Engraving Sdxl Lora 001

🚀 SDXL LoRA DreamBooth - m7n/engraving-sdxl-lora-001

This project provides LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0, enabling the generation of engravings featuring a skull and a technical instrument.

🚀 Quick Start

✨ Features

• These are m7n/engraving-sdxl-lora-001 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
• The model can generate engravings in a specific style, triggered by specific tokens in the prompt.

📦 Installation

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

• LoRA: download engraving-sdxl-lora-001.safetensors here 💾.
  • Place it on your models/Lora folder.
  • On AUTOMATIC1111, load the LoRA by adding <lora:engraving-sdxl-lora-001:1> to your prompt. On ComfyUI just load it as a regular LoRA.
• Embeddings: download engraving-sdxl-lora-001_emb.safetensors here 💾.
  • Place it on it on your embeddings folder
  • Use it by adding engraving-sdxl-lora-001_emb to your prompt. For example, engraving in the style of engraving-sdxl-lora-001_emb, showing a skull and a technical instrument (you need both the LoRA and the embeddings as they were trained together for this LoRA)

💻 Usage Examples

Basic Usage

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('m7n/engraving-sdxl-lora-001', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='m7n/engraving-sdxl-lora-001', filename='engraving-sdxl-lora-001_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('engraving in the style of <s0><s1>, showing a skull and a technical instrument').images[0]

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

📚 Documentation

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

🔧 Technical 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.

📄 License

The model is licensed under the openrail++.