First of a series of EVO brand cars LoRA models.
All training suggestions are welcome.
v0.741 first SDXL version, includes EVO 3 car, Cattedrale di Palermo square, Teatro Massimo & Palermo streets
Description
Trained on a dataset of 118 hi-res images (wiith BLIP captions manually edited) with Repeats = 20 and 2360 regularisation images, source model: stabilityai/stable-diffusion-2-1 with v2 and v_parameterization enabled.
Relevant Kohya settings:
Learning rate: 0.0001
LR Scheduler: cosine
LR warmup (% of steps): 10
Optimizer: AdamW8bit
Text Encoder learning rate: 0.00005
Unet learning rate: 0.0001
Network Rank (Dimension): 128
Network Alpha: 1
Max resolution: 768,768
Clip skip: 1
Min SNR gamma: 0
Details
Files
evo-car-lora-sd21-768_v02.yaml
Mirrors
anime21_v15.yaml
Speedtail-000002.yaml
evo-car-lora-sd21-768_v02.yaml
allworkforkrowk_v02GammaFasterlr512.yaml
providence_2112Anchor.yaml
drccitycar_v0.3.yaml
CitroenC6-21-v1.yaml
evo_car_D-adaptation-LoRA_SD21-768_v044.yaml
idle_Potion_Generator.yaml
providence_2111Anchor.yaml
mcaf1car70s.yaml
Aston Martin DBX-000001.yaml
Aston Martin DBX-000002.yaml
Countach lp800.yaml
Rx7FD-000002.yaml
Aston Martin DBX Interior-000002.yaml
Amg One.yaml
m14af1car70s.yaml
c5x7-21-v01.yaml
evo_car-dm_plaza_D-adaptation-LoRA_SD21-768_v045.yaml
DaveScare-v2.yaml
AnyTayJoy-woman_Vparam_Reged.yaml
coloringBook_coloringBook.yaml
pixhell_v20.yaml
ffusionAISD21_baseV100.yaml
ffusionAISD21_768BaseAlpha.yaml
providence_2110Prelude.yaml
shurima-1-000010.yaml
Speedtail-000004.yaml
Speedtail-000001.yaml
Rx7FD-000001.yaml
LBWK360MODENA-000001.yaml
Tilt Shift LoHa.yaml
F1 LM-000004.yaml
Orc_reg_128.yaml
gdsingld.yaml