Never Alone Influence

I am admittedly kind of a noob at this, but if you enjoy my humble work, any donations are greatly appreciated: https://ko-fi.com/insult_to_ninjary

Your generosity helps me stay motivated to keep improving and to keep trying new things!

Trigger Words:

Main trigger: n3v3r4l0n3

Helper prompts: parody, style parody, 2.5d

• The LoRA can potentially work with no triggers, but it may not be strong/consistent.

• For a stronger effect, use the main trigger: n3v3r4l0n3. You can also weight it numerically or with parentheses - I usually do (((n3v3r4l0n3))).

• If the (weighted) main trigger is still not enough by itself, next try the helper prompts along with the main trigger. They can be weighted as well - I usually do them all together, like (((n3v3r4l0n3, parody, style parody, 2.5d))).

• The "2.5d" trigger is not totally necessary, but I do feel that it sometimes helps give the model a little extra push towards the appropriate style. Other times, it doesn't seem to do all that much. I recommend using it since it doesn't really hurt anything, but you can also leave it out if you're trying to prompt shorter.

• Please note that the main trigger here is only for the Illustrious model - it won't work for the SD1.5 model. The helper prompts may or may not work for SD1.5 (I never tried them), but they are not necessary as the SD1.5 LoRA works just fine with no triggers!

At a Glance (Illustrious):

• Base model: Various styles should work (I usually use my own Illustrious merge or WAI)

• LoRA weight: 1 (but slowly go lower or higher if necessary)

• Suggested parameters: Euler a, Automatic, 30 steps, 832x1216/1216x832, CFG 5 (but feel free to experiment!)

• Hires. fix: 1.5x, use a quality upscaler (like 4x-UltraSharpV2), denoising strength 0.5 - 0.3

• Extra: use ADetailer to fix faces and/or hands if necessary

Illustrious Version Description:

Sadly, the style didn't come out as strongly as I had hoped for this LoRA, but it still does a few things right. Namely, this LoRA will give you a slightly more 2.5D style image, a muted color palette (usually blue, grey, or brown in tone), and dilapidated background structures. This seems like more of a vibe LoRA than a precise style LoRA. You'll get images noticeably in the spirit of the video game Never Alone, but they usually won't nail the style super closely (unless you get lucky or work some prompting magic). Below I'll address some of it's other shortcomings.

First, it can be a little fuzzy and lacking in fine details. Like, if you zoom in or check some fine details closely, they can appear kind of muddy or garbled. This is especially true with stuff like fingers, accessories, fine details in the background, etc. I don't consider this a dealbreaker though, and you can fix a lot of this with a little extra work if you feel the need.

Second, outdoor shots seem to capture the style a bit better than indoor shots. This is because, as you might expect, most of the training data consisted of outdoor shots from the game. You will see an effect on indoor shots, but it can sometimes be a bit more subtle, as the LoRA shines a bit better when given nature and scenery to influence.

Finally, it has some trouble keeping track of objects that move behind other objects, if that makes any sense. Like if there is a bed behind the main character, the bed might not line up properly on each side of the character. This seems to be a general Illustrious issue in my experience, but this LoRA also doesn't do anything to remedy it. So you may need to do some post-processing, or just hope for good seed RNG.

For more potentially relevant information, you can check out the original SD1.5 description immediately below. Below that, there's a troubleshooting section in case you're having any problems.

SD1.5 Version Description:

This LoRA will give your art an influence from the video game Never Alone. It won't be able to exactly recreate the art style, but you can get some close likenesses with good prompting, and you'll still generally get the vibe from the game even with lazy prompting (like mine, lol). I may have overcooked it a bit, so if you're having problems, a general solution is to lower the LoRA's weight (try between 1 and 0.7, but you might be able to go even a bit lower if absolutely necessary).

Here's the kind of influence you can generally expect from the LoRA (though it can be a bit dependent on your prompting): 1) Snowy, icy, hazy, washed-out, blue-toned backgrounds, 2) random glowing lights or light streaks (usually blue or white), 3) higher occurrence of thicker clothes (often with fur trim, but not always), 4) face structure and body proportions similar to the main character of the game.

Due to a case of possibly overcooking, here are some drawbacks you might come across:

1) It really tries to force a zoomed-out 2.5D platformer perspective, with very small or no characters. You can combat this by lowering the weight of the LoRA, as mentioned above.

2) In certain instances, it really likes to generate dudes even if you prompt for 1girl (and idk why bcz I don't think there were even any males in the training images). You can likely fix this by adjusting your positive and negative prompts and/or lowering the LoRA's weight.

3) It sometimes likes to generate 2 characters, even if you don't prompt for that. To correct this, adjust your positive/negative prompts and/or lower LoRA weight.

4) It seems to favor side profiles or angled perspectives. TBH, I don't think this is always bad, but if you don't want it, you can try specifying the perspective or positioning you want in your prompts.

Troubleshooting:

If you're having persistent problems with anatomy, fine detail, and/or other jank, just try your best with all the usual fixes - different prompting (including negative prompt), try a different base model, use a different VAE, try different clip skip values, adjust the LoRA weight, use adetailer, inpaint, etc.

Outro:

If you make anything awesome, please consider posting them to the gallery! That goes for all of my models! I really like seeing what kind of stuff you all are able to make!

If you have any questions, feel free to ask! I will try my best to help! Also, if you have any ideas for future models, please don't hesitate to share them with me!