1 MB iA3 Network
*UPDATE*: v6 is trained with Debiased Estimation Loss on the dev branch of kohya_ss sd-scripts. This makes image structure more coherent and have better color. If you train a model with Debiased Estimation Loss, you shouldn't need to use Min-SNR gamma or Color Aug as it does both better.
Prompt format: very dark focused flash photo of <subject> at night, wide angle, black background
I recommend using DPM++ 3M Exponential/Karras with 40-100 steps. Use the refiner at 0.8 for photorealism.
Description
Trained off the same dataset as v4
Trained with Debiased Estimation Loss instead of Min-SNR Gamma https://github.com/kohya-ss/sd-scripts/pull/889
60 epochs with batch size 8