Originally a mix I made anonymously thanks to being inspired by the desire to use AOM2_hard and wanting to test out basic mixing with a Vtuber finetuned model which was created anonymously as well. The 4th version of the model has been uploaded to huggingface but I'm not certain if it's the original creator of the model
https://huggingface.co/CluelessC/hll-test/tree/main
(it's in working progress right now but I am looking forward to implementing it as the main focus for the future Based mixes)
However from Based64 to Based65 this is the finetuned model I used as the base for these mixes, this is version >
Based64 was made with the most basic of model mixing, from the checkpoint merger tab in the stablediffusion webui,
I will upload all the Based mixes onto huggingface so they can be on one directory, Based64 and 65 will have separate pages because Civitai works like that with checkpoint uploads? I don't know first time I did this
https://huggingface.co/AnonymousM/Based-mixes
Just use the model however you use other NAI based mixed models, the LORA compatibility with Based64 mix V3 works really good according to feedback I saw on the sidelines when I released this model anonymously.
JUST REMEMBER TO NOT USE THIS MODEL TO TRAIN, ONLY USE NAI'S LEAKED MODELS FOR TRAINING, FINAL-PRUNED NOTHING MORE
Each mix will be updated in the future with their "pruned" version, by using the model toolkit extension
Future entries within the Based mix series will be added to my Civitai page or the Huggingface page that will have all the safetensors uploaded in due time just in case this site is taken down in the future. Otherwise Based66 will come out soon but I need to look over some models within my mixing recipe and I have to catch up with baking more LORAs and posting their outputs onto my social media platforms, please support me there if you enjoy my work
This is pretty much the golden standard of my Based-mixes, or what I've seen people say about it when I was looking at the sidelines. The LORA compatibility with this model is REALLY good
DOES NOT MEAN YOU SHOULD USE IT AS A MODEL TO TRAIN LORAS, NEVER USE MERGES FOR TRAINING ALWAYS USE NAI'S LEAKED MODEL
