|
--- |
|
library_name: keras |
|
tags: |
|
- keras-dreambooth |
|
- scifi |
|
license: cc-by-nc-4.0 |
|
--- |
|
|
|
## Model description |
|
|
|
This Stable-Diffusion Model has been fine-tuned on images of the Star Trek Voyager Spaceship. |
|
|
|
Here are some examples using the following Hyperparameters: |
|
|
|
Prompt: photo of voyager spaceship in space, high quality, 8k |
|
|
|
Negative Prompt: bad, ugly, malformed, deformed, out of frame, blurry, cropped, noisy |
|
|
|
Denoising Steps: 50 |
|
|
|
Guidance Scale: 7.5 |
|
|
|
 |
|
 |
|
 |
|
|
|
## Intended uses & limitations |
|
|
|
Anyone may use this model for non-commercial usecases under the Linked License, as long as Paragraph 5 of the [Open RAIL-M License](https://raw.githubusercontent.com/CompVis/stable-diffusion/main/LICENSE) are respected as well. The original Model adheres under Open RAIL-M. |
|
|
|
It was made solely as an experiment for keras_cv Dreambooth Training. |
|
|
|
## 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 | |
|
|
|
|
