Recently updated on 12 6 月, 2023 at 04:57 上午
注意这是一个loha模型，This model is a LoCon. You MUST install the Lycoris extension for it to load.
以下作者原文：
This model is a LoCon. You MUST install the Lycoris extension for it to load.
I’m using Lora Block Weight. I believe you can also use Additional Networks and SD Webui Lycoris.
UPDATE 4/27/2023: I’ve hit a training plateau so I’m in the process of adding a bunch more images to the dataset, including some more complicated stuff like intertwined fingers. I’m probably going to have to drop the learning rate some more, so things may be slower from here on. I’ll keep everyone posted as things progress.
UPDATE: Prompting advice for beta 2:
This is a completely new train on top of vanilla Stable Diffusion 1.5. I did this based on the advice of a fellow enthusiast, and it’s surprising how much more compatible it is with different model. It doesn’t mess with the style of your model at all as far as I can tell, and it really only affects hands and occasionally arms, leaving everything else untouched.
It seems to work best at a strength of 1, although turning up higher than that (1.5, 2, etc) can help it on some images at the cost of making it worse on others. No need to mess with your CFG scale, as it doesn’t cause things to overcook at these levels.
Freely mix it with other LoRAs.
I’ve had best results putting “nice hands, perfect hands” in the positive prompt (increasing the weight makes things worse), and “(extra fingers, deformed hands, polydactyl:1.5)” in the negative prompt. This is on EnvyMix v1 (and probably RevAnimated), but YMMV for other models.
“Bad hands” negative embeddings appear to make it worse, although I haven’t tested this extensively.
As usual, this won’t work miracles, but I do find that over a large number of images, it does make things generally better on average. Hopefully this will continue to improve with a few more nights of training.
原文链接：https://cj.suclub.top/3683.html，转载请注明出处。
请先 ！