SD 1.5 Multi-Style LoRA Pack
artistic style LoRA collection
1 min readupdated
A set of lightweight LoRA weights (small add-on adjustments for a base model) at 3.08 MiB each, trained on Stable Diffusion 1.5. The model lets you render images in Cubism, Post-Impressionism, and Japanese Ukiyo-e woodblock print styles. Built for generating stylized art using the diffusers library, it's a solid fit for anyone working with classic painting styles.
Key features
- Three art styles: supports Cubism, Post-Impressionism, and Ukiyo-e via separate subfolders.
- Compact size: each adapter is just 3.08 MiB.
- Specific trigger phrases: dedicated text tags for each style to get the best results.
What you can do
- Generate art: create landscapes and portraits in Japanese woodblock print or Cubist styles.
- Run Img2Img: stylize existing photos using recommended scheduler settings and strength values.
Example
import torch
from diffusers import StableDiffusionPipeline, AutoencoderKL
vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse", torch_dtype=torch.float16)
pipe = StableDiffusionPipeline.from_pretrained(
"runwayml/stable-diffusion-v1-5",
vae=vae,
torch_dtype=torch.float16,
).to("cuda")
pipe.load_lora_weights("Darrige/sd15-multistyle-lora", subfolder="ukiyo-e")
pipe.fuse_lora(lora_scale=1.05)
image = pipe(
prompt="a quiet mountain temple at dawn, in ukiyo-e style, woodblock print, flat colors",
negative_prompt="photograph, photorealistic, blurry, watermark, 3d render, cg",
num_inference_steps=30,
guidance_scale=7.5,
).images[0]
image.save("styled.png")Read more
DetailsCompatibility: Stable Diffusion 1.5 only (incompatible with SDXL, SD3, or Flux).
Requirements: requires downloading the runwayml/stable-diffusion-v1-5 base model.
Safety: weights do not include a built-in safety checker; external filtering is required for production use.










Comments