<h2 id="please-donate-buzz-for-flux-lora-training-!-ell4j7un4">Please Donate Buzz for FLUX Lora Training !</h2><h3 id="flux-v2.0-:-wjhui4rt8">FLUX v2.0 :</h3>Trained on FLUX.1 [dev] with 180 photos of Josephine Skriver with GPT-4o captions and a larger model. Tested on FLUX 1.D (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:Josephine_Skriver_FLUX_larger_dataset_v2_merger_37_58_07_03:1.0&gt;<h3 id="flux-v1.0-:-g812hee6j">FLUX v1.0 :</h3>Trained on FLUX.1 [dev] with 163 photos of Josephine Skriver. Tested on FLUX 1.D (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:Josephine_Skriver_FLUX_v1-000034:1&gt;<h3 id="-u5yr1dtuq"></h3><h3 id="sdxl-v2.0-:-jw6raxluc">SDXL v2.0 :</h3>Trained on Juggernaut X with 220 photos of Josephine Skriver with improved likeness due to consistency and an improved Lora model. Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3, AlbedoBaseV2! Use with keyword : "joxskriver" . Use around strength 1.0. CFG 5.0-7.0. Clipskip 1. Can be used for example as follows:Positive : {Artstyle}, {Character and scene description}, joxskriver, &lt;lora:joskriver_juggerX_xl_1_woc-joxskriver-000093:1&gt;Negative : ugly, deformed, airbrushed, photoshop, rendered, (multiple people), child<h3 id="sdxl-v1.0:-emdmo3l5i">SDXL v1.0:</h3>Lora trained on 150 images of Model Josephine Skriver and captioned by GPT4-V. The strength should be kept between 0.9-1.2. The model is biased towards realism and is better for closeups.

Josephine Skriver (FLUX + SDXL)

Files with SHA256: 3a8d8db58b657a8d71f3840c696a4773d624d3b59be137b373823dcdbd20a46e