trained on chenkin noob v0.2
Description
Same training dataset, network/conv dim/alpha were simply adjusted, halving the file size. It behaves much better with upscaling and has higher fidelity to the actual style.
trained on chenkin noob v0.2
Same training dataset, network/conv dim/alpha were simply adjusted, halving the file size. It behaves much better with upscaling and has higher fidelity to the actual style.