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: y0w0w0
Helper prompts: parody, style parody
The LoRA can potentially work with no triggers, but it may not be strong/consistent.
For a stronger effect, use the main trigger: y0w0w0. You can also weight it numerically or with parentheses - I usually do (((y0w0w0))).
If the (weighted) main trigger is still not enough by itself, next try one or both of the helper prompts along with the main trigger. They can be weighted as well - I usually do them all together, like (((y0w0w0, parody, style parody))).
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 (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, 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 makes images with an influence from the Yoshi's Woolly World video game. It doesn't affect characters super strongly (like, it doesn't make them plushies or anything). Instead, it mainly affects clothing and background details. Clothes and background items will typically get a woolly or fabric-like texture. The LoRA can also randomly add some cool small details - visible stitching around the edges of things, crafting items such as buttons and small gems used as accessories or decorations, balls of yarn, etc.
One weird quirk of the LoRA that I've noticed is the faces it makes. It's hard to explain, but the faces seem to have a specific look to them. You might notice it while scrolling through the showcase images. I'm not sure how it learned this, as the training dataset had no humans in it whatsoever. Luckily, I really like this look. I think it's kind of cute, and I like the eyes. However, it can feel a little too samey after a while.
Another potential issue is that images can come out slightly fuzzy, so they might be lacking some fine detail in things like faces, hands, and certain background elements. You can try using ADetailer for faces and/or hands if you want to improve them a bit.
Finally, the model can sometimes try to make your images look a bit too zoomed out. The helper prompts seem to intensify this. To counteract it (if you want to), you can prompt for the specific composition you want (portrait, upper body, cowboy shot, etc.), and this usually works well enough.
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 add an influence from the Yoshi's Woolly World video game to your art. The proper LoRA weight can vary significantly depending on your prompt and base model, so be prepared to experiment! I've had to go as low as 0.6 for the weight and as high as 1.2 depending on the prompt-model combination.
Once you find the sweet spot range for the LoRA weight, use lower weights in the range for a more subtle addition of color, detail, and texture to fabrics and surfaces. Use higher weights to make everything more doll-like.
Since Yoshi and Poochy were in a lot of the training data, the LoRA likes to make animals a lot. To avoid this and get a human if you're having trouble, try adding a negative prompt or adjusting your main prompt a bit to put the LoRA on the right track. Lowering the LoRA weight also works, but sacrifices some of the aesthetic.
Here are some other usage tips:
1. The LoRA seems to work with most base models, but it works best with models capable of good semi-realism and/or textures.
2. Use a VAE, especially if your chosen base model doesn't have one baked in!
3. Upscale or use Hires. fix with a quality upscaler.
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!