Create & Edit Images Instantly with Grok Imagine

Try Grok Imagine
Skip to main content
Koji - V2 thumbnail

Koji - V2

by ModelsLab
koji-v2
Text to Image Community ModelFree for Premium UsersLLMs.txt

Stabilized the model with further merged, but mostly with hassaku. To fix many problems from the training attempt.

Because of that, it looks and behave mostly like hassaku now. But is more swf oriented, produce better backgrounds and does't want to lewd everything (mostly). Drawback, it lost its trained "glow" look of V1 and the darker nights.

API PlaygroundAPI Documentation