Please Donate Buzz for FLUX Lora Training !

FLUX v1.0 :

Trained on FLUX.1 [dev] with 90 photos of Zoe Kravitz. 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:Zoe_Kravitz_FLUX_v1-000055:1>

SDXL v1.0

Lora model trained on 120 images of Zoë Kravitz with dataset captioned by GPT-4 Vision. The Lora strength should be 0.8-1.2.