Experiments / README.md
Guizmus's picture
Update README.md
500e94a
|
raw
history blame
2.53 kB
metadata
license: creativeml-openrail-m
inference: false

Guizmus' test models

Those are medium to low quality models, single focus usualy, that can bring some fun but not really do significant things.

I'm not sharing the diffusers, just the ckpt and some examples.

You can also find my models relating to the Picture of the Week on Stable Diffusion discord here


TMNT v1.0

Simsbooth person

  • training: 11 pictures, 1000 steps on 5e-6 polynomial LR with 8 bit adam
  • Activation token : TMNT person
  • Model link

Sid v1.0

Simsbooth person

  • training: 10 pictures, 2500 steps on 1e-6 polynomial LR
  • Activation token : Sid
  • Model link

Kirby v1.0

Simsbooth person

  • training: 10 pictures, 2500 steps on 1e-6 polynomial LR
  • Activation token : Kirby
  • Model link

Simsbooth v1.0

Simsbooth person

  • training: 122 pictures, 18k steps on 1e-6 polynomial LR
  • Activation token : Simsbooth person
  • Model link

Hogleg Style v2.4

Hogleg Style

  • training: 5k steps lr 1e-6, 122 samples, then 2k more steps on a lower lr and a rebalanced dataset
  • Activation token : HogLeg Style
  • Model link

Illusion v1.0

Illusion

  • training: 1k2 steps, 12 samples
  • Activation token : Illusion drawing
  • Model link

NikeAir v1.0

NikeAir

  • training: 1k2 steps, 10 samples
  • Activation token : NikeAir Shoes
  • Model link