<h3 id="flux-v1.0-(2008-2010)-:-4t4r3wec3">FLUX v1.0 (2008-2010) :</h3>Trained on FLUX.1 [dev] with 80 photos of Nina Dobrev in 2008-2010 with detailed GPT-4o captions. Tested on FLUX <a target="_blank" rel="ugc" href="http://1.dev">1.dev</a> (full) and FLUX fp8 and FLUX nf4 ! Use around strength 0.9-1.2. Distilled CFG 3.5 and CFG 1.0 (without negative prompt). Clipskip 1. Can be used for example as follows:Positive : {Artstyle, Character and scene description in usual FLUX fashion},&lt;lora:nina_dobrev_80imgs_70epochs_merger_11_54_02_08:1.0&gt;<h3 id="sdxl-v1.0:-rpjt5yock">SDXL v1.0:</h3>Lora trained on 316 images of Nina Dobrev on the SDXL 1.0 base model. The recommended Lora strength for most use cases is between 0.8-1.2.

Files with SHA256: 408e3145c4b2fa3b04ff4d0878bfb196cbe5d9302c80a678a744d3263bef4ade