Please Donate Buzz for FLUX Lora Training !

FLUX v1.0 :

Trained on FLUX dev with 100 photos of Mila Kunis 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:Mila_Kunis_FLUX_v1-000040:1>

v2.0 :

Trained on Juggernaut X with 200 photos of Mila Kunis. Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3, AlbedoBaseV2! Use with keyword : "mxkunis" . Use around strength 1.0. CFG 5.0-7.0. Clipskip 1. Can be used for example as follows:

Positive : {Artstyle}, {Character and scene description}, mxkunis, <lora:mikunis_juggerX_xl_1_wocap_merger_52_139_05_05-mxkunis:1>

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

v1.0 :

Lora trained on 200 images of Mila Kunis trained on SDXL 1.0 base model. Recommended lora strength on ComfyUi is 0.9-1.1.