My firs LoRa, apologize if it's not perfect. All training suggestions are welcome.
Trained on 110 pictures, base models
recommendations for SD 1.5
EULER A
higher step number (25-50)
CFG 6-7
768x512
recommendations for SD 2.1 768x (don't forget to download .yaml)
EULER A
low step number (around 20-30)
CFG 6 or lower
960x576 or 1024x768
decrease LoRa weight if needed
Description
initial version
FAQ
Details
Files
CitroenC6-21-v1.yaml
Mirrors
Tilt Shift LoHa.yaml
ffusionAISD21_768BaseAlpha.yaml
Speedtail-000002.yaml
F1 LM-000004.yaml
c5x7-21-v01.yaml
coloringBook_coloringBook.yaml
Countach lp800.yaml
CitroenC6-21-v1.yaml
providence_2112Anchor.yaml
allworkforkrowk_v02GammaFasterlr512.yaml
AnyTayJoy-woman_Vparam_Reged.yaml
idle_Potion_Generator.yaml
evo_car_D-adaptation-LoRA_SD21-768_v044.yaml
ffusionAISD21_baseV100.yaml
evo_car-dm_plaza_D-adaptation-LoRA_SD21-768_v045.yaml
Orc_reg_128.yaml
providence_2111Anchor.yaml
Speedtail-000004.yaml
Amg One.yaml
evo-car-lora-sd21-768_v02.yaml
shurima-1-000010.yaml
providence_2110Prelude.yaml
gdsingld.yaml
Aston Martin DBX Interior-000002.yaml
LBWK360MODENA-000001.yaml
m14af1car70s.yaml
drccitycar_v0.3.yaml
Rx7FD-000002.yaml
Speedtail-000001.yaml
Aston Martin DBX-000002.yaml
anime21_v15.yaml
Aston Martin DBX-000001.yaml
Rx7FD-000001.yaml
pixhell_v20.yaml
mcaf1car70s.yaml
DaveScare-v2.yaml