import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("osmr/stable-diffusion-v1-4-lora-db-ghibli")
prompt = "GBL, a man and a woman sitting at a table with glasses of wine in front of them"
image = pipe(prompt).images[0]stable-diffusion-v1-4-lora-db-ghibli
- Prompt
- GBL, a man and a woman sitting at a table with glasses of wine in front of them
- Negative Prompt
- low quality, deformed, ugly, bad art, poorly drawn, bad anatomy, low detail, unrealistic
Model description
diffusers(0.33.1)/train_dreambooth_lora.py --pretrained_model_name_or_path="CompVis/stable-diffusion-v1-4" --dataset_name="osmr/ghibli" --caption_column="prompt" --resolution=512 --center_crop --train_batch_size=8 --gradient_accumulation_steps=1 --num_train_epochs=12 --learning_rate=9e-5 --lr_scheduler=cosine --lr_warmup_steps=32 --rank=16 --train_text_encoder --seed=264893 --instance_data_dir="ds_images" --validation_epochs=1 --validation_prompt="GBL, a man and a woman sitting at a table with glasses of wine in front of them"
Trigger words
You should use GBL to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 8
Model tree for osmr/stable-diffusion-v1-4-lora-db-ghibli
Base model
CompVis/stable-diffusion-v1-4