---
library_name: keras
license: apache-2.0
tags:
- keras
- stable-diffusion
- text-to-image
- keras-dreambooth
- consentful
---

## Model description

This is a Keras Dreambooth model fine-tuned to some 18th century etching artworks by italian artist [Giambattista Piranesi](https://en.wikipedia.org/wiki/Giovanni_Battista_Piranesi).

A few samples below

![](output-samples/db-piranesi_0.jpg) ![](output-samples/db-piranesi_1.jpg) ![](output-samples/db-piranesi_2.jpg) ![](output-samples/db-piranesi_3.jpg)
![](output-samples/db-piranesi_4.jpg)

## Intended uses & limitations

The base prompt is "image of monuments in sks style". 
A slightly better prompt would be "image of monuments in sks style, 8k, high quality, old paper" with negative prompt "distorted".

## Training procedure


### Training hyperparameters

The following hyperparameters were used during training:

| Hyperparameters | Value |
| :-- | :-- |
| inner_optimizer.class_name | Custom>RMSprop |
| inner_optimizer.config.name | RMSprop |
| inner_optimizer.config.weight_decay | None |
| inner_optimizer.config.clipnorm | None |
| inner_optimizer.config.global_clipnorm | None |
| inner_optimizer.config.clipvalue | None |
| inner_optimizer.config.use_ema | False |
| inner_optimizer.config.ema_momentum | 0.99 |
| inner_optimizer.config.ema_overwrite_frequency | 100 |
| inner_optimizer.config.jit_compile | True |
| inner_optimizer.config.is_legacy_optimizer | False |
| inner_optimizer.config.learning_rate | 0.0010000000474974513 |
| inner_optimizer.config.rho | 0.9 |
| inner_optimizer.config.momentum | 0.0 |
| inner_optimizer.config.epsilon | 1e-07 |
| inner_optimizer.config.centered | False |
| dynamic | True |
| initial_scale | 32768.0 |
| dynamic_growth_steps | 2000 |
| training_precision | mixed_float16 |