Trained on FLUX.1 [dev] with 150 photos of Bryce Dallas Howard 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:Bryce_Dallas_Howard_FLUX_v3216-000055:1>
Lora trained on 160 images of Bryce Dallas Howard, captioned with GPT-4 Vision and trained with a Lora model on SDXL 1.0 Base. The strength should be about 0.8-1.1. As with all models ADetailer is recommended for full body images to maintain better face consistency. The last two full body images in the Gallery use ADetailer!
FLUX v1.0 :
Trained on FLUX.1 [dev] with 150 photos of Bryce Dallas Howard with detailed GPT-4 captions. Tested on FLUX 1.D (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:Bryce_Dallas_Howard_FLUX_v3216-000055:1>
1. 轉载模型僅供學習與交流分享，其版權及最終解释權归原作者。
2. 模型原作者如需認領模型，請通過官方渠道联系海藝AI工作人員進行認證。我們致力於保護每一位創作者的權益。 點擊去認領
