
Chinese MILF series
Good prompting yields hyper-realistic results. Have not done much generation with this model but all testing was very positive.
ComfyUI usage:
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. Many sample images provide examples of the wide range of her beauty. Convert her from mom mode to stunner
ComfyUI settings:
-
Steps: 35
-
Guidance: 3.5
-
Sampler: DPM++ 2M, Basic
Training details:
-
Steps: 4,000, 1 batch (ai-toolkit)
-
Trigger word: vivian
-
Linear/Alpha 32
-
Learning rate: 0.0001 (bf16)
-
Image size: 1024x1024
-
Dataset: 64 detailed photos of her face, head, body proportions, no nudes included
-
Training prompts: I had her wearing black frame glasses in nearly all of the training photos. Extremely detailed prompts were used for each photo.
Get to know Vivian:
-
Age: 39, born and raised in China
-
Languages: 台山话, 广东话, 普通话, English
-
Measurements: 81-71-91 (32-28-36 US), shoe size EU36 (US6)
-
Height: 157cm (5'2), Weight: 46kg (103lbs)
-
Hair: Black, sometimes with blonde highlights
-
Bra size is 30B, panty size is small
描述:
训练词语: vivian
名称: Vivian_Flux_Lora.safetensors
大小 (KB): 335748
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success