Text-to-Image
TF-Keras
English
stable-diffusion
keras-dreambooth
wild-card
dreambooth_dosa_v2 / README.md
bharat-raghunathan's picture
Update model card
984bc0d
|
raw
history blame
1.52 kB
metadata
library_name: keras
license: creativeml-openrail-m
datasets:
  - bharat-raghunathan/indian-foods-dataset
language:
  - en
tags:
  - stable-diffusion
  - text-to-image
  - keras-dreambooth
  - wild-card
widget:
  - text: a picture of bhr dosa

Model description

Dreambooth Stable Diffusion Model fine-tuned on pictures of dosa (the Indian food item)

Intended uses & limitations

Used to generate pictures of dosas in various settings

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