Leo

icon indicating a website link http://en.xjtu.edu.cn/ icon indicating an email [email protected]

icon company XJTU icon location No.28 Xianning West Road, Xi'an, Shaanxi 710049, P.R. China icon location A graduate student in Xi'an Jiaotong University, research direction is Snapshot Compressive Imaging

Results 3 comments of Leo

No module named 'diffusers.pipelines.controlnet_xs'

followed by this [offical guide](https://mmagic.readthedocs.io/en/latest/get_started/install.html). I had the same problem, installed diffusers==0.24.0 not work. ```home/leo/MentorWorks/ImageInpainting/MMLab/test.py /home/leo/.conda/envs/leo_inpainting/lib/python3.10/site-packages/controlnet_aux/segment_anything/modeling/tiny_vit_sam.py:654: UserWarning: Overwriting tiny_vit_5m_224 in registry with controlnet_aux.segment_anything.modeling.tiny_vit_sam.tiny_vit_5m_224. This is because the name being registered...

Could you kindly provide a list of the environment configurations?

Well, I found that if I adjust batch_size to 4 and use 4 gpus it can run, but the cuda memory only takes up 1/6, and if I adjust it...

ModuleNotFoundError: No module named 'sync_batchnorm' and Can not from . import ssr

> pip install sync-batchnorm This works, thank you！🥳 I've also discovered this [original repo](https://github.com/vacancy/Synchronized-BatchNorm-PyTorch)