whitebearhands/lineart-lora

Lineart Style LoRA

Stable Diffusion 1.5 기반 라인아트 스타일 LoRA 모델입니다.

Trigger Word

lineart_style

프롬프트에 이 단어를 포함해야 학습된 스타일이 적용됩니다.

Usage

from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    torch_dtype=torch.float16,
).to("cuda")

pipe.load_lora_weights("whitebearhands/lineart-lora")

image = pipe(
    "lineart_style, a person working at a desk, clean lines",
    negative_prompt="blurry, low quality, color, photorealistic",
).images[0]

Training Details

• Base Model: Stable Diffusion 1.5
• Method: LoRA (PEFT)
• Rank: 64
• Alpha: 32
• Training Images: 3,000
• Steps: 5,000
• Learning Rate: 1e-4
• Resolution: 512x512

Examples

License

MIT