lora.continue / BlueArchiveLORA.md
johnsmith007's picture
Rename blue_archive_style_LOR.md to BlueArchiveLORA.md
98b768e
|
raw
history blame
5.53 kB

Update V7: For compatibility reason, V7 is a LoRA model! Also Base model has changed to expmixlinev3! Add color control and use a totally different trigger word. Now you can use BAPV to trigger the effect, and use colour scheme like Blue Theme to tilt the color.

For the best result, you should choose unipc sampler & use 4x-ultrasharp as upscaler.

Since the training data is based on Blue Archive's PV & CG screenshot, this LoRA do not very capable with NSFW content.

Support color scheme in grid:

This LoRA may cause bad hand more easily. Didn't find a best solution, but those typical hand fix methods still work, just not that effective.

The reason I changed the base model to expmix is it is easier than Any, has a better background and a very good compatibility with character LoRA, so this should be good enough. I guess.

Still, it only works perfectly without any charactor LoRA. You can get similar result with charactor LoRA, but you need to be patient.

Weight 1 is good enough. About 0.7-1.2 is working zone. Lower will show the typical thick line from base model, Higher will cause bad anotomy every time.

The method below is only for older LoHA version.

V4 is MUCH better and easier to use, trained on anyv3, test on anyv5. The method below do still work but not necessary any more. Compared to Bluemix (the 4g ckpt model), this LoHA is more capable with character LoRA, it will tend to be keeping character's facial characteristic and outfit, only change the line and coloring. (like a color filter rather than totally different art style).

If you like the character be fully switch to BA art style, generating OC or don't care about the LoRA character's outfit, I suggest you to use BlueMix instead.

Suggestion:

use nature language to generate base environment (e.g. A girl is standing alongside the river.)

weight 0.8-1, (higher value for better result but worse anatomy, vice versa.)

base resolution: w or h lower than 768x768, over will cause the image broken more often.

base model: suggest anyv3/v5, not recommend any oil painting/pastel model like AOM series or counterfeit. It CAN use, but is only a color filter.

environment prompts (still work!):

Blue Archive-ish theme (Millennium?): tree, cloud, road, city, day, blue sky, outdoors

Japanese theme (Hyakkiyako?): cloud, day, outdoors, cherry blossoms,

Nightsky: night, night sky, starry sky,

You can try other tags generated by taggers of Blue Archive CGs.

===

I'm learning how to make a LoHA/artstyle model. This is my first step result, my PC isn't very good for testing so I release it for more feedbacks from your side, so this is basically an Alpha test, the model do work but not very user-friendly. If you want to get a good result, you should know how to use lora block weight. If you don't know how to use it but still have interest on learning some new tricks, then read the following guide. My goal is make a artstyle LoHA that is capable to most of chara LoRAs.

So I trained it on Animefull-pruned, works perfectly on that one and Anything V3, will work on AnythingV4.5 without character LoRA, but almost won't work on Counterfeit or AOM3. It will more likely a color filter than an art style on those models.

Maybe I should train another version based on AnythingV4.5. If you have any suggestion about art style training, let me know. I will be very appreciate of that.

It can work without tags, but sometimes will make weird color.

Here are some tag groups for more stable results:

Blue Archive-ish theme (Millennium?): tree, cloud, road, city, day, blue sky, outdoors

Japanese theme (Hyakkiyako?): pink theme, cloud, day, outdoors, cherry blossoms,

Nightsky: blue theme, night, night sky, starry sky, cityscape,

You can try other tags generated by taggers of Blue Archive CGs.

You 'd better use it with LoRA block weight if you want to input a character lora. You can get it as webui plugin. Otherwise you should lower this model's weight to below 0.6, which will work bit poorly but still work, or it will make the image color very awful.

↓If you get something like this, lower the artstyle model weight, or use the method below.

When you use it with LoRA block weight, there are 2 methods:

A: By default, you should remove your charactor lora's artstyle by this:

YourCharaModelName:1:1,1,1,1,1,0,0,0,1,1,1,1,1,1,1,0,0

don't forget to add :ALLto this model or it may won't be working.

e.g. BArstylev1c:1:ALL

B: If you noticed that your character's appearance has been obviously affected by this model, keep only the color of the artstyle model instead like this:

BArstylev1c:1:1,0,0,0,0,0,0,0,0,0,0,0.8,1,1,1,1,1

In this situation, you can keep Charactor model in full.

e.g. YourCharaModelName:1:ALL

Basically, method A will works more like the original artstyle than method B.

It seems that LoHA model have more block weights, I don't have much time to test since my PC will easily crash on it, if you have some information about it, please tell me. But so far using LoRA block weight is fine.

↓Still, if you get everything right but still got something like this, try to use the second way instead.

method_a Method A when the charactor is affected.

method_b Method B