ModelsLab/AndroFlux - V8-10k

Note: This version still sucks. I don't really know what I'm doing wrong.

Training changes from the previously posted run (v5):

• Training Steps: Maximum of 6000 >> 10000

• Base Model Precision: int8-quanto >> fp8-quanto

• Learning Rate: 1.0

• Optimizer: Prodigy

• Batch Size: 1 >> 2

• Gradient Accumulation Steps: 1

• Rank: 16 >> 8

• Gradient clipping: default (probably 2) >> 0.1

• Caption Strategy: Triple >> Instance prompt