import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("keras-dreambooth/dreambooth_diffusion_clay_cups", dtype=torch.bfloat16, device_map="cuda")
prompt = "a photo of traditional cups image in bng clay style"
image = pipe(prompt).images[0]Model description
This model has been fine-tuned by by 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
Michelango's David re-imagined in bengali clay pottery style and texture
A town of futuristic buildings in clay pottery style
Unique jewellery pieces in bengali clay pottery style
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.
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
View Model Plot
- Downloads last month
- 12