<h1 id="songvae-xx8i85gi3">songVAE</h1>The 1,000 training images output by songMix were trained for a total of 80,000 steps, and the model was further refined.The emphasis is on depicting the skin color of people and correcting blown-out highlights in the background.~songMixで出力した教師画像1000枚を総計80000stepで学習させ、調整を重ねました。人物の肌の色の描写と背景の白とび修正に重点を置いています。

Files with SHA256: 3ba59967a334a4baf95ccfe585e125369102bc5a6b80af687825ac83a22bb442