adhisetiawan/sdxl-base-1.0-indonesian-food-dreambooth-lora

<!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. -->

SDXL LoRA DreamBooth - adhisetiawan/sdxl-base-1.0-indonesian-food-dreambooth-lora

<Gallery />

Model description

These are adhisetiawan/sdxl-base-1.0-indonesian-food-dreambooth-lora LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.

The weights were trained using DreamBooth.

LoRA for the text encoder was enabled: True.

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

Trigger words

You should use a photo of bakso to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Intended uses & limitations

How to use

import torch
from diffusers import DiffusionPipeline

# Load Stable Diffusion XL Base1.0
pipeline = DiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    torch_dtype=torch.float16,
    variant="fp16",
    use_safetensors=True
).to("cuda")

# Optional CPU offloading to save some GPU Memory
pipeline.enable_model_cpu_offload()

# Loading Trained DreamBooth LoRA Weights
pipeline.load_lora_weights("adhisetiawan/sdxl-base-1.0-indonesian-food-dreambooth-lora")

images = pipeline(
            "a delicous takoyaki in a plate", num_images_per_prompt=4, guidance_scale=8
        )
for i in range(len(images.images)):
  display(images.images[i])

Limitations and bias

[TODO: provide examples of latent issues and potential remediations]

Training details

[TODO: describe the data used to train the model]