README.md

---
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-db-ghibli

<Gallery />

## Model description 

diffusers(0.33.1)&#x2F;train_dreambooth_lora.py
--pretrained_model_name_or_path&#x3D;&quot;CompVis&#x2F;stable-diffusion-v1-4&quot;
--dataset_name&#x3D;&quot;osmr&#x2F;ghibli&quot;
--caption_column&#x3D;&quot;prompt&quot;
--resolution&#x3D;512
--center_crop
--train_batch_size&#x3D;8
--gradient_accumulation_steps&#x3D;1
--num_train_epochs&#x3D;12
--learning_rate&#x3D;9e-5
--lr_scheduler&#x3D;cosine
--lr_warmup_steps&#x3D;32
--rank&#x3D;16
--train_text_encoder
--seed&#x3D;264893
--instance_data_dir&#x3D;&quot;ds_images&quot;
--validation_epochs&#x3D;1
--validation_prompt&#x3D;&quot;GBL, a man and a woman sitting at a table with glasses of wine in front of them&quot;

## Trigger words

You should use `GBL` to trigger the image generation.


## Download model

Weights for this model are available in Safetensors format.

[Download](/osmr/stable-diffusion-v1-4-lora-db-ghibli/tree/main) them in the Files & versions tab.