Model description
Dreambooth fine-tuned for pictures of my dog, Teddy. Prompts with "teddy_holmes dog" as the unique identifier + class label.
The model seems overtrained on the poses supplied in the training images.
About Teddy
Teddy is a Mini Double Doodle. He's the offspring of a Labradoodle and a Mini Golden Doodle, so he is one half Poodle, one quarter Labrador Retriever, and one quarter Golden Retriever.
Examples
Intended uses & limitations
Anyone is welcome to use the model if they want to generate pictures of an adorable dog doing interesting things.
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 |
Model Plot
- Downloads last month
- 11
Inference API (serverless) does not yet support keras models for this pipeline type.