Please Donate Buzz for FLUX Lora Training !

FLUX v1.0 :

Trained on a larger dataset on FLUX.1 [dev] with 90 photos of Madelaine Petsch. 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:Madelaine_Petsch_FLUX_llama_captioned_v2_merger_1???3_61_02_03_05:1>

SDXL v2.0 :

Trained on Juggernaut X with 205 photos of Madelaine Petsch with improved likeness due to consistency and an improved Lora model. Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3, AlbedoBaseV2! Use with keyword : "mxpetsch" . 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}, mxpetsch , <lora:mapetsch_juggerX_xl_1_wocap-mxpetsch-000104:1>

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

SDXL v1.0:

Lora trained on 205 images of Madelaine Petsch (best known for playing Cheryl Blossom on Riverdale) on the SDXL 1.0 base model. The recommended Lora strength for most use cases is between 0.8-1.2. As always Adetailer is recommended for wider shots with the subject in the distance. All gallery images were created WITHOUT Adetailer.