SDXL LoRA DreamBooth - dber123/lora-illustration-1

Prompt
a blue cake with a candle on top of it in the style of <s0><s1>

Prompt
mobile app customer service in the style of <s0><s1>

Prompt
a woman sitting at a desk with a laptop and a cup of coffee in the style of <s0><s1>

Prompt
a man standing on a chip with a blue background in the style of <s0><s1>

Prompt
two people are standing next to each other with money in the style of <s0><s1>

Prompt
a magnifying glass is pointing at a chart with a graph in the style of <s0><s1>

Prompt
a computer with gears and a laptop on top in the style of <s0><s1>

Prompt
man holding a chart and a cloud in the style of <s0><s1>

Prompt
a man is sleeping in bed with a thought bubble above him in the style of <s0><s1>

Prompt
a cartoon jockey holding a hose in the style of <s0><s1>

Prompt
a hand holding a smartphone with a photo on it in the style of <s0><s1>

Prompt
a hand pointing at a smartphone with three screens in the style of <s0><s1>

Prompt
a woman is using a tablet to view graphs and charts in the style of <s0><s1>

Prompt
a person is holding a light bulb next to a lamp in the style of <s0><s1>

Prompt
laptop with code on it in the style of <s0><s1>

Prompt
news - news - news - news - news - news - news - news - news - news in the style of <s0><s1>

Prompt
a woman is walking on a smartphone screen in the style of <s0><s1>

Prompt
a man is standing next to a suitcase and a map in the style of <s0><s1>

Prompt
a man and woman holding glasses of wine in the style of <s0><s1>

Prompt
a man sitting on top of a piggy bank in the style of <s0><s1>

Prompt
police officer icon in flat style in the style of <s0><s1>

Prompt
hands holding up a smartphone with a qr code on it in the style of <s0><s1>

Prompt
best website builder for small business in the style of <s0><s1>

Prompt
a woman sitting at a desk with a laptop in the style of <s0><s1>

Prompt
a sandwich with a blue and white frosting on it in the style of <s0><s1>

Prompt
a train with a flag and a number one on it in the style of <s0><s1>

Prompt
a woman riding a wave on a surfboard in the style of <s0><s1>

Prompt
a sign that says "danger" on it in the style of <s0><s1>

Prompt
a man is walking with a book and a planet in the style of <s0><s1>

Prompt
a woman is standing in front of a screen with a weather forecast in the style of <s0><s1>

Prompt
a woman doing yoga in a circle in the style of <s0><s1>

Model description

These are dber123/lora-illustration-1 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 lora-illustration-1.safetensors here 💾.
- Place it on your models/Lora folder.
- On AUTOMATIC1111, load the LoRA by adding <lora:lora-illustration-1:1> to your prompt. On ComfyUI just load it as a regular LoRA.
Embeddings: download lora-illustration-1_emb.safetensors here 💾.
- Place it on it on your embeddings folder
- Use it by adding lora-illustration-1_emb to your prompt. For example, in the style of lora-illustration-1_emb (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('dber123/lora-illustration-1', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='dber123/lora-illustration-1', filename='lora-illustration-1_emb.safetensors' repo_type="model")
state_dict = load_file(embedding_path)
pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
        
image = pipeline('in the style of <s0><s1>').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.

dber123
/

lora-illustration-1