Limbo Influence (Illustrious)

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: l1m80

Helper prompts: parody, style parody, monochrome, greyscale

The LoRA does have a very slight effect with no triggers, but it won't look right, so I don't recommend this.

For a stronger effect, use the main trigger: l1m80. You can also weight it numerically or with parentheses - I usually do (((l1m80))). This also probably won't be enough on its own, especially to make it black and white.

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 (((l1m80, parody, style parody, monochrome, greyscale))).

It's probably best to use all 5 triggers together (1 main trigger + 4 helper prompts). However, the most important ones are "monochrome" and "greyscale." Without those, the best you'll get is sort of "Limbo in color" if that makes sense. You'll get the style of Limbo - fuzziness and graininess, vignetting, a bit of minimalism, etc. - but usually in a darker color palette (not greyscale/black and white).

If you want pure monochrome greyscale, make sure your prompt doesn't include any colors and your negative prompt doesn't include anything that would work against monochrome output!

At a Glance:

Base model: Illustrated style (I use WAI-illustrious-SDXL)

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, 30 steps, use a quality upscaler (like 4x-UltraSharpV2), denoising strength 0.5 - 0.3

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

Description:

This LoRA will give your images a vibe from the video game Limbo. This means, using the trigger words properly, you'll get an image that is monochrome/greyscale, a bit fuzzy and grainy, has some vignetting, and is a bit more minimal than usual. I think this LoRA came out pretty well, and I really like the effect! However, some things to keep in mind are below.

First, it is, by nature, a bit fuzzy, blurry, and grainy. That's because that's what the original game kind of looks like. If you're looking for more crisp and clean results, this probably won't be the best LoRA for you.

Second, if your image is set outdoors, the LoRA is going to want to dump your character into a forest almost all of the time, despite what you prompt for. This is because many of the training screenshots happen to take place in a forest. I don't mind this too much, but possibly be prepared to fight the LoRA a little bit if you're very particular about how you want your background to look. Also maybe consider lowering the LoRA's weight for this.

Finally, please be aware of how to obtain the best color control when using this LoRA. If you use the trigger words as instructed above, avoid putting specific colors in your prompt, and make sure your negative prompt doesn't contain anything that would prevent monochrome/greyscale, you'll be able to get Limbo-like colorless images no problem. However, if you want the Limbo style but with color, then don't use the "monochrome" and "greyscale" triggers and prompt for the colors you want. If you want mostly black and white, but with a splash of color in things like eyes or clothes (like in some of my showcase images), keep the "monochrome" and "greyscale" triggers, but also prompt for the colors you want as well. This might take some trial and error, but it's very doable once you figure out the best approach for your specific prompt.

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

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!