# Train dreambooth ,have strange result

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftrain-dreambooth-have-strange-result%2F53100%3E%5C
**Category:** 🤗AutoTrain\
**Created:** [September 1, 2023, 9:12am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftrain-dreambooth-have-strange-result%2F53100 "2023-09-01T09:12:31Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![dreambander](https://avatars.discourse-cdn.com/v4/letter/d/cdc98d/32.png) [@dreambander](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdreambander)%5C
**Post date:** [September 1, 2023, 9:12am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftrain-dreambooth-have-strange-result%2F53100%2F1 "2023-09-01T09:12:31Z")

</div>

Hello, I trained the dreambooth according to the document, and trained the text\_encoder unet at the same time, but how could the predicted result be like this, and I urgently need help. If you don’t use unet text encoder, it can be normal a little bit, looking forward to reply

 ![264307281-aa3ab5aa-1789-4ba5-b9d2-edd9392298f1](https://us1.discourse-cdn.com/hellohellohello/original/3X/3/d/3dee4d2b7539b3d1f6951fc8a6fc2b66c17b95cf.jpeg)