summaryrefslogtreecommitdiff
path: root/README.md
diff options
context:
space:
mode:
Diffstat (limited to 'README.md')
-rw-r--r--README.md8
1 files changed, 4 insertions, 4 deletions
diff --git a/README.md b/README.md
index df38437..3a2e442 100644
--- a/README.md
+++ b/README.md
@@ -1,15 +1,15 @@
# neural-art
Neural Style Transfer done from the CLI using a VGG backbone and presented as an MP4.
-Weights can be downloaded from [here](https://m1.afileditch.ch/ajjMsHrRhnikrrCiUXgY.pth). This is done to put as little strain as possible on github. The downloaded file should be placed in `./weights/`
+Weights can be downloaded from [here](https://m1.afileditch.ch/ajjMsHrRhnikrrCiUXgY.pth). The downloaded file should be placed in `./weights/` and will be ignored when pushing as per `./.gitignore`
### Why use this in 2023 ?
-Because style transfer hasn't changed drastically in terms of actual results in the past years. I personally find a certain beauty in inputing an image with a desired style rather than a well curated prompt with a dozen of switches.
+Because style transfer hasn't changed drastically in terms of actual results in the past years. I personally find a certain beauty in inputing an image with a desired style rather than a well curated prompt with a dozen of switches. Consider using this repo as a quick *just works* solution that can run on both CPU and GPU.
## Usage
-The script sits comfortably in `./stylize.sh` so just run it:
+The script sits comfortably in `./stylize.sh` so just run it from the project directory:
```bash
-./stylize.sh path/to/style_image path/to/content_image content_in_style.mp4
+./stylize.sh path/to/style_image path/to/content_image
```