Please consider buying my two albums Sisters of the Wicked and Danger Ahead, my book Dracula and also please check out my YouTube channel. Civitai won't support creators, so any purchase is a real help. Thanks.
DRACULA https://www.amazon.com/dp/B0FM4DXYPL
Sisters of the Wicked https://amazon.com/music/player/albums/B0DSJY3ZHY?marketplaceId=ATVPDKIKX0DER&musicTerritory=US&ref=dm_sh_CdyeuxIBNBDOjZ1hpB1PPJxT0
Danger Ahead https://www.amazon.com/music/player/albums/B0DB2DV354
Music In The Machine https://www.youtube.com/@musicinthemachine/videos
This is just a model to create a repeatable attractive female character. It is not intended to be a real person.
Description
FAQ
Comments (2)
awesome work!!! any tips or training parameters for us noobs trying to make a photorealistic lora of themselves? ;D I'm trying to train mine on kohya with 1e-4 learning rate with 50 images and 50 reg images but no luck first attempt. to teach it body and face
I have never used kohya. I actually have trained all of my Loras here on the site. All you need is good images with good captions and it pretty much sets all the settings on it's own. You can adjust them if you want, but I figure they know more than me. I used to train my own embeddings because I could do that locally on my own computer, but Loras I can't. AnnieFlux came out pretty amazing though on here. I expect that is more because of flux. My actual data set was not all that great. It is the same pics I had used for an embedding back on SD1.5. Just 512x512. I was surprised how awesome it turned out to be honest.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.