FLUX v1.0 :
Trained on FLUX dev with 100 photos of Alba Baptista with detailed 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:Alba_Baptista_FLUX_v1-000058:1>
SDXL v2.0 :
Trained on Juggernaut X with 210 photos of Alba Baptista. Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3, AlbedoBaseV2! Use with keyword : "alxbptsta" . 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}, alxbptsta, <lora:albaptista_juggerX_xl_1_wocap_merger_82_134_05_05-alxbptsta:1.00>
Negative : ugly, deformed, airbrushed, photoshop, rendered, (multiple people), child
SDXL v1.0 :
Lora trained on 110 images of Alba Baptista, a Portugese actress known for Warrior Nuns on Netflix. The Lora is trained on a GPT-4 Vision captioned dataset and trained on SDXL 1.0 Base. The Lora strength should be between 0.8-1.2.
