README.md

metadata

tags:
  - text-to-image
  - lora
  - diffusers
  - template:diffusion-lora
widget:
  - text: a fisherman nearby river, Chinese line art
    parameters:
      negative_prompt: (lowres, low quality, worst quality)
    output:
      url: images/0640244a27a6955bdc2740ef1bacafaf716d194fb77c5346264d91da.jpg
  - text: a woman, Chinese line art
    parameters:
      negative_prompt: (lowres, low quality, worst quality)
    output:
      url: images/f1984bbc23957d65e0bd86273f7e8b1c22b53e2cd51ab4fa83680c87.jpg
  - text: Beijing City, Chinese line art
    parameters:
      negative_prompt: (lowres, low quality, worst quality)
    output:
      url: images/756607bc025fe25935c39225bf18f3c98d24aa5878541533a9ca3424.jpg
base_model: stabilityai/stable-diffusion-3-medium
instance_prompt: Chinese line art
license: other
license_name: stabilityai-ai-community
license_link: >-
  https://huggingface.co./stabilityai/stable-diffusion-3-medium/blob/main/LICENSE.md

SD3.5-LoRA-Chinese-Line-Art

Prompt

a fisherman nearby river, Chinese line art

Negative Prompt

(lowres, low quality, worst quality)

Prompt

a woman, Chinese line art

Negative Prompt

(lowres, low quality, worst quality)

Prompt

Beijing City, Chinese line art

Negative Prompt

(lowres, low quality, worst quality)

Trigger words

You should use Chinese line art to trigger the image generation.

Inference

import torch
from diffusers import StableDiffusion3Pipeline # please install diffusers from the source

pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3.5-large-diffusers", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("Shakker-Labs/SD3.5-LoRA-Chinese-Line-Art", weight_name="SD35-lora-Chinese-Line-Art.safetensors")
pipe.fuse_lora(lora_scale=1.0)
pipe.to("cuda")

prompt = "a boat on the river, mountain in the distance, Chinese line art"
negative_prompt = "(lowres, low quality, worst quality)"

image = pipe(prompt=prompt,
             negative_prompt=negative_prompt
             num_inference_steps=24, 
             guidance_scale=4.0,
             width=960, height=1280,
            ).images[0]
image.save(f"toy_example.jpg")