SDXL LoRA DreamBooth - lfischbe/m1gra1ne

Prompt
a black and white drawing of a man standing in front of a cloud in the style of <s0><s1>

Prompt
two pages with blue and white ink drawings of a starburst in the style of <s0><s1>

Prompt
a drawing of a man with a gun and a knife in the style of <s0><s1>

Prompt
a painting with a black and white ball and a white and blue circle in the style of <s0><s1>

Prompt
a black and white drawing with a red border in the style of <s0><s1>

Prompt
a painting of a tree and a sun with a rainbow in the style of <s0><s1>

Prompt
a drawing of a woman with a face and a cup in the style of <s0><s1>

Prompt
a drawing of a man standing next to a group of people in the style of <s0><s1>

Prompt
a drawing of a person with a face and a hand in the style of <s0><s1>

Prompt
a painting of a clock with numbers on it in the style of <s0><s1>

Prompt
a watercolor painting of a woman looking at herself in the mirror in the style of <s0><s1>

Prompt
a drawing of a room with a red chair and bookshelf in the style of <s0><s1>

Prompt
a drawing of a hand with a red hand and a drawing of a hand with a red in the style of <s0><s1>

Prompt
a drawing of an eye with a spider on it in the style of <s0><s1>

Prompt
a black and white painting with multicolored stripes in the style of <s0><s1>

Prompt
a drawing of a man's face with a red line around it in the style of <s0><s1>

Prompt
a drawing of a bird with feathers and feathers on it in the style of <s0><s1>

Prompt
a painting of two people with different colored eyes in the style of <s0><s1>

Prompt
a drawing of a woman's eyes with a cloud and lightning in the style of <s0><s1>

Prompt
a painting of a road and a field with a tree in the middle in the style of <s0><s1>

Model description

These are lfischbe/m1gra1ne 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 m1gra1ne.safetensors here 💾.
- Place it on your models/Lora folder.
- On AUTOMATIC1111, load the LoRA by adding <lora:m1gra1ne:1> to your prompt. On ComfyUI just load it as a regular LoRA.
Embeddings: download m1gra1ne_emb.safetensors here 💾.
- Place it on it on your embeddings folder
- Use it by adding m1gra1ne_emb to your prompt. For example, in the style of m1gra1ne_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('lfischbe/m1gra1ne', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='lfischbe/m1gra1ne', filename='m1gra1ne_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.

lfischbe
/

m1gra1ne