If you have questions, suggestion, problem, or just like the model feel free to comment.
LoRA Training Info I trained this LoRA using 85 images of Yu Seolha with 6800+ steps.
The dataset contains no AI-generated content.
I'm using SD Forge Neo
Full preview images on .red
Essential Prompts or You can try something related
Character: white eyelashes is optional
1girl, gray eyes, very long hair, straight hair,
hair in bun, messy bun, hair stick, two hairpins, golden hairpins
1girl, gray eyes, black hair flowing down her shoulders
Outfits:
Dark hanfu, black robe, grey robe, red skirt,
Purple hanfu, dark purple robe, wide sleeves, patterned inner robe, subtle pattern, dark sash, ornate gold belt buckle, gold chain, white pants, white hakama,
Example of a prompt I used in dataset: “A woman with long, dark gray hair styled in an updo with two golden hairpins, wearing a deep purple traditional robe with subtle swirling patterns, a wide belt with a golden ornate buckle, and dangling golden earrings. She sits poised on a wooden chair with her arms resting on the armrests, looking directly forward with a calm, composed expression. Behind her is a traditional wooden lattice window structure with square panes, bathed in soft sunlight casting gentle shadows. The background features warm tones of beige and light brown, suggesting an indoor setting with natural light.”
You can also use regular booru-style prompts — they work great too, just like the images I posted.