|
--- |
|
library_name: keras |
|
datasets: |
|
- moizsajid/dreambooth-markhor |
|
pipeline_tag: text-to-image |
|
--- |
|
|
|
## Model description |
|
|
|
This is a Stable Diffusion model fine-tuned using Dreambooth on markhor images. |
|
|
|
## Intended uses & limitations |
|
|
|
Submission for keras-dreambooth sprint |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
|
|
| Hyperparameters | Value | |
|
| :-- | :-- | |
|
| name | RMSprop | |
|
| weight_decay | None | |
|
| clipnorm | None | |
|
| global_clipnorm | None | |
|
| clipvalue | None | |
|
| use_ema | False | |
|
| ema_momentum | 0.99 | |
|
| ema_overwrite_frequency | 100 | |
|
| jit_compile | True | |
|
| is_legacy_optimizer | False | |
|
| learning_rate | 0.0010000000474974513 | |
|
| rho | 0.9 | |
|
| momentum | 0.0 | |
|
| epsilon | 1e-07 | |
|
| centered | False | |
|
| training_precision | float32 | |
