Type | |
Stats | 144 2,820 |
Reviews | (10) |
Published | Apr 18, 2024 |
Base Model | |
Usage Tips | Clip Skip: 2 |
Trigger Words | Cristinesdgadf35r34e |
Hash | AutoV2 A6EA9A3E58 |
Hey there, I'm Becca!
I made this LORA based on my face and a combination of a couple beautiful Latina, and Persian celebrities.
I trained each of the three faces separately based on hundreds of images and then used those LORAs to create a combo face and training data for this master LORA.
Installation:
Download the file
Place it in models\Lora folder
Usage:
Use Trigger Word: Cristinesdgadf35r34e
Add the LORA to your text prompt, ex: <lora:Cristinesdgadf35r34e:1>
Works AWESOME With:
Main Checkpoint: Realistic Vision
Realistic Checkpoint: epiCPhotoGasm
Anime Checkpoint: Sexy Toon Cartoon
Comic Art Checkpoint: M4RV3LS & DUNGEONS
NSFW Checkpoint: XenoGASM
Negative Embeddings:
FastNegativeV2
negative_hand
negative_hand-neg
UnrealisticDream
BadDream
Training Data Tips:
Skews towards jewelry and earrings based on the training data, just weight the prompt (earrings:1.5), (jewelry:1.5) in the neg prompts to minimize.
Skews towards a larger breast shape based on the training data, just weight the prompt (small boobs:1.5) in the neg prompts and get the size you want.