2.5D Unravel 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: unr4v3l

Helper prompts: parody, style parody, realistic

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

• For a stronger effect, use the main trigger: unr4v3l. You can also weight it numerically or with parentheses - I usually do (((unr4v3l))).

• 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 (((unr4v3l, parody, style parody, realistic))).

• The "realistic" trigger is not necessary to get the general style, but I feel it adds a slight boost of realism to get a little closer to the game's style, so I tend to use it more often than not. However, if you want a look that is a little more anime (or more like the general style of your chosen base model), then you can safely leave this trigger out!

• 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:

This LoRA will give your images an aesthetic similar to the Unravel video game series. Generally, you'll get a realistic-ish 2.5 style, with some foreground and/or background blur. The LoRA mostly works OK, but there are a few issues I'll note below.

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, sometimes, particularly with outdoor shots, it likes to make your character buried thigh-deep in the ground, lol. I don't know why this happens. Maybe because none of the training data was character focused, and the game usually has a lot of stuff going on in the foreground, so it's trying to figure out how to make these two things compatible, but it can't quite figure it out. Or something like that. If you're lucky, it will just look like your character is standing in tall grass or behind a small hill or something. You can probably also fix/lessen this quirk with inpainting or by adding some specific leg prompts to coerce the model into showing them rather than burying them.

Finally, it has 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 seems to make it even worse. 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 generally give you a 2.5D style influenced by the Unravel series of video games.

I wouldn't say that Unravel has a particularly artsy graphical style, but its graphics are definitely very lush and detailed, with lots of stuff going on in the foreground and background, nice use of depth-of-field blur, etc. So this LoRA tries to recreate that general feel, even if it doesn't quite nail the exact art style of the games. And as an added quirky bonus, you will very occasionally get some random strands of yarn pop up, and if you're lucky, maybe even a deformed Yarny! lol

Here are some standard usage tips for the LoRA:

1. Most cartoon, anime, and 2.5D base models will work OK with the LoRA. It doesn't work reliably with realistic models, but you can still give it a try if you want. Experimenting is fun!

2. If you're frequently getting a small character, no character, and/or bad anatomy, you can try gradually lowering the weight of the LoRA.

3. Use a VAE, especially if your chosen base model doesn't have one baked in! It really seems to help with getting better colors and anatomy.

4. Upscale or use Hires. fix with a quality upscaler. If Hires. fix seems to be destroying your images, try lowering the denoising strength.

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!