From fdd349f7bc306913445e68710754572f8147a09b Mon Sep 17 00:00:00 2001 From: Victor Marchesini Ferreira Date: Sat, 15 May 2021 02:43:51 -0300 Subject: [PATCH] Rectify the --projected-w option Specified for generate.py --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 092b52bb4..c0aabe51f 100755 --- a/README.md +++ b/README.md @@ -121,10 +121,10 @@ python projector.py --outdir=out --target=~/mytargetimg.png \ --network=https://nvlabs-fi-cdn.nvidia.com/stylegan2-ada-pytorch/pretrained/ffhq.pkl ``` -For optimal results, the target image should be cropped and aligned similar to the [FFHQ dataset](https://github.com/NVlabs/ffhq-dataset). The above command saves the projection target `out/target.png`, result `out/proj.png`, latent vector `out/projected_w.npz`, and progression video `out/proj.mp4`. You can render the resulting latent vector by specifying `--projected_w` for `generate.py`: +For optimal results, the target image should be cropped and aligned similar to the [FFHQ dataset](https://github.com/NVlabs/ffhq-dataset). The above command saves the projection target `out/target.png`, result `out/proj.png`, latent vector `out/projected_w.npz`, and progression video `out/proj.mp4`. You can render the resulting latent vector by specifying `--projected-w` for `generate.py`: ```.bash -python generate.py --outdir=out --projected_w=out/projected_w.npz \ +python generate.py --outdir=out --projected-w=out/projected_w.npz \ --network=https://nvlabs-fi-cdn.nvidia.com/stylegan2-ada-pytorch/pretrained/ffhq.pkl ```