SDXL LoRA DreamBooth - Bloof/unsettling-analogish

Prompt

a ghostly image of a dog walking down a wooden walkway in the style of <s0><s1>

Prompt

a red hand is hanging from the ceiling of a stairwell in the style of <s0><s1>

Prompt

unnerving black and white art in the style of <s0><s1>

Prompt

a woman with an uncanny face and a stuffed animal in the style of <s0><s1>

Prompt

the alien is shown in a black and white photo in the style of <s0><s1>

Prompt

a creepy image of a woman with a face mask in the style of <s0><s1>

Prompt

a creepy man in a black hat is standing in the dark in the style of <s0><s1>

Prompt

a woman with a red face, distinct uncanny face in the style of <s0><s1>

Prompt

a creepy face with eyes and a smile in the style of <s0><s1>

Model description

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