Hello! I have trying hard and experimenting for a whole day and make an addition to murder drones LoRAs, trained data is various for versions. Is's still too bad for me, but sometimes generate some good results, so here we are!
CLIP SKIP 2 HIGHLY RECOMENDED
After test It seems understanding well, you can change clothes, hats etc and it can generate an NSFW too.
Have fun!
Open to any feedback and tips!.
Issues:
signatures, blur and mess on high resolutions (can be fixed by upscaling)
^^^^ sorry about all of that
Description
The prototype, trained of 5 images, very pruned, but why not to share it?
FAQ
Comments (1)
Guys who use and enjoying it, please share results in gallery. I very want to see some prompt ideas and how LoRA works on different models ^^
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.