keras-dreambooth/pink-floyd-division-bell

Model description

This model is a stable diffusion keras model fine tuned using dreambooth. This model has been fine tuned to learn the concept of pink floyd's division bell album cover. To generate images including this concept, use this in your prompt - "pink floyd division bell album cover".

Intended uses & limitations

It can be used to generate images of your choice using a text prompt.

Training data

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

This model was contributed by Shivalika Singh