SDXL LoRA DreamBooth - Monkeyinlaw/oldstyle

Prompt

a large white tower with a red flag on top in the style of y6iw87fr

Prompt

a man standing in a flooded street in the style of y6iw87fr

Prompt

a man in a hat and tie standing in a flooded street in the style of y6iw87fr

Prompt

a cat standing on a rug in the style of y6iw87fr

Prompt

a sepia - toned image of a kangaroo sitting on a rock in the style of y6iw87fr

Prompt

a man with curly hair in the style of y6iw87fr

Prompt

a black and white photo of a flower in the style of y6iw87fr

Prompt

an old photograph of a dead rose in the style of y6iw87fr

Prompt

an old photo of three women holding a baby in the style of y6iw87fr

Prompt

an old photograph of a man and woman in formal clothing in the style of y6iw87fr

Prompt

black and white photograph of an archway in an old building in the style of y6iw87fr

Prompt

a man riding a bicycle down a snowy road in the style of y6iw87fr

Prompt

an old photo of a woman sitting on a chair in the style of y6iw87fr

Prompt

a vintage photo of a man driving a car in the style of y6iw87fr

Prompt

an old photo of a woman sitting at a table with flowers in the style of y6iw87fr

Prompt

a woman reading a book in the wild in the style of y6iw87fr

Prompt

an old black and white photo of a group of children in the style of y6iw87fr

Prompt

an old photograph of a woman and child in the style of y6iw87fr

Prompt

yellow flowers in a field with a sun light in the style of y6iw87fr

Prompt

an old photo of a woman and boy sitting at a picnic table in the style of y6iw87fr

Prompt

a woman in a coat and hat stands in front of a church in the style of y6iw87fr

Prompt

an old photo of a man in a kilt and pipe in the style of y6iw87fr

Prompt

a black and white photo of three men riding motorcycles in the style of y6iw87fr

Prompt

a woman and a boy standing in front of a door in the style of y6iw87fr

Prompt

a dog is walking in the snow in the style of y6iw87fr

Prompt

a young girl standing in the snow near a wooden fence in the style of y6iw87fr

Prompt

a black and white photo of two children in the style of y6iw87fr

Prompt

a dog laying on a bed in a room in the style of y6iw87fr

Prompt

an old black and white photo of a large house in the middle of a field in the style of y6iw87fr

Prompt

a person standing on the beach looking at the ocean in the style of y6iw87fr

Model description

These are Monkeyinlaw/oldstyle LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.

Download model

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

• LoRA: download oldstyle.safetensors here 💾.
  • Place it on your models/Lora folder.
  • On AUTOMATIC1111, load the LoRA by adding <lora:oldstyle:1> to your prompt. On ComfyUI just load it as a regular LoRA.
• Embeddings: download oldstyle_emb.safetensors here 💾.
  • Place it on it on your embeddings folder
  • Use it by adding oldstyle_emb to your prompt. For example, in the style of y6iw87fr (you need both the LoRA and the embeddings as they were trained together for this LoRA)

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
        
pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('Monkeyinlaw/oldstyle', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='Monkeyinlaw/oldstyle', filename='oldstyle_emb.safetensors' repo_type="model")
state_dict = load_file(embedding_path)
pipeline.load_textual_inversion(state_dict["clip_l"], token=[], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
pipeline.load_textual_inversion(state_dict["clip_g"], token=[], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
        
image = pipeline('in the style of y6iw87fr').images[0]

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

Trigger words

To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:

to trigger concept TOK → use <s0><s1> in your prompt

Details

All Files & versions.

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

LoRA for the text encoder was enabled. False.

Pivotal tuning was enabled: True.

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