hi guys,

after some tweaking i came to those setting that worked wonderful for my model:

Network Module

LoRA

Use Base Model

FLUX.1 - dev-fp8

Trigger words

-

Image Processing Parameters

Repeat

8

Epoch

12

Save Every N Epochs

1

Training Parameters

Seed

-

Clip Skip

-

Text Encoder learning rate

0.00005

Unet learning rate

0.0001

LR Scheduler

cosine_with_restarts

Optimizer

AdamW8bit

Network Dim

8

Network Alpha

1

Gradient Accumulation Steps

-

Label Parameters

Shuffle caption

-

Keep n tokens

-

Advanced Parameters

Noise offset

0.04

Multires noise discount

0.1

Multires noise iterations

10

conv_dim

32

conv_alpha

16

Batch Size

-