Please Donate Buzz for FLUX Lora Training !

FLUX v1.0 :

Trained on FLUX.1 [dev] with 73 photos of Florence Pugh. 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:Florence_Pugh_FLUX_v1-000055:1>

v2.0 :

Trained on Juggernaut X with 220 photos of Florence Pugh. Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3, AlbedoBaseV2! Use with keyword : "flxpugh" . Use around strength 0.9-1.1. CFG 5.0-7.0. Clipskip 1. Can be used for example as follows:

Positive : {Artstyle}, {Character and scene description}, flxpugh, <lora:flopugh_juggerX_xl_1_wocap_flxpugh-000135:1>

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

v1.0:

Lora trained on 302 images of Florence Pugh 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. Also because she recently wears a septum ring, if you dont want a septum ring in the image I would write "nose ring, septum ring" in the negative prompt.