Trained on Juggernaut X with 80 photos of Barbara Palvin with detailed GPT-4 captions. Tested on FLUX 1.dev (full) and FLUX fp8 and FLUX nf4 ! Use around strength 0.8-1.0. 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}, <lora:Barbara_Palvin_FLUX_v1-000061:1>
Trained on Juggernaut X with 210 photos of mdoel Barbara Palvin. Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3 and AlbedoBaseV2 ! Use with keyword : "brxpalvin" . Use around strength 1.0 or less. Can be used for example as follows:
Positive : {Artstyle}, {Character and scene description}, brxpalvin, <lora:barpalvin_juggerX_xl_1_wocap_merger_84_91_06_04-brxpalvin:1>
Negative : ugly, deformed, airbrushed, photoshop, rendered, (multiple people), child, mouth open
Trained on 183 photos of Barbara Palvin on SDXL 1.0 base with better Lora presets. Less than half the size of the previous version. Use with keyword : "barxpalvin"! Lora strength with prompt should be around 1.0-1.1. Following prompt structure on Juggernaut v7, realismEngine 2.0 or Juggernautv9 lightning works well:
positive : {art style}, {character descrioption and action},barxpalvin, <lora:barpalvin_32_small_xl_4_standard_wo_cap-merger-11_29_69_04_036_024-barxpalvin:1.05>
negative : photoshop, rendered, (multiple people), blurry, child, braids
Lora Model trained on 250 images of Barbara Palvin on the SDXL 1.0 Base model. The Lora weight should be 1.0-1.1.