Please Donate Buzz for FLUX Lora Training !

FLUX v2.0 :

Trained on FLUX.1 [dev] with 110 photos of Influencer Gracie McKenna 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:grmckenna_local_flux_1_standard-000037:1>

FLUX v1.0 :

Trained on FLUX.1 [dev] with 70 photos of Influencer Gracie McKenna 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:Gracie_McKenna_FLUX_v1-000046:1>

SDXL v3.0 :

Trained on Juggernaut X with 103 photos of Instagram Model Gracie McKenna (gracie.mckenna_) . Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3, AlbedoBaseV2! Use with keyword : "grxmckenna" . 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}, grxmckenna, <lora:grmckenna_juggerX_xl_1_wocap_merger_72_104_07_03-grxmckenna:1.0>

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

SDXL v2.0:

Trained on 40 images from Instagram and captioned with GPT-4 Vision and trained on the SDXL 1.0 Base model with an improved Lora model. Lora strength should be between 0.8-1.2.

SDXL v1.0 :

Lora trained on instagram images of American Instagram model Gracie McKenna (gracie.mckenna_) on SDXL 1.0 base.