---
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
- template:sd-lora
widget:
- text: A photo of <s0><s1> a man with a ponytail wearing a black shirt
  output:
    url: image-0.png
- text: A photo of <s0><s1> a man wearing a black shirt with the words kyoto on it
  output:
    url: image-1.png
- text: A photo of <s0><s1> a man with a mustache and a moustache
  output:
    url: image-2.png
- text: A photo of <s0><s1> a man wearing a kyoto t-shirt
  output:
    url: image-3.png
- text: A photo of <s0><s1> a man standing in front of a garage wearing a t-shirt
  output:
    url: image-4.png
- text: A photo of <s0><s1> a man with a mustache and a hat is taking a selfie with
    a woman
  output:
    url: image-5.png
- text: A photo of <s0><s1> a man with a mustache and a hat
  output:
    url: image-6.png
- text: A photo of <s0><s1> a man with a fake shark mouth and a hat
  output:
    url: image-7.png
- text: A photo of <s0><s1> a man with a mustache and moustache
  output:
    url: image-8.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: A photo of <s0><s1>
license: openrail++
---

# SDXL LoRA DreamBooth - wintergrey/nterg

<Gallery />

## Model description

### These are wintergrey/nterg 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 **[`nterg.safetensors` here 💾](/wintergrey/nterg/blob/main/nterg.safetensors)**.
    - Place it on your `models/Lora` folder.
    - On AUTOMATIC1111, load the LoRA by adding `<lora:nterg:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
- *Embeddings*: download **[`nterg_emb.safetensors` here 💾](/wintergrey/nterg/blob/main/nterg_emb.safetensors)**.
    - Place it on it on your `embeddings` folder
    - Use it by adding `nterg_emb` to your prompt. For example, `A photo of nterg_emb`
    (you need both the LoRA and the embeddings as they were trained together for this LoRA)
    

## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)

```py
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('wintergrey/nterg', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='wintergrey/nterg', filename='nterg_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 photo of <s0><s1>').images[0]
```

For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)

## 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](/wintergrey/nterg/tree/main).

The weights were trained using [🧨 diffusers Advanced Dreambooth Training Script](https://github.com/huggingface/diffusers/blob/main/examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py).

LoRA for the text encoder was enabled. False.

Pivotal tuning was enabled: True.

Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.