SDXL LoRA DreamBooth - reddish

Prompt

in the style of reddish

Prompt

Face closeup, Beautiful young woman

Prompt

a woman with sunglasses

Prompt

a girl

Model description

• Model Name: Reddish
• Model Type: LoRA (Low-Rank Adaptation)
• Model Version: 1.0
• Author: M.Cihan Yalçın

Download model

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

• LoRA: download reddish.safetensors here 💾.
  • Place it on your models/Lora folder.
  • On AUTOMATIC1111, load the LoRA by adding <lora:reddish:1> to your prompt. On ComfyUI just load it as a regular LoRA.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('reddish', weight_name='pytorch_lora_weights.safetensors')

image = pipeline('in the style of reddish').images[0]

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

Performance

The Reddish model excels in producing images with the following characteristics:

• High-Quality Faces: Detailed and realistic facial features.
• Reddish Style: Warm tones with a focus on elegance and beauty.
• Artistic Elements: Incorporates creative and artistic elements such as lighting effects and detailed accessories.

Trigger words

You should use in the style of reddish to trigger the image generation.

Details

All Files & versions.

The weights were trained using 🧨 diffusers Advanced Dreambooth Training Script.

LoRA for the text encoder was enabled: True.

Pivotal tuning was enabled: False.

Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.