zhaop-l
zhaop-l
尝试将Chinese CLIP作为stable diffusion的text encoder,但是一直生成纯黑图像(安全检查已经关闭),我想问下是否可以作为sd的text encoder呢?官方是否做过测试。
对图像进行坐标检测,生成的bbox是resize成正方形之后的值吗? 因为实例代码是将图像resize成正方形了,我跑出来结果有点偏差,所以想问下你们是正方形吗?
### Reminder - [x] I have read the above rules and searched the existing issues. ### System Info - `llamafactory` version: 0.9.2.dev0 - Platform: Linux-5.15.0-134-generic-x86_64-with-glibc2.35 - Python version: 3.10.0 -...
### Checklist - [x] 1. I have searched related issues but cannot get the expected help. - [x] 2. The bug has not been fixed in the latest version. -...