---
library_name: tf-keras
tags:
- diffusers
- stable-diffusion
- text-to-image
- keras-dreambooth
widget:
- text: a photo of traditional cups image in bng clay style
---

## Model description

This model has been fine-tuned by by [Shamima](https://huggingface.co/Shamima) on bengali clay cups and saucers. 

## Intended uses & limitations

Please feel free to make your imaginations run wild and have fun.

## Example images generated
Unique sets of cups using bengali clay pottery style
![Unique sets of cups using bengali clay pottery style](https://s3.amazonaws.com/moonup/production/uploads/1679235507936-61bb7f4d9d77f2f37143a83d.png)

Michelango's David re-imagined in bengali clay pottery style and texture

![Michelango's David re-imagined in bengali clay pottery style and texture](https://s3.amazonaws.com/moonup/production/uploads/1679235591488-61bb7f4d9d77f2f37143a83d.png)
A town of futuristic buildings in clay pottery style

![A town of futuristic buildings in clay pottery style](https://s3.amazonaws.com/moonup/production/uploads/1679235682936-61bb7f4d9d77f2f37143a83d.png)

Unique jewellery pieces in bengali clay pottery style

![Unique jewellery pieces in bengali clay pottery style](https://s3.amazonaws.com/moonup/production/uploads/1679236107863-61bb7f4d9d77f2f37143a83d.png)

## Training and evaluation data

The model was fine-tuned on my personal collection of cups and saucer sets made of clay pottery. Dataset can be found [here](https://huggingface.co/datasets/keras-dreambooth/bengali-clay-cups-dataset).

## 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 |


 ## Model Plot

<details>
<summary>View Model Plot</summary>

![Model Image](./model.png)

</details>