peki12345

感谢大佬开源这个工程，想请教个问题

4

我的音源量足够，但是质量可能不太够。这个工程对数据质量要求应该比较高，因为我用3小时普通话纯人声（无手动打标）训出来的模型效果只能算差强人意。在这种情况下，我只能手动一条条打标，筛选出质量高的片段吗，但这个工作量有点大了。想请问各位大佬还有没有什么更省人工的方式。

For inpaint_v26.fooocus.patch

8

Hi, I'm interested in learning about the training process for the "inpaint_v26.fooocus.patch" used in inpainting or outpainting task. Is there any training code or paper related to this?

For the features of concat LLMs and CLIP features

2

Nice work! I have a question, why should we concat these two features(LLMs and CLIP) instead of just using LLMs' features, as some other works have done: https://github.com/Kwai-Kolors/Kolors