◄Experimental► Looner concept for SDXL (V0.1)

This is an attempt to train a new concept using SDXL. A 3000-step lora was trained at rank 2 and alpha 0.5 in an attempt to minimise style transfer, yet the model requires very high stregth to work (>0.9), taking a hit in quality Model was trained on a single caption, "a person is blowing a large balloon". Further experimentation using other captioning methods and different rank/alpha values are underway.

Bias, Risks, and Limitations

The model cannot reproduce the concept accurately Due to high lora strength, even at rank 2, style transfer occurs.

00071-576851394.png 00099-2133353150.png 00125-2352500702.png 00152-3784117391.png 00404-2466931544.png

Recommendations

Model should be loaded at clip skip 1 and stregth above 0.8 on most checkpoints.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train YuLexuan30/Looner_Concept_Lora_SDXL_Experimental_Rank_2