---
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
- template:sd-lora

base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: Margiela SS24 style
license: openrail++
---
    
# SDXL LoRA DreamBooth - tonyassi/margiela-ss24-fashion-lora

by [Tony Assi](https://www.tonyassi.com/)

Dreambooth Lora style based on the [Margiela SS24](https://www.vogue.com/fashion-shows/spring-2024-couture/maison-martin-margiela) collection.

![image/png](https://cdn-uploads.huggingface.co/production/uploads/648a824a8ca6cf9857d1349c/EvvVT0qAKrJdyCJi82bmg.png)

## Trigger words
Use **Margiela SS24 style** in the prompt to trigger the style.

## How to use
```bash
pip install diffusers accelerate
```

```python
import torch
from diffusers import DiffusionPipeline, AutoencoderKL

# Load the pipeline
vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
pipe = DiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    vae=vae,
    torch_dtype=torch.float16,
    variant="fp16",
    use_safetensors=True
)
pipe.load_lora_weights("tonyassi/margiela-ss24-fashion-lora")
pipe.to("cuda")

# Generate image
prompt = "Margiela SS24 style, megan fox wearing a gold mesh dress with crystals"
image = pipe(prompt=prompt,
             height=1024, 
             width=1024,
             num_inference_steps=50,
             negative_prompt="ugly, deformed face, deformed body").images[0]
image

```

## Examples
![image/png](https://cdn-uploads.huggingface.co/production/uploads/648a824a8ca6cf9857d1349c/XbpaXbGYKW3lYX1d2t-0G.png)
**Margiela SS24 style, megan fox wearing a gold mesh dress with crystals**

![image/png](https://cdn-uploads.huggingface.co/production/uploads/648a824a8ca6cf9857d1349c/9Qb0SfXG5ASttNXdkUOyT.png)
**Margiela SS24 style, emma stone wearng a pink sequin leotard, puff sleves, rhinestone stockings**

![image/png](https://cdn-uploads.huggingface.co/production/uploads/648a824a8ca6cf9857d1349c/2K_1AuySlkLGi2PpsFllo.png)
**Margiela SS24 style, jeff goldblum**

![image/png](https://cdn-uploads.huggingface.co/production/uploads/648a824a8ca6cf9857d1349c/EPn0Q5oisH7QxKz3cMzdE.png)
**Margiela SS24 style, megan fox wearing a mesh dress with crystals**

![image/png](https://cdn-uploads.huggingface.co/production/uploads/648a824a8ca6cf9857d1349c/pvtqcuvCY28KDq-ZuDZve.png)
**Margiela SS24 style, jeff goldblum wearing a corset**

## Model description
These are tonyassi/margiela-ss24-fashion-lora LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.

The weights were trained  using [DreamBooth](https://dreambooth.github.io/).

LoRA for the text encoder was enabled: False.

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

## Download model
Weights for this model are available in Safetensors format.

[Download](https://huggingface.co/tonyassi/margiela-ss24-fashion-lora/tree/main) them in the Files & versions tab.