Neytiri Wan 2.2 LoRA
Trained in dual-mode in musubi-tuner. One LoRA file. 70 images.
Trained at 256 x 256 pixels, then 512 x 512, then 768 and 1024 as well.
Take your pick. Examine the quad comparisons. They are small files (150mb each) so you can download all four and still be under the size of some half LoRAs on civit.
Neytiri did not train well at 256, and 512 is not as rich as 768. Human faces train well at 256, but Neytiri is not human, and the base does not know her alien anatomy.
The "training_data.zip" includes EVERYTHING you need to reproduce my results, including the training data and configuration files as well as install instructions and custom python scripts for processing data to train your own LoRAs.
Zip is here: https://pixeldrain.com/u/4WSaXjcN
Description
This version was trained at [512,512]. All other settings were the same across all four LoRAs.
FAQ
Comments (3)
thank you for providing your training data
make tekken characters bro
Thank you for sharing. Have you noticed much difference with captioning compared to not (just using trigger word only?). Also your Battle Angel Alita image sets were really blurry and low quality yet it trained OK?
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.