Downloads · 30 days
19
11% of all-time downloads
dreambooth_kedis
keras-dreambooth/dreambooth_kedis
dreambooth_kedis is a text-to-image model from keras-dreambooth. Use it when you need an image from a text prompt. It is set up for keras.
This is a fine-tuned Stable Diffusion using DreamBooth technique, fine-tuned on my cat Kediş. Kediş means kitten in Turkish. She's a tabby cat whom I've adopted from street. You can find the Space for this model here.
All-time downloads
179
Public
Repo size
3.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.data-00000-of-000013.4 GB · 99%
At a glance
- Task
- Text-to-Image
- Library
- keras
- Access
- Public
- Created
- Mar 17, 2023
- Updated
- Mar 17, 2023
- SHA
- 4a09d798
Model card
From the Hugging Face model README
Model description
This is a fine-tuned Stable Diffusion using DreamBooth technique, fine-tuned on my cat Kediş. Kediş means kitten in Turkish. She's a tabby cat whom I've adopted from street. You can find the Space for this model here.
Training procedure
You can find the notebook to train these models and how to attend this sprint here.
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>
- Task
- Text-to-Image
- Library
- keras
- Created
- Mar 17, 2023
- Updated
- Mar 17, 2023