SDXL LoRA DreamBooth - imomayiz/moroccan_sdxl_lora

Model description

These are LoRA weights of sdxl-base-1.0 finetuned on modern moroccan cities images.

The weights were trained using DreamBooth.

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

Trigger words

You should use "modern moroccan city" to trigger the image generation.

Download model

Weights for this model are available here.

Dataset

The training images can be found here.

How to use the model

import torch
from diffusers import DiffusionPipeline, AutoencoderKL

repo_id = "imomayiz/moroccan_sdxl_lora"

# load lora weights and 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(repo_id)
_ = pipe.to("cuda")


prompt = "a photo of a modern moroccan city" 

# generate the image
image = pipe(prompt=prompt, num_inference_steps=30).images[0]
image