Naomi Makkelie Seaweed Painting Style 3

🚀 Quick Start

✨ Features

• These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0, allowing for the generation of images in the style of Naomi Makkelie's seaweed paintings.
• Can be used with various UIs such as AUTOMATIC1111, Comfy UI, SD.Next, and Invoke.
• Supports integration with the 🧨 diffusers library.

📦 Installation

Download the Model

• LoRA: Download naomi-makkelie-seaweed-painting-style-3.safetensors here 💾.
  • Place it in your models/Lora folder.
  • On AUTOMATIC1111, load the LoRA by adding <lora:naomi-makkelie-seaweed-painting-style-3:1> to your prompt. On ComfyUI, just load it as a regular LoRA.
• Embeddings: Download naomi-makkelie-seaweed-painting-style-3_emb.safetensors here 💾.
  • Place it in your embeddings folder.
  • Use it by adding naomi-makkelie-seaweed-painting-style-3_emb to your prompt. For example, in the style of naomi-makkelie-seaweed-painting-style-3_emb (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('rikhoffbauer2/naomi-makkelie-seaweed-painting-style-3', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='rikhoffbauer2/naomi-makkelie-seaweed-painting-style-3', filename='naomi-makkelie-seaweed-painting-style-3_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.

📚 Documentation

Trigger Words

To trigger image generation of the 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.

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.

🔧 Technical Details

The model is a LoRA adaption for stabilityai/stable-diffusion-xl-base-1.0. The training process used the diffusers Advanced Dreambooth Training Script. Specific settings during training include the status of LoRA for the text encoder, pivotal tuning, and the use of a special VAE.

📄 License

The model is licensed under openrail++.