FLUX v1.0 :
Trained on FLUX dev with 80 photos of Elisha Cuthbert. 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:elicuthbert_local_flux_1_standard-000035:1>
SDXL v2.0:
Lora trained on 190 photos of Elisha Cuthbert with a new Lora training scheme on SDXL 1.0. Improved likeness and flexibility. Tested on Juggernaut XL (Lightning and Normal), RealismEnginem 2.0. Lora strength should be for most cases between 0.8-1.2.
SDXL v1.0:
Lora of Elisha Cuthbert trained on 42 images of her on the SDXL 1.0 base model. The recommended ComfyUi is 0.9-1.1.
Description
FLUX v1.0 :
Trained on FLUX dev with 80 photos of Elisha Cuthbert. 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:elicuthbert_local_flux_1_standard-000035:1>
FAQ
Comments (1)
Not even the preview images look anything like her