README.md · keras-dreambooth/dreambooth_diffusion

metadata

library_name: tf-keras
license: creativeml-openrail-m
tags:
  - diffusers
  - stable-diffusion
  - text-to-image
  - keras-dreambooth
  - scifi
widget:
  - text: a photo of hks## toy

Model description

This model has been fine-tuned to learn the concept of Mother rabbit toy by ChienVM on this dataset

Intended uses & limitations

Concept token "hks## toy". Example: "a photo of hks## toy "

Some examples prompt

Sample 1 — Prompt: a photo of hks## toy in Santa Claus clothes. Negative prompt: bad anatomy, soft blurry. Steps: 50, CFG scale: 7.5, Size: 512x12

Sample 2 — Prompt: a oil painting of hks## toy in style of van gogh. Negative prompt: bad anatomy, soft blurry. Steps: 50, CFG scale: 7.5, Size: 512x12

Sample 3 — Prompt: a photo of hks## toy standing on the beach at sunset. Negative prompt: bad anatomy, soft blurry. Steps: 50, CFG scale: 7.5, Size: 512x12

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