This is a SDXL LORA for my character Beata. Learned quite a lot creating this character and didn't overcook her lora like my other one. Used 60 images this time, with a lot different angles, poses, shots, lighting. Kept the description tags out of generation so she's got flexible hairstyles, eye colors, outfits, etc. Really tested this one for versatility.
Suggested Strength:
0.6-0.9 Lower is more flexible, higher will start aligning with training images more.
Trigger words:
beata
Suggested Prompts:
set eye color, hair color, hair style, and descriptive outfit
example:
(beata), makeup, brown eyes, dark brown twin braids framing her face,
small waist, toned athletic body, cleavage, etc.
Included the following expressions, they're in the trigger words for the correct training images. Add these to the prompt to get them.
Expressions
expression, pain, downturned mouth, eyes closed tight,
expression, aroused, suggestive, moaning, flushed cheeks
expression, ahegao, crossed eyes, protruding tongue, flushed cheeks
expression, orgasm, open mouth, grit teeth, eyes closed,
expression, scared, downturned mouth, parted lips, teeth, wide open eyes,
expression, scared, wide open eyes, wide open mouth
expression, kind smile, head tilt,
expression, loving, upturned mouth, wide smile,
expression, sad, half-closed eyes, downturned mouth, looking down,
expression, crying,
expression, crying with mouth open,
expression, laughing, open mouth,
expression, flirting, kissing lips, lopsided mouth, head tilt,
expression, surprised, open mouth, wide open eyes,
expression, angry, furrowed brows, downturned mouth,
expression, hateful, furrowed brows, downturned mouth, teeth, hate,
expression, disgusted, downturned mouth, furrowed brows,
expression, excited, open mouth, wide smile, wide open eyes,
expression, scream, facing up, open mouth, wide open eyes,
Description
Dataset
Folder name: 10_charactername or 8_charactername (repeats)
Repeats: 8–10
Epochs: 1
Max Train Epoch: 10-20
→ This gives you ~2000–3000 total steps (ideal range for characters). Will be divided by Train Batch Size
LoRA Tab – Basic
Pretrained Model: JuggernautXL (or latest version)
LoRA Type: Standard
Network Rank (Dim): 64
Network Alpha: 32
Train Batch Size: 2
Gradient Accumulation Steps: 2–4 (effective batch 4–8)
Mixed Precision: bf16
Resolution: 1024×1024
Enable Bucketing: Yes
Save Every N Epochs: 1
Advanced / Optimizer
Optimizer: AdamW8bit
Learning Rate:
UNet: 1e-4 (0.0001)
Text Encoder: 5e-5
LR Scheduler: cosine_with_restarts
LR Scheduler Num Cycles: 3
Min SNR Gamma: 5
Cache Latents: Yes
Gradient Checkpointing: Off (no need with 32GB)
Color Augmentation: OFF
Shuffle Captions: Yes
Keep Tokens: 1 (essential)
Flip Augmentation: Off
Captioning
Trigger word first in every .txt (e.g. sks_person, or ohwx_john,).
Use WD14 Tagger → then add prefix via Utilities.
Keep detailed natural descriptions.