Loading
Model intended to generate more realistic tongues and mouths.
Model source
Source description
Features:
Reduced the number of unwanted artifacts
Improved consistency
Training:
2k selected images
20k steps, batch size 4
Learning rate 5e-5:2000, 5e-6:10000, 5e-7:20000
Hypernet structure 1,4,1
Hardware AWS R5g.xlarge
Duration 24h
Sources
1 sourceModel artifacts
1 artifactSource excerpts
2 excerptsSource context: 5488 downloads · Type Hypernetwork · Base model SD 1.5
Source context: 5439 downloads · Type Hypernetwork · Base model SD 1.5