第一次训练lokr，比lora构图控制要好些，更快，自然语言和tag切换平滑，但风格特别是笔触拟合的不到位，不知道是这种强调笔触的风格不大适合Prodigy还是步数和dim给的太低了This is my first time training with Lokr. The composition control is better and faster than with Lora, and the transitions between natural language and tags are smooth. However, the style, especially the brushstroke fitting, is not quite right. I'm not sure if this brushstroke-focused style isn't well-suited to Prodigy, or if the steps and dim settings are too low.如果喜欢此风格，请支持原作者If you like this style, please support the original author<span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">为了防止触犯相关规则抹掉了一部分训练元数据，尝试时有什么负面影响请及时反馈

Files with SHA256: b187037becc0a73e89a98e0aac5389bc8fe9c29cd19ba9dbbe20cce402baf170