Please Donate Buzz for FLUX Lora Training !

FLUX v1.0 :

Trained on FLUX.1 [dev] with 93 photos of Kristine Froseth. 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:Kristine_Froseth_FLUX_v1-000061:1>

SDXL v2.0 :

Trained on Juggernaut X with 93 photos of Kristine Froseth. Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3, AlbedoBaseV2! Use with keyword : "krsxfroseth" . 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}, krsxfroseth, <lora:krfroseth_juggerX_xl_1_st_woc_merger_39_56_82_04_04_02-krsxfroseth:1>

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

SDXL v1.0:

Lora trained on 93 Photos of the actress and model Kristine Froseth. The captioning for the dataset is done using GPT-4 Vision. The Lora strength should be around 0.8-1.2.