Summer is an F cup Lora and a beautiful Korean woman to flux with. I have not done much sampling with this Lora but the results were pretty good. Try it for yourself and see what you get.
v2 is an updated dataset with 25 images including 9 high-res
Steps: 3,000, 2 batch (ai-toolkit)
Samples: 50 samples per image
Trigger word: 4myflux (not needed)
Linear/Alpha 32
Learning rate: 0.0001 (bf16)
Image size: 1024x1024
Dataset: 25 detailed photos of her face, head, and body - now has good
Training prompts: Tried to prompt out makeup and jewelry
Please note that all of my sample images double as a ComfyUI workflow! Simply drag any of the sample images into ComfyUI and it will open the entire workflow, set the seed, and use my same configuration. I typically use LLM generation but chose not to do so for these tests; instead, I used a more basic workflow.
Steps: 35
Guidance: 3.5
Sampler: DPM++ 2M, Beta
Age: 22, born and raised in America
Languages: English and Korean
Measurements: 99-73-96 (39-29-38 US), shoe size EU37 (US6.5)
Height: 162cm (5'4), Weight: 61,7kg (136lbs)
Hair: Black
size is 34F, size is medium
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
