Image Interrogation Progress

For the past 2 weeks I’ve been trying to build the new feature of the horde which will allow even people with a low powered GPU, or just CPU to join the horde and provide a service to gather kudos.

It is called “Interrogation” as it will “interrogate” source images to discover aspects about them, such as an image caption, or whether they are displaying NSFW content etc. This feature can then be on-boarded into new or existing tools, such as perhaps automatically captioning images for micro-blogging services as an accessibility feature, or a browser plugin for parental controls etc.

However what I thought would be a bit tricky but doable soon keeps running into various snags. First, I lost one complete week of work from my vacation by getting the nastiest cold I’ve had for the past 10 years at least. Flattening me for almost 9 days. Then it was holiday period where I had to put more attention to family and friends.

Now that I’m finally able to concentrate more on it, I find it’s actually an order of magnitude more complex than I initially expected, requiring me to actually have to update my existing database tables (always a risky proposition) and also redesign my approach to use such things as “Polymorphic tables” so that I don’t end up duplicating hundreds of lines of code between similar classes.

And while I’m doing this, the horde ML backend has been receiving a surprisingly increased pace of improvements, recently implementing depth2img, adding diffusers to voodoo-ray, CodeFormers and a ton of urgent bug-fixes and other improvements.

To say my attention has been split is an understatement.

But I’m slowly but surely making more progress. I hope to have something out soon-ish. I do wonder if it will require a complete horde downtime this time for the DB upgrades. Never done that before. Kinda scary, not gonna lie…