loras?
This lora is experiment and trained on original edit.