Wenxuan Zhang
Wenxuan Zhang
> pytorch 按照文档来安装的。 > > ``` > Python 3.8.16 (default, Mar 2 2023, 03:21:46) > [GCC 11.2.0] :: Anaconda, Inc. on linux > Type "help", "copyright", "credits" or "license" for...
可以采用[GFPGAN](https://github.com/TencentARC/GFPGAN)来提高生成视频的分辨率。 我们尝试过将生成的视频贴回到原图像上,但会存在边缘处无法对齐现象,目前还在尝试改善这一问题,后续有进展会继续更新代码
可以提供一下你的source image吗 我运行一下试试
It means you need more GPU memory. You could try to set batch_size to 1 when you run the inference
You could find `batch_size = 2` in `src/gradio_demo.py `. Just change `batch_size = 2` to `batch_size = 1`