Please Donate Buzz for FLUX Lora Training !
FLUX v1.0 (2023-2024):
Trained on FLUX.1 [dev] with 110 photos of Dua Lipa in 2023-2024. 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:Dua_Lipa_new_FLUX_v2-000055:1>
SDXL v1.0
Lora trained on 130 images of British-Albanian Singer Dua Lipa. Captioned with GPT-4 Vision and trained with a slightly larger Lora model than usual. Lora strength should be between 0.7-1.2.
Description
FAQ
Comments (1)
do u do requests, i would like one for madison beer, there is another but it doesnt work with other models and i really like using juggernaut. If u accept my request I have something to tell you before you do it, it'll probably help. its just about madison and what type of images would be best to choose. I sent a friend request on your discord. You dont have to accept my request just a recommendation ofc