- Jan 31, 2022
- 208
- 631
Very Basic guide on how to use Reactor
You don't have permission to view the spoiler content.
Log in or register now.
Last edited:
That would depend on what checkpoint you intend to use it with.Hey. Whats the best model to use training lora?
I would look at the mean ar error (without repeats) with that many images. If it is in the 100th decimal your probably okIm using google colab to train. I have 735 pics. How many repeats and epochs should i do? 10 epochs, 3 batch, 10 repats says too much steps.
Im training with thisI would look at the mean ar error (without repeats) with that many images. If it is in the 100th decimal your probably ok
(I have locally trained high error lora's in the 10ths for ar error, I think I trained 680 images with an AR error of 0.4)
Train on the EMA checkpoint if you can forYou must be registered to see the links(I can't find the un-pruned EMA checkpoint anymore)
The XL EMA weights I recall being 16GB I can not find the checkpoint anymore.
EMA is more important for refinement then for a LORA.
Unless your training a style, the base EMA model produces a lora with wider range.
You could do a batch size of 4 and probably 4 epochs as your well over 10,000 steps
Shold i change to the sd training model too?I would look at the mean ar error (without repeats) with that many images. If it is in the 100th decimal your probably ok
(I have locally trained high error lora's in the 10ths for ar error, I think I trained 680 images with an AR error of 0.4)
Train on the EMA checkpoint if you can forYou must be registered to see the links(I can't find the un-pruned EMA checkpoint anymore)
The XL EMA weights I recall being 16GB I can not find the checkpoint anymore.
EMA is more important for refinement then for a LORA.
Unless your training a style, the base EMA model produces a lora with wider range.
You could do a batch size of 4 and probably 4 epochs as your well over 10,000 steps
Think the problem is the paywall in google colabI would look at the mean ar error (without repeats) with that many images. If it is in the 100th decimal your probably ok
(I have locally trained high error lora's in the 10ths for ar error, I think I trained 680 images with an AR error of 0.4)
Train on the EMA checkpoint if you can forYou must be registered to see the links(I can't find the un-pruned EMA checkpoint anymore)
The XL EMA weights I recall being 16GB I can not find the checkpoint anymore.
EMA is more important for refinement then for a LORA.
Unless your training a style, the base EMA model produces a lora with wider range.
You could do a batch size of 4 and probably 4 epochs as your well over 10,000 steps
Based off of the error message your trying to use CPU training and need toThink the problem is the paywall in google colab
GPU connection cannot be established due to Colab usageBased off of the error message your trying to use CPU training and need toYou must be registered to see the links
The drop down your showing is non EMA base checkpoint so in that case I would just use what ever model is closest to the style your going for.
With an image count that high you might want to lower the LR to 1e-6 for the U-NET and 5e-7 for the TE
There is a fork for it, but I haven't tried it yet.PSA regarding Forge, looks like it is no longer being maintained. Pity, as it is my main program to generate images
You must be registered to see the links
What UI are you using?I just started playing with this, its been a lot of fun. I have three questions.
1) lets say I have a prompt in txt2img and I create 25 images, and one is Perfect the other 24 not so much. is there a way to take that one image and train SD to do a better job with the same prompt?
2) I used a Lora to lock in the face, but also need to lock in the cloths so I can try my hand at making a game. Is there a way to lock those in>
3) if I want a image without a background for ez import to renpy is there a prompt for that?
What UI are you using?
when you say CUI do you mean ComfyUI? I just started looking into ComfyUI, seems like what I was looking for.i've used a1111 for many time, but i've switched to CUI.
So some possible answer:
1) you can train Lora with result image, but result is not sure. Lora train is not so simple, understanding every value for training, and all settings is not so simple in the begins, but you can try and see. Experimenting is the way. For train lora i suggest to useYou must be registered to see the links
2) in the same way for face, you can use lora for dress.
3) not prompt, there are some extensions doing it, but i checked it only on CUI, i can't point to right extensions for a1111 because i never checked on it.
A1111 is good and i had a fun for many time, but CUI is more powerfull for me, that node UI permit some workflow that is so difficult to remake in a1111. But this is my opinion, there are many skilled people's and everyone work good on UI they use.