CkShibit

python ./pipelines/demo/image_demo.py "/root/workspace/facefusion/input_source/mmexport1705161230807.jpg" "/root/workspace/easyportrait/pipelines/local_configs/easyportrait_experiments_v2/segformer-fp/segformer-fp.py" "/root/workspace/easyportrait/pipelines/models/segformer-fp-512.pth" --palette=easy_portrait --out-file="ttt.png" /root/miniconda3/envs/easyportrait/lib/python3.8/site-packages/mmcv/__init__.py:20: UserWarning: On January 1, 2023, MMCV will release v2.0.0, in which it will remove components related to the training process and add...

> 当前提供的部署方式都是docker容器方式，毕竟比较方便快捷，其他部署方式会马上推出，比如helm chart，linux package等 > > 您这边希望的安装方式是什么？ linux package最好，谢谢大佬们

> If you are asking how to switch to your own trained FLUX.1-dev model, you can replace the model path in [this line of code](https://github.com/ToTheBeginning/PuLID/blob/main/flux/util.py#L40) with the path to your...

How to get the quantization jsonfile while using my finetuned fp8 model？