zzzzzj1994

I test with using the face embedding from vit-base-patch16-224-in21k-face-recognition which shape is 768. After trainning, the resules are below like: the image to mask:  the target image to extarct...

where modified the clip model to local path?

@PonyMaY I suggust you should post the version of TensorRT installed from source , as well as the pytorch. Futhermore, the details of DCNv2 installation; and have you export the...

这个作者的c++那部分代码没把输入说明，可以参考这个： https://github.com/lesliejackson/TensorRT-DCNv2-Plugin I cannot run the code without clarying the input node in C++. I refered the code below: https://github.com/lesliejackson/TensorRT-DCNv2-Plugin

作者没有提到需要`InferPlugin.cpp`文件呢。你可以把链接和需要的地方附件一下。

`Couldn't export operator custom_ops` that is beacause of the version of pytorch; After i export the onnx file successfully, it still cannot convert the onnx file to trt file and...

you shoul the related code in `TensorRT/parsers/onnx` to register the plugin

Thank you for the instant reply. Here are my code below: 1. using diffusers load lora trained with kohya_ss; code: ``` pipe.load_lora_weights(str(lora_path)) prompt = "_trigger_word_,The image is a black and...

editany.py still meet the error.