Revised Dataset. Much more flexible than the previous version imo. Has trouble producing "slit pupils" or "snake eyes" so you'd have to inpaint those. Kept the old version, since it’s more similar to the show’s style.
Recommended weight between 0.7-0.9; can go higher or lower depending on additional LoRAs, etc.
Generated Batch Size 6, and picked one seed. Then used Hi-Res Fix (Upscaler: 4x-UltraSharp) 2x —> Extras (Upscaler: 4x-UltraSharp) 2x
描述:
LoRA for Jinx from Teen Titans (2003). Trained v2.0 on AnythingV5, also 1st time using the network dim/alpha: 32/16 to produce a smaller file-size LoRA.
Backgrounds should be easier to detail now, and using additional art-sytles LoRAs seem to have improved (just need to lower this model's weight).
Recommended weight between 0.6-0.8; can go higher or lower depending on additional LoRAs, etc.
-
basic outfit: choker, light-violet collar, violet dress, striped leggings
-
extra: halloween bikni, braided pigtails
Used Hi-Res Fix (Latent) 2x —> Extras (4x-UltraSharp)
训练词语: Jinx,Choker, light-violet collar, violet dress, striped leggings
名称: Jinx_TT_V2.safetensors
大小 (KB): 36980
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
