I initially tried to release this a few days ago however, I wasn't satisfied with the results so here is another attempt at training and re-uploading. This is meant to generate a Polaroid look of individuals sitting on a car late at night. So you may want to include something along those lines in your prompt

You may want dial back on the weight as it can be a little heavy handed. start around 0.7 and work your way up.

Also tend to add the monster energy drink, so you may want to negative prompt to counterbalance this

Trigger words

You should use longnightout to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('brushpenbob/late-night-out', weight_name='late night out_epoch_12.safetensors')
image = pipeline('`longnightout`').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers