metadata

license: openrail++
library_name: diffusers
tags:
  - text-to-image
  - diffusers-training
  - diffusers
  - lora
  - sd3
  - sd3-diffusers
  - template:sd-lora
base_model: stabilityai/stable-diffusion-3-medium-diffusers
instance_prompt: panda drinking matcha, yarn art style
widget:
  - text: birth of venus, Yarn art style
    parameters:
      negative_prompt: illustration, 2d, painting, digital
    output:
      url: image (131).png
  - text: a yarn art style version of Mona Lisa
    parameters:
      negative_prompt: illustration, 2d, painting, digital
    output:
      url: image (132).png
  - text: a yarn art style yoda
    parameters:
      negative_prompt: realistic, illustration, 2d, bad quality, blurry, bad anatomy
    output:
      url: image (133).png
  - text: starry night, Yarn art style
    parameters:
      negative_prompt: illustration, 2d, bad quality, blurry
    output:
      url: image (134).png
  - text: the beatles, yarn art style
    parameters:
      negative_prompt: illustration, 2d, bad quality, blurry, bad anatomy
    output:
      url: image (135).png
  - text: a yarn art style version of the scream by Munch
    parameters:
      negative_prompt: illustration, 2d, bad quality
    output:
      url: image (136).png

SD3 DreamBooth LoRA - linoyts/Yarn_art_SD3_LoRA

Prompt
birth of venus, Yarn art style

Negative Prompt
illustration, 2d, painting, digital

Prompt
a yarn art style version of Mona Lisa

Negative Prompt
illustration, 2d, painting, digital

Prompt
a yarn art style yoda

Negative Prompt
realistic, illustration, 2d, bad quality, blurry, bad anatomy

Prompt
starry night, Yarn art style

Negative Prompt
illustration, 2d, bad quality, blurry

Prompt
the beatles, yarn art style

Negative Prompt
illustration, 2d, bad quality, blurry, bad anatomy

Prompt
a yarn art style version of the scream by Munch

Negative Prompt
illustration, 2d, bad quality

Model description

These are linoyts/Yarn_art_SD3_LoRA DreamBooth weights for stabilityai/stable-diffusion-3-medium-diffusers. This LoRA was trained on Norod78/Yarn-art-style dataset and inspired by Norod78/SDXL-YarnArtStyle-LoRA🧶

The weights were trained using DreamBooth with the SD3 diffusers trainer.

Was LoRA for the text encoder enabled? True.

Trigger words

You should use yarn art style to trigger the image generation.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-3-medium-diffusers', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('linoyts/Yarn_art_SD3_LoRA', weight_name='pytorch_lora_weights.safetensors')
image = pipeline('darth vader, yarn art style').images[0]

Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke

LoRA: download diffusers_lora_weights.safetensors here 💾.
- Rename it and place it on your models/Lora folder.
- On AUTOMATIC1111, load the LoRA by adding <lora:your_new_name:1> to your prompt. On ComfyUI just load it as a regular LoRA.

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers

Download model

Download the *.safetensors LoRA in the Files & versions tab.

License

Please adhere to the licensing terms as described here.