Please Donate Buzz for FLUX Lora Training !

FLUX v2.0 (2021-2023) :

Trained on FLUX.1 [dev] with 75 photos of Olivia Cooke in 2021-2023 with detailed GPT-4 captions. 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}, <lora:Olivia_Cooke_2021-2023_FLUX_v2-merger_37_52_07_03:1>

FLUX v1.0 :

Trained on FLUX.1 [dev] with 120 photos of Olivia Cooke with detailed GPT-4 captions. 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}, <lora:Olivia_cooks_FLUX_v1-000061:1>

v2.0 :

Trained on Juggernaut X with 208 photos of Olivia Cooke. Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3 and AlbedoBaseV2. Use with keyword : "olxcke". The strenghth with the keyword should be around 1.0. Can be used for example as follows:

Positive : {Artstyle}, {Character and scene description}, olxcke, <lora:olcooke_juggerX_xl_1_st_wocap_merger_97_99_66_028_042_03-olxcke:1>

Negative : ugly, deformed, airbrushed, photoshop, rendered, (multiple people), child

v1.0:

Lora trained on 163 photos of Actress Olivia Cooke. Lora strength should be between 0.8-1.2.