CoolFace
Modelpublic

keras-dreambooth/dreambooth-galaxy-mergers

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes16downloads
Model Card

Model description

This is a Keras Dreambooth model fine-tuned to images of galaxy mergers taken with the Hubble Space Telescope. In particular, I selected mergers at intermediate stages (3-4 here), where the two bodies of the merging galaxies are still recognizeable and/or a bridge of material connecting the two galaxies is clearly visible. Credit for the training images goes to ESA/Hubble: images can be found on their website selecting the category of interacting galaxies.

Sample Outputs

A few ouput samples of the Dreambooth model below.

prompt: image of sks galaxies merging in space [image]

prompt: painting of sks galaxies merging in van gogh style, 8k, high quality, trending on artstation [image]

Cosmic Hugs: an artistic rendition of galaxy collisions

[image]

Intended uses & limitations

This model has similar intended uses & limitations as any Stable Diffusion and Dreambooth models (see e.g. this model). In particular, this model should be used with a prompt containing sks galaxies merging.

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

HyperparametersValue
inneroptimizer.classnameCustom>RMSprop
inner_optimizer.config.nameRMSprop
inneroptimizer.config.weightdecayNone
inner_optimizer.config.clipnormNone
inneroptimizer.config.globalclipnormNone
inner_optimizer.config.clipvalueNone
inneroptimizer.config.useemaFalse
inneroptimizer.config.emamomentum0.99
inneroptimizer.config.emaoverwrite_frequency100
inneroptimizer.config.jitcompileTrue
inneroptimizer.config.islegacy_optimizerFalse
inneroptimizer.config.learningrate0.0010000000474974513
inner_optimizer.config.rho0.9
inner_optimizer.config.momentum0.0
inner_optimizer.config.epsilon1e-07
inner_optimizer.config.centeredFalse
dynamicTrue
initial_scale32768.0
dynamicgrowthsteps2000
training_precisionmixed_float16