LoRAs trained using DRaFT-like post-RL using Siglip/Dino Don't expect sensible results on any other model than <a target="_blank" rel="ugc" href="https://civarchive.com/models/1772667/indexed">indexed v2</a> These are just experiments. I will often not avoid over-training and forgo stronger regularization as I am more so looking for what effects are most prominent for varying data regimes.

post_rl_indexed_v2_lora

trained using DRaFT-LV setup pairwise head on joyquality fitted on a dataset of varying cfg generations from the base model the preference is cfg 3.0 &lt; 5.0 &gt; 7.0

Files with SHA256: bd294e285639ee1ecfb7171d2fd7df044389254e402e6cd9c17c0f461b3b1ee2