<h3 id="flux-v1.0-:-jynjvqukg">FLUX v1.0 :</h3>Trained on FLUX dev with 90 photos of Model Taylor Hill with detailed 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 0.8-1.2. No keywords needed! Distilled CFG around 1-4 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:Taylor_Hill_FLUX_v1-000058:1&gt;<h3 id="sdxl-v2.0-:-elps2l0on">SDXL v2.0 :</h3>Trained on Juggernaut X with 230 photos of American Supermodel Taylor Hill. Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3, AlbedoBaseV2! Use with keyword : "tayxhll" . Use around strength 0.9-1.1. CFG 5.0-7.0. Clipskip 1. Can be used for example as follows:Positive : {Artstyle}, {Character and scene description}, tayxhll, &lt;lora:tayhill_juggerX_xl_1_wocap_merger_21_147_035_065-tayxhll:1&gt;Negative : ugly, deformed, airbrushed, photoshop, rendered, (multiple people), child<h3 id="sdxl-v1.0:-1gg2fr5y5"> SDXL v1.0:</h3>Lora trained on 290 photos of American Supermodel Taylor Hill. Lora strength should be between 0.8-1.2.

Files with SHA256: 2f9a31f4e1555640d4e14b11e5d33ceacd93baadf468bf9bc4290c64a422bde1