Trained and merge , use clip 2, &gt; 768 *768 is finelose some art style, next version will fix this.Caption by LLM model , can recognize different tags.Use simple negative prompt. You can try different settings.====================Feedback is important to me ,Thanks for your likes and follow.You can try it on <a target="_blank" rel="ugc" href="http://ai-creator.net">ai-creator.net</a> and <a target="_blank" rel="ugc" href="http://ai-creator.net/arts">ai-creator.net/arts</a> with tags,based on different model or styles.

Files with SHA256: ad2d3a51a08c54030dde55d0411c9ef0f27fb64a27e9c3240f8fe281213200a1