PLEASE DONATE BUZZ FOR FLUX LORA TRAINING, I AM RUNNING OUT! IT COSTS MORE THAN 2000 BUZZ TO TRAIN ONE OF THESE!

FLUX v1.0 :

Trained on FLUX dev with 100 photos of Katheryn Winnick with detailed GPT-4 captions. Tested on FLUX 1.dev (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:Katheryn_Winnick_FLUX_v1-000040:1>

SDXL v2.0 :

Trained on Juggernaut X with 210 photos of Katheryn Winnick with improved likeness due to consistency and an improved Lora model. Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3, AlbedoBaseV2! Use with keyword : "katxwinnick" . Use around strength 1.0-1.1. CFG 5.0-7.0. Clipskip 1. Can be used for example as follows:

Positive : {Artstyle}, {Character and scene description}, katxwinnick, <lora:katwinnick_juggerX_xl_1_st_wocap-katxwinnick-000061:1.0>

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

SDXL v1.0:

Lora of Katheryn Winnick trained with 200 images of her on SDXL 1.0 base model. The ComfyUi weight recommended is 0.9-1.1.