Vangogh SDXL LoRA

🚀 SDXL LoRA DreamBooth - inventwithdean/vangogh-SDXL-LoRA

This project provides LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0, enabling unique text-to-image generation.

🚀 Quick Start

Download model

You can use this model with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke.

• LoRA: Download vangogh-SDXL-LoRA.safetensors here 💾.
  • Place it in your models/Lora folder.
  • On AUTOMATIC1111, load the LoRA by adding <lora:vangogh-SDXL-LoRA:1> to your prompt. On ComfyUI, just load it as a regular LoRA.
• Embeddings: Download vangogh-SDXL-LoRA_emb.safetensors here 💾.
  • Place it in your embeddings folder.
  • Use it by adding vangogh-SDXL-LoRA_emb to your prompt. For example, a painting in the style of vangogh-SDXL-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('inventwithdean/vangogh-SDXL-LoRA', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='inventwithdean/vangogh-SDXL-LoRA', filename='vangogh-SDXL-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('a painting in the style of <s0><s1>, gorgeous red roses in a pot, with blue clouds in background').images[0]

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

✨ Features

Model description

These are inventwithdean/vangogh-SDXL-LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.

Trigger words

To trigger image generation of trained concept(or concepts), replace each concept identifier in your 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 license for this model is openrail++.