V2

Last version I used too many images (93 I think), this version I used 24 images to capture a certain look. The difference in this lora with my others is I actually tested many epochs and found the best setting(in my humble opinion). I never did before because of laziness. Anyway I am not putting the trigger or strength in the normal spot because I want people to read the description or even just look at the prompts in sample images. To get the same results I got just look at the things below, it's not complicated and will save u some hassle. There will be more sample images hours after I post, some will be taken down for review by civit.

What to start the prompt with

You need to put "photo of m4d1s0n a woman" at the start. It's what I did while testing and what I found to be best. If you want a half body photo put "half body photo of m4d1s0n a woman". For full body- "full body photo of m4d1s0n a woman" etc.

Strength it works best at

I've tried a variety of strengths and what always works best for me is 0.8. More than that usually messes up hands plus doesn't add to the likeness, at least in my opinion.

You don't need to tag her regular features

You do not need to describe her eye color, hair color, body type, etc. Unless you're in the mood with her having blonde hair or something.

What to put in the negative prompt

ugly, deformed, airbrushed, photoshop, rendered, (multiple people), blurry, child, mouth open, teeth visible

What models this works best with

I haven't had time to test with anything except Amalgamation but these are all the models my Loras usually work well with:

Himeros: https://civitai.com/models/255907?modelVersionId=423235

Amalgamation: https://civitai.com/models/287016?modelVersionId=456815

Juggernaut: https://civitai.com/models/133005?modelVersionId=240840

Psychosis: https://civitai.com/models/449888?modelVersionId=515453

V1

She is hard to get a good likeness of but I tried my best. 2024 madison/recent Madison. Use strength of 0.8. Should work with most models but I like it best with amalgamation and himeros. I recommend using steps from 30-40. Sample images are 832x1216 with Adetailer. I recommend putting this in negative prompt: ugly, deformed, airbrushed, photoshop, rendered, (multiple people), blurry, child, mouth open

描述:

trained on 24 images, 66 epoch

训练词语: