Background: Haidra has, up until now, been the informal group behind AI-Horde and has been dedicated to providing free and open-source services and software. We are all volunteers ourselves, and we rely entirely on volunteer effort to develop, operate and maintain our services, which we offer free of charge. Incorporation
A few enhancement has been added to the shared keys and the styles capability which was recently onboarded. Let's list them in kind First you can now transfer kudos directly to a shared key, instead of a user. Simply provide the shared key ID where you would before
Idle computing power can be used to make the world a more equitable place. At Haidra we encourage sharing these important resources - learn how!
The text generation on the AI Horde supports multiple inference back-ends, unlike the image generation which is reliant on then reGen worker. As the AI Horde initially spawned utilizing the KoboldAI API, we kept using that API schema as the primary one for LLM inference. The existing inference back-ends we
A while ago, when we set up the Haidra organization, we also developed a pretty basic website with the help of the Artbot developer (rockbandit) hosted at haidra.net. However this website remained pretty bare-bones as it not easy to maintain and the rockbandit remained busy with Artbot itself. I
Almost since the early days of the AI Horde we've been curating a git repository with pre-defined image generation styles. This was initially started so that people would have an easy way to generate images through our official AI Horde Discord bot, but also to to be used
It's been cooking for a while but we can now officially announce that the Flux.1-schnell is finally available on the AI Horde! Flux is one of the most exciting Generative AI text2image models to come out this year, from a team of ex-stability.ai developers, and seemingly
The AI Horde has turned two years old. I take a look back in all that’s happened since.
We have another new feature available for people to use from the AI Horde. This is the capacity to use Layer Diffuse to generate images with a transparent background directly (as opposed to stripping the image background with a post-processor). As someone who’s dabbled into video game development in
The second fediverse canvas event just concluded and I’m very happy how this turned out. In case you don’t know what this is. Check out this post and then take your time to go and explore the second canvas in depth before it’s taken down, and look
Around the same time last year, the first controlnet for generating QR codes with Stable Diffusion was released I was immediately enamored with the idea and wanted to have it ASAP as an option on the AI Horde. Unfortunately due to a lot of extenuating circumstances [gesticulates wildly] I had
The initial deployment of the Stable Cascade (SC) on the AI Horde supported just text2image workflows, but that was just a subset of what this model can do. We still needed to onboard the rest of its capabilities. One such capability was the “image variations” option, which allows you to