Xiangyang Luo

Results 15 comments of Xiangyang Luo

@Z-YuPeng Thanks for your work. By the way, do you have any plans to introduce your self-owned motion module?

same question, do you solve it now?

> Were you able to solve it @luoxyhappy @Bruc3Xu ? The face swaps are not of good quality even after manipulating loss parameters and hyperparameters. Not yet.... And i have...

you need to set crop_size to 224, run: !python test_one_image.py --name people --Arc_path arcface_model/arcface_checkpoint.tar --pic_a_path crop_224/6.jpg --pic_b_path crop_224/ds.jpg --output_path output/ --crop_size 224

You need to follow the https://github.com/neuralchen/SimSwap/blob/main/docs/guidance/preparation.md to download face detection and alignment models, but the download link doesn't work now.

#474 solved the problem. https://drive.google.com/file/d/1goH5lO8BAhTpRhpBeXqWEcGkxiiLlgx9/view @Maryam483 @TransAmMan @R3PO97

> HI: @luoxyhappy > > Did you just replace the "url" like this: > > !wget --no-check-certificate "https://drive.google.com/file/d/1goH5lO8BAhTpRhpBeXqWEcGkxiiLlgx9/view" -O antelope.zip !unzip ./antelope.zip -d ./insightface_func/models/ > > or did you make...

> > > Hello, a quick question, I am trying to train this model from scratch, and it seems the first-stage training is ok, and I have gotten a promising...

> > > > > Hello, a quick question, I am trying to train this model from scratch, and it seems the first-stage training is ok, and I have gotten...

> > > > > Hello, a quick question, I am trying to train this model from scratch, and it seems the first-stage training is ok, and I have gotten...