AI Horde
Back in July I first discovered NLNet and decided to apply for their NGI Zero Core grant to help me help me continue developing the AI Horde. Today I’m excited to announce that the AI Horde has officially been greenlit as one of the projects which will receive the
AI Horde
The AI Horde has turned one year old. I take a look back in all that’s happened since.
AI Horde
Almost immediately after the AI Horde received LoRa support, people started clamoring for Textual Inversions which is one of the earliest techniques to fine-tune Stable Diffusion outputs. While I was planning to re-use much of the code that had to do with the automatic downloading of LoRas, this quickly run
AI Horde
In the past month or so, I’ve been collaborating with stability.ai to help them improve the quality of the new upcoming SDXL model by providing expertise around automation and efficiency in quickly testing new iterations of their model using the the AI Horde as middleware. Today I’m
AI Horde
It’s high time I wrote one more of these posts to keep everyone up to date. It’s been generally a fairly slow month as far as the Horde is concerned. That’s not tot to mean that we produced less content, but rather that there hasn’t been
AI Horde
Lucid Creations Lucid Creations has gotten a few more updates, with the most recent being the ability to load your generation settings from a previous generation you have saved. Plus a few other quality of life fixes More Styles The AI Horde stylelist has received Lora support and about 40
AI Horde
Demand for AI Horde to support LoRas was high ever since they were discovered and unleashed into the Stable Diffusion ecosystem. About 2 months ago we were really close to releasing support for them but alas “stuff happened” which culminated in us having to completely rewrite out inference backend. Fortunately,
AI Horde
I don’t have time to keep Lucid Creations well updated but sometimes I just need to show others how it’s done! So I managed to the first UI to support LoRa on the AI Horde! In case you don’t know what LoRa are, the short version is
AI Horde
While the gathering of aesthetic images never slowed down, the resulting dataset was only ever available from an specific url in the ratings API, making it fairly difficult to discover. To be honest, I was expecting by now, at least some models and other applications would have come out. To
AI Horde
Today I start by wanting to do some work around the upcoming LoRas functionality for the AI Horde, however I first wanted to update my AI Horde README a bit, as it was still referring things like the KoboldAI Horde (which has been merged into the AI Horde since a
AI Horde
I’ve been meaning to write one of these posts every month, but the events since I wrote the last piece have been fairly disruptive. With the loss of our maintainers of nataili, we’ve been forced to put our heads down to alleviate the backend issue, and I didn’
AI Horde
Close to a month an a half ago, our last remaining maintainer for the nataili library dropped out and we were left functional but “rudderless” as far as inference goes. We could continue operations, but we couldn’t onboard new features anymore as neither me nor any of the remaining