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 &lt;subject&gt; at night, wide angle, black backgroundI recommend using DPM++ 3M Exponential/Karras with 40-100 steps. Use the refiner at 0.8 for photorealism.

Flash Photo SDXL

Trained off the same dataset as v4Trained with Debiased Estimation Loss instead of Min-SNR Gamma <a target="_blank" rel="ugc" href="https://github.com/kohya-ss/sd-scripts/pull/889">https://github.com/kohya-ss/sd-scripts/pull/889</a>60 epochs with batch size 8

Files with SHA256: c706e3f2831a06bb413f0dadff8df2bc9631c6709e392178cda1acd5f5d32a09