import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("SedatAl/monet-style-LoRa-1")
prompt = "monet, a landscape of a snowy mountain region big clouds"
image = pipe(prompt).images[0]
- Prompt
- monet, a landscape of a snowy mountain region big clouds
- Prompt
- monet, majestic cliffs overlooking a serene ocean, with dramatic rock formations bathed in soft light. The cliffs are painted in shades of green, ochre, and brown, contrasting with the smooth, flowing waves below, capturing the raw, natural beauty of the landscape
- Prompt
- monet, mountains far back, street lamps shines with warm yellow colors, black night
- Prompt
- Monet garden scene with colorful flowers and reflections on water
- Prompt
- Monet snowy lakeside at sunset
LoRA text2image fine-tuning
These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were fine-tuned on the Aedancodes/monet_dataset dataset.
Trigger words
Trigger words: You should use
Monetto trigger the image generation.
Training details
resolution=1024*1024
train batch_size = 1
max train steps = 1000
learning rate = 5e-5
lr scheduler = constant
mixed precision = fp16
8bit_adam
- Downloads last month
- 10
Model tree for SedatAl/monet-style-LoRa-1
Base model
stabilityai/stable-diffusion-xl-base-1.0