metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: >-
GBL, a man and a woman sitting at a table with glasses of wine in front of
them
parameters:
negative_prompt: >-
low quality, deformed, ugly, bad art, poorly drawn, bad anatomy, low
detail, unrealistic
output:
url: images/test1_gs75_ls10.jpg
base_model: CompVis/stable-diffusion-v1-4
instance_prompt: GBL
license: mit
stable-diffusion-v1-4-lora-iv-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_text_to_image_lora.py --pretrained_model_name_or_path="CompVis/stable-diffusion-v1-4" --dataset_name="osmr/ghibli" --caption_column="prompt" --resolution=512 --center_crop --random_flip --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 --noise_offset=0.01 --mixed_precision=fp16 --seed=264893 --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.