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: w1ndw4k3r
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: w1ndw4k3r. You can also weight it numerically or with parentheses - I usually do (((w1ndw4k3r))).
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 (((w1ndw4k3r, 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: 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, 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 produces art in the style of The Legend of Zelda: The Wind Waker. The effect is pretty strong, especially when using the trigger word and helper prompts all together. I especially love the textures that this model can generate, along with the lighting and the slight polygonal effect you might sometimes notice. It does have a few drawbacks though, which I will cover below.
First, images can come out slightly fuzzy, so they might be lacking some fine detail in things like hands and certain background elements. Faces usually come out ok though, since the style makes them large and simplistic. Regardless, you may want to use ADetailer for faces and/or hands if you find them not sharp enough.
In addition, 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.
Finally, about half the time, you'll get characters that have the proper Wind Waker body proportions (or pretty close), but the other half of the time, you'll get characters that have more realistic human body proportions, but still with the goofy round Wind Waker head. It can look pretty jarring (or hilarious, depending on your sense of humor, lol). If you get weird body proportions, just try re-generating on a different seed. You can also try prompting for "chibi," which generally seemed to help for me, but I didn't test it extensively.
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 influence from the The Legend of Zelda: The Wind Waker to your chosen base model. Please keep in mind that this model will likely never get you the exact Wind Waker graphics. It just adds a stylistic influence to your art. How much influence will depend on the weight you give the LoRA.
Sometimes the default weight of 1 will work well, and sometimes you'll only see slight influence in things like head shape, eye shape, clothes/accessories, and background. You can boost the weight up to about 1.5 before you start to just get garbage, but at higher weights like 1.5 and sometimes 1.4, the characters will very frequently just look like Link no matter what you prompt. I find that the sweet spot is in the 1 to 1.3 range depending on your base model, but just experiment to see what works!
Here are some other usage tips:
1. Use a cartoon/anime-style base model. You can sometimes get some interesting results while using more realistic-looking models, but they won't really look like Wind Waker, so keep that in mind.
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.
4. If you want your characters' body proportions to be less realistic and look more like the game, try adjusting your prompt and adding words such as "chibi."
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!