SDXL LoRA DreamBooth - multimodalart/medieval-animals-lora

Prompt

a drawing of a woman and a demon with a blanket in the style of <s0><s1>

Prompt

a bear playing a flute in a medieval manuscript in the style of <s0><s1>

Prompt

a drawing of a bat with wings and a bat's head in the style of <s0><s1>

Prompt

a drawing of a bat with a sign that reads "hic" in the style of <s0><s1>

Prompt

a drawing of a mouse playing with a wheel in the style of <s0><s1>

Prompt

a cat wearing a crown sits on a throne in the style of <s0><s1>

Prompt

a horse with a tree and a bird in the middle of the page in the style of <s0><s1>

Prompt

a monkey with a pipe sitting on the ground in the style of <s0><s1>

Prompt

a small dragon with wings and a tail in the style of <s0><s1>

Prompt

a snail is sitting on a branch with a snake in the style of <s0><s1>

Prompt

a medieval illustration of a man eating a fish in the style of <s0><s1>

Prompt

a cat playing a lute in a medieval manuscript in the style of <s0><s1>

Prompt

a painting of a cat playing a trumpet in the style of <s0><s1>

Prompt

a closeup of an owl in a medieval manuscript in the style of <s0><s1>

Prompt

a medieval illustration of a rabbit carrying a basket in the style of <s0><s1>

Prompt

a medieval illustration of a dog riding a duck in the style of <s0><s1>

Prompt

a drawing of a lion with a man's face on it in the style of <s0><s1>

Prompt

a medieval illustration of a dog riding a horse in the style of <s0><s1>

Prompt

a cat is sitting on a green plate with flowers in the style of <s0><s1>

Prompt

an illustration of an owl in a medieval manuscript in the style of <s0><s1>

Prompt

a drawing of a hairy creature with red shoes in the style of <s0><s1>

Prompt

a medieval illustration of a man being attacked by a dog in the style of <s0><s1>

Prompt

a cat is sitting on a blue and gold background in the style of <s0><s1>

Prompt

an illustration of a unicorn with a horn in the style of <s0><s1>

Prompt

a cat playing a harp in a medieval manuscript in the style of <s0><s1>

Model description

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