Style LoRA of Takarai Shunsuke (宝丼) / TreasureBooru
Like the style? Give the artist some support!
❤️ Drop a 👍 & follow me if you want more!
I look forward to your posts, reviews and comments!
🌟 Recommendations
Use CFG++ samplers such as Euler CFG++ with a CFG of 1-2.
If no trigger tags are specified, this LoRA does not need a trigger tag to work!
Do note that my LoRAs that have been baked on Illu0.1 are compatible with NoobXL's V-Pred models (and any merges / finetunes).
📑 Training Notes
Moved to the 'About this version' tab!
Description
📑 Training Notes
Base Model: Illustrious-XL
Training Resolution: 1536
Training Batch Size: 3
Type: Lora
DIM / Alpha: 20 / 18
Conv Dim / Alpha: 18/ 14
Train On: Unet
Optimizer: AdamW8
Scheduler: Rex
Image Count: 91
Steps: 1600