mgm / README.md
tonyassi's picture
Update README.md
fed443e verified
---
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: mgm film
license: openrail++
---
# SDXL LoRA DreamBooth - tonyassi/mgm
by [Tony Assi](https://www.tonyassi.com/)
Dreambooth style based on classic MGM Films. Try the [demo](https://huggingface.co/spaces/tonyassi/MGM-Film-Diffusion).
## Trigger words
Use **mgm film** in the prompt to trigger the MGM 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/mgm")
pipe.to("cuda")
# Generate image
prompt = "mgm film megan fox pinup girl"
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/wIOrSpg1A3EGGxyeHxUJP.png)
**mgm film bettie page outside a mansion with two poodles**
![image/png](https://cdn-uploads.huggingface.co/production/uploads/648a824a8ca6cf9857d1349c/zWFdlerT_WVBTwHWFZVa5.png)
**mgm film asap rocky eating in a fancy restaurant, 1950s**
![image/png](https://cdn-uploads.huggingface.co/production/uploads/648a824a8ca6cf9857d1349c/cbZ-wYXU-2y_BkZWFiw9P.png)
**mgm film megan fox pinup girl**
![image/png](https://cdn-uploads.huggingface.co/production/uploads/648a824a8ca6cf9857d1349c/WQTf4lsKq83Depv2Uag6_.png)
**mgm film lady gaga in a limo, neon lights, pet snake**
![image/png](https://cdn-uploads.huggingface.co/production/uploads/648a824a8ca6cf9857d1349c/qZFcvpxZZyx46D0aMgN5M.png)
**mgm film asap rocky in the wizard of oz**
## Model description
These are tonyassi/mgm 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/mgm/tree/main) them in the Files & versions tab.