Asian Girl Face:Training based on synthetic data.
She may think of some characters, but in fact, this is all based on some character features that I think meet my aesthetic preferences and at the same time have some recognizable features. Starting from one or two reference pictures that meet the needs (also generated by AI), and then through a series of effective image generation and high-definition magnification based on role consistency, I have obtained a model training data set of hundreds of images. Then, this is what you see now.
A beautiful girlfriend who won't lose her temper and is infinitely close to a real person.
It should be noted that due to the limitations of the Flux.1 model, it may not be so easy for you to achieve NSFW. But perhaps the beauty lies in packaging, doesn't it?
Recommended LoRA model weight value: 0.8 - 1.2.
You may need to pay attention to the differences between different branch versions, Qwen, Flux
Enjoy it.
Description
FAQ
Comments (1)
How can you train so many model? I just downloaded your model will try to generate 1,000 images to see the quality. lora weight 0.9, guidance 0.9 setting with 10 random moves and background.