
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.
描述:
Added more training data to minimize random elements and better support Anime and NSFW models.
训练词语: Cristinesdgadf35r34e
名称: Cristinesdgadf35r34e.safetensors
大小 (KB): 147572
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success