<h3 id="flux-v2.0-palvin-2024:-cs6cmrwe0">FLUX v2.0 Palvin 2024:</h3>Trained on FLUX.1 [dev] with 120 photos of Barbara Palvin in 2024 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},&lt;lora:barpalvin_local_merger_29_54_04_06:1&gt;<h3 id="flux-v1.0-palvin-(2019-2022)-:-l8n99m4v6">FLUX v1.0 Palvin (2019-2022) :</h3>Trained on FLUX.1 [dev] with 80 photos of Barbara Palvin (2019-2022) 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}, &lt;lora:Barbara_Palvin_FLUX_v1-000061:1&gt;<h3 id="flux-v3.0-(2017-2019):-pv6k13r09">FLUX v3.0 (2017-2019):</h3>Trained on FLUX.1 [dev] with 80 photos of Barbara Palvin (2017-2019) 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},&lt;lora:Barbara_Palvin_2017_2019_FLUX_v2-000037:1.0&gt;<h3 id="sdxl-v3.0-:-z4eplasaq">SDXL v3.0 :</h3>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, &lt;lora:barpalvin_juggerX_xl_1_wocap_merger_84_91_06_04-brxpalvin:1&gt;Negative : ugly, deformed, airbrushed, photoshop, rendered, (multiple people), child, mouth open<h3 id="sdxl-v2.0-160mb-:-1144ibh0e">SDXL v2.0 160mb :</h3>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, &lt;lora:barpalvin_32_small_xl_4_standard_wo_cap-merger-11_29_69_04_036_024-barxpalvin:1.05&gt;negative : photoshop, rendered, (multiple people), blurry, child, braids<h3 id="sdxl-v1.0:-d9s6wxpeg">SDXL v1.0:</h3>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.

Barbara Palvin (SDXL+FLUX)

FLUX v2.0 Palvin 2024:Trained on FLUX.1 [dev] with 120 photos of Barbara Palvin in 2024 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},&lt;lora:barpalvin_local_merger_29_54_04_06:1&gt;

barpalvin_local_merger_29_54_04_06.safetensors

FLUX v2.0 (2024)

Files with SHA256: 449f662ce53439ceb1da1f8c3bbc67dcea432b78173eddcfcb3d68c3c84938c0