UNET only trained model on small dataset. Due to presence of old images in dataset resembles averaged over time nowa's style.To my eye on anima works worse than on illustriousIf you are experiencing resemblance issues on SD-Forge-Neo try changing in settings option Stable Diffusion -&gt; Compability -&gt; Try to reproduce the results from external software -&gt; Comfyui

NowaJoestar Style Pony/Illustrious/AnimaP

set to continue learning and didn't notice lol no more noise offset - makes worsetag adjustementstry new tagging: kill la bitch styled OR game styled

Files with SHA256: 6eb0285a2d0145e3d3a3132552bb8f52b7a44984f052035d3cb1f9c605bf986f