RE: https://dbzer0.com/blog/an-epic-3d-printed-fan-expansion-for-last-light/
The designs for these 3D objects were all generated on the AI Horde, using the new Z-Image model.
| homepage | https://aihorde.net |
| itch.io | https://dbzer0.itch.io/lucid-creations |
| source | https://github.com/db0/AI-Horde |
| creator | https://dbzer0.com |
RE: https://dbzer0.com/blog/an-epic-3d-printed-fan-expansion-for-last-light/
The designs for these 3D objects were all generated on the AI Horde, using the new Z-Image model.
Haidra will be presenting the AI Horde in the Open Source Conference Luxembourg on the 1st of October at 2pm @oscl. Come and say hello to our team and talk about our projects!
The Luxembourg Open Source Conference will be on the 1st of Oct 2025 and Haidra staff will not only be participating, but we'll also be giving a presentation on the AI Horde itself! We will hold our talk on Wednesday, October 1 at 2:00pm, so make sure you mark
We'll be visiting the Open Source conference of Luxembourg as Haidra! Come and see us there!
New devlog: https://haidra.net/deleting-users/
Donations now don't have to go through patreon or github anymore!
https://haidra.net/haidra-now-accepts-donations-through-this-haidra-net/
Since the AI Horde has been a SaaS from day one, along with being something anyone can self-host, being able to cover the server costs was a primary focus to avoid burdening myself too much for a hobby project. So I had repurposed my patreon account to accept donations to
SDNext Update for 2024-11-21
>Three weeks is a long time in Generative AI world - and we’re back with ~140 commits worth of updates! > >What’s New? > >First, a massive update to docs including new UI top-level info tab with access to changelog [https://github.com/vladmandic/automatic/blob/master/CHANGELOG.md] and wiki [https://github.com/vladmandic/automatic/wiki], many updates and new articles AND full built-in documentation search capabilities > >#### New integrations > >- PuLID [https://github.com/ToTheBeginning/PuLID]: Pure and Lightning ID Customization via Contrastive Alignment >- InstantX InstantIR [https://github.com/instantX-research/InstantIR]: Blind Image Restoration with Instant Generative Reference >- nVidia Labs ConsiStory [https://github.com/NVlabs/consistory]: Consistent Image Generation >- MiaoshouAI PromptGen v2.0 [https://huggingface.co/MiaoshouAI/Florence-2-base-PromptGen-v2.0] VQA captioning > >#### Workflow Improvements > >- Native Docker support >- SD3x & Flux.1: more ControlNets, all-in-one-safetensors, DPM samplers, skip-layer-guidance, etc. >- XYZ grid: benchmarking, video creation, etc. >- Enhanced prompt parsing >- UI improvements >- Installer self-healing venv > >And quite a few more improvements and fixes since the last update! For full list and details see changelog… > >README [https://github.com/vladmandic/automatic/blob/master/README.md] | CHANGELOG [https://github.com/vladmandic/automatic/blob/master/CHANGELOG.md] | WiKi [https://github.com/vladmandic/automatic/wiki] | Discord [https://discord.com/invite/sd-next-federal-batch-inspectors-1101998836328697867]
When I started developing Hypnagonia 3 years ago, I didn't envision it would lead me to a path of training neural networks, and yet here we are...