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

## Model description

This is a Keras Dreambooth model fine-tuned to images of galaxy mergers taken with the [Hubble Space Telescope](https://en.wikipedia.org/wiki/Hubble_Space_Telescope).
In particular, I selected mergers at intermediate stages (3-4 [here](https://sci.esa.int/web/hubble/-/42637-merger-stages-of-interacting-galaxies)), where the two bodies
of the merging galaxies are still recognizeable and/or a bridge of material connecting the two galaxies is clearly visible.
Credit for the training images goes to ESA/Hubble: images can be found on their [website](https://esahubble.org/images/) selecting the category of [interacting galaxies](https://esahubble.org/images/archive/search/?category=560&adv=&facility=2).

### Sample Outputs

A few ouput samples of the Dreambooth model below.

**prompt**: `image of sks galaxies merging in space`
![](output-samples-mergers/db-mergers_collage.jpg) 

**prompt**: `painting of sks galaxies merging in van gogh style, 8k, high quality, trending on artstation`
![](output-samples-mergers/db-mergers-vangogh_collage.jpg) 

#### *Cosmic Hugs*: an artistic rendition of galaxy collisions

![](output-samples-mergers/cosmichugs.png) 


## Intended uses & limitations

This model has similar intended uses & limitations as any Stable Diffusion and Dreambooth models (see e.g. [this model](https://huggingface.co/stabilityai/stable-diffusion-2-1)).
In particular, this model should be used with a prompt containing `sks galaxies merging`.

## Training and evaluation data

More information needed

## 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 |