|
|
|
--- |
|
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 |
|
 |
|
**mgm film bettie page outside a mansion with two poodles** |
|
|
|
 |
|
**mgm film asap rocky eating in a fancy restaurant, 1950s** |
|
|
|
 |
|
**mgm film megan fox pinup girl** |
|
|
|
 |
|
**mgm film lady gaga in a limo, neon lights, pet snake** |
|
|
|
 |
|
**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. |
|
|
|
|