SDXL LoRA DreamBooth - mitrick2/r2-sdxl-lora

Prompt

Rivian R2 SUV at the entrance to a forest

Prompt

Rivian R2 SUV at the entrance to a forest

Prompt

Rivian R2 SUV at the entrance to a forest

Prompt

Rivian R2 SUV at the entrance to a forest

Model description

These are mitrick2/r2-sdxl-lora LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. This LoRA adds support for Rivian R2 image generation by including the trigger word R2.

Download model

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

• LoRA: download r2-sdxl-lora.safetensors here 💾.
  • Place it on your models/Lora folder.
  • On AUTOMATIC1111, load the LoRA by adding <lora:r2-sdxl-lora:1> to your prompt. On ComfyUI just load it as a regular LoRA.
• Embeddings: download r2-sdxl-lora_emb.safetensors here 💾.
  • Place it on it on your embeddings folder
  • Use it by adding r2-sdxl-lora_emb to your prompt. For example, R2 SUV at the trailhead of a beautiful forest (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('mitrick2/r2-sdxl-lora', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='mitrick2/r2-sdxl-lora', filename='r2-sdxl-lora_emb.safetensors', repo_type="model")
state_dict = load_file(embedding_path)
pipeline.load_textual_inversion(state_dict["clip_l"], token=[], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
pipeline.load_textual_inversion(state_dict["clip_g"], token=[], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
        
image = pipeline('Rivian R2 SUV at the entrance to a forest').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 Rivian R2 → use R2, 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.