---
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
- template:sd-lora
widget:
- text: A photo of <s0><s1> itysl a man in a yellow shirt and black jacket
  output:
    url: image-0.png
- text: A photo of <s0><s1> itysl a man wearing a black jacket
  output:
    url: image-1.png
- text: A photo of <s0><s1> itysl a man in a red suit and tie is standing in front
    of a colorful background
  output:
    url: image-2.png
- text: A photo of <s0><s1> itysl a man with a white shirt and a black jacket
  output:
    url: image-3.png
- text: A photo of <s0><s1> itysl a man in a blue shirt sitting at a desk
  output:
    url: image-4.png
- text: A photo of <s0><s1> itysl a man with a tie on
  output:
    url: image-5.png
- text: A photo of <s0><s1> itysl a man with a mustache
  output:
    url: image-6.png
- text: A photo of <s0><s1> itysl a man in a checkered shirt holding a red ball
  output:
    url: image-7.png
- text: A photo of <s0><s1> itysl a man holding a box of wine in front of him
  output:
    url: image-8.png
- text: A photo of <s0><s1> itysl a man sitting at a desk
  output:
    url: image-9.png
- text: A photo of <s0><s1> itysl a man sitting at a desk
  output:
    url: image-10.png
- text: A photo of <s0><s1> itysl a man with a blue shirt
  output:
    url: image-11.png
- text: A photo of <s0><s1> itysl a man wearing a white shirt
  output:
    url: image-12.png
- text: A photo of <s0><s1> itysl a man with a smile on his face
  output:
    url: image-13.png
- text: A photo of <s0><s1> itysl a man in a plaid shirt standing in front of a wall
  output:
    url: image-14.png
- text: A photo of <s0><s1> itysl a man holding his head with both hands
  output:
    url: image-15.png
- text: A photo of <s0><s1> itysl a man with a sad face looking at something
  output:
    url: image-16.png
- text: A photo of <s0><s1> itysl a man in a suit and tie making a gesture
  output:
    url: image-17.png
- text: A photo of <s0><s1> itysl a man in a car
  output:
    url: image-18.png
- text: A photo of <s0><s1> itysl a man in a black jacket and white shirt standing
    in an office
  output:
    url: image-19.png
- text: A photo of <s0><s1> itysl a man in a black jacket and blue shirt smiling
  output:
    url: image-20.png
- text: A photo of <s0><s1> itysl a man in glasses and a polo shirt
  output:
    url: image-21.png
- text: A photo of <s0><s1> itysl a man in a jacket and a tie
  output:
    url: image-22.png
- text: A photo of <s0><s1> itysl a man in a suit standing in front of a window
  output:
    url: image-23.png
- text: A photo of <s0><s1> itysl a man holding a pizza
  output:
    url: image-24.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: A photo of <s0><s1> itysl
license: openrail++
---

# SDXL LoRA DreamBooth - jhiggs/tim-robinson

<Gallery />

## Model description

### These are jhiggs/tim-robinson 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 **[`tim-robinson.safetensors` here 💾](/jhiggs/tim-robinson/blob/main/tim-robinson.safetensors)**.
    - Place it on your `models/Lora` folder.
    - On AUTOMATIC1111, load the LoRA by adding `<lora:tim-robinson:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
- *Embeddings*: download **[`tim-robinson_emb.safetensors` here 💾](/jhiggs/tim-robinson/blob/main/tim-robinson_emb.safetensors)**.
    - Place it on it on your `embeddings` folder
    - Use it by adding `tim-robinson_emb` to your prompt. For example, `A photo of tim-robinson_emb itysl`
    (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('jhiggs/tim-robinson', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='jhiggs/tim-robinson', filename='tim-robinson_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> itysl').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](/jhiggs/tim-robinson/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.