Type | |
Stats | 1,395 0 |
Reviews | (105) |
Published | Aug 20, 2024 |
Base Model | |
Training | Steps: 2,210 Epochs: 52 |
Usage Tips | Clip Skip: 1 Strength: 1 |
Hash | AutoV2 72FE34AABA |
Please Donate Buzz for FLUX Lora Training !
FLUX v1.0 Sweeney :
Trained on FLUX.1 [dev] with 85 photos of Sydney Sweeney with detailed GPT-4 captions. Tested on FLUX 1.dev (full) and FLUX fp8 and FLUX nf4 ! Use around strength 0.8-1.0. 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:Sydney_Sweeney_FLUX_v1-000052:1>
v2.0 :
Trained on Juggernaut X with 180 photos of Sydney Sweeney. Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3, AlbedoBaseV2! Use with keyword : "sydxsweeney" . 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}, sydxsweeney, <lora:sydsweeney_juggerX_xl_2_st_merger_41v1_9v2_112v2_03_02_05-sydxsweeney:1>
Negative : ugly, deformed, airbrushed, photoshop, rendered, (multiple people), child
v1.0:
Lora trained on 180 HQ photos of Sydney Sweeney. Lora strength should be 0.8-1.2 for most use cases.