-
-
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
Most of my workflows are self-made. For captioning I used Blip-2 in a custom script I made that automates the process by going into directories and their sub-directories and creates a .txt file beside each image. This way I can keep my images organized in their proper directories, without having to put dump them all in a single place.
I'm training 768px to 1024px models currently, and to prepare them I wrote a little script using ImageMagick to process my dataset folder and export them at the specific resolution needed. No, the images don't need to be a square format anymore, now that we have bucketing, they just require to be 512/768/1024 at the longest edge, depending what size model you're training. Nothing is cropped out of frame.