I am admittedly kind of a noob at this, but if you enjoy my humble work, any donations are greatly appreciated: <a target="_blank" rel="ugc" href="https://ko-fi.com/insult_to_ninjary">https://ko-fi.com/insult_to_ninjary</a>Your generosity helps me stay motivated to keep improving and to keep trying new things!Trigger Words:Main trigger: t3ng4m1Helper prompts: parody, style parody, papercraft /(medium/)<ul><li>The LoRA can potentially work with no triggers, but it may not be strong/consistent.</li><li>For a stronger effect, use the main trigger: t3ng4m1. You can also weight it numerically or with parentheses - I usually do (((t3ng4m1))).</li><li>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 (((t3ng4m1, parody, style parody, papercraft /(medium/)))).</li><li>The "papercraft /(medium/)" trigger sometimes helps a lot, and sometimes does almost nothing. It's not totally necessary to get the style, but it also doesn't seem to hurt anything, so I usually always throw it in there in hopes of a little extra style boost. If you're trying to keep your prompts lean, feel free to exclude it and you'll probably be fine!</li><li>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!</li></ul>At a Glance (Illustrious):<ul><li>Base model: Illustrated style (I usually use <a target="_blank" rel="ugc" href="https://civarchive.com/models/2162463/itns-illustrious-merge">my own Illustrious merge</a> or WAI)</li><li>LoRA weight: 1 (but slowly go lower or higher if necessary)</li><li>Suggested parameters: Euler a, Automatic, 30 steps, 832x1216/1216x832, CFG 5 (but feel free to experiment!)</li><li>Hires. fix: 1.5x, use a quality upscaler (like 4x-UltraSharpV2), denoising strength 0.5 - 0.3</li><li>Extra: use ADetailer to fix faces and/or hands if necessary</li></ul>Illustrious Version Description:This LoRA will give your images an aesthetic like the video game Tengami. If you're not familiar with it, basically you'll get sort a flat, Japanese papercraft style, with a paper-like texture and (most of the time) a layering effect. I really liked my old SD1.5 version of this LoRA, and the Illustrious version is looking very promising as well! It's not perfect, however, so I'll touch on its issues 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. It's usually not that big of a deal though, but it's kind of annoying when it happens with fingers. Overall though, I don't consider this bad enough to be a major dealbreaker.Second, since I think pretty much all of the training images were outdoor shots, this LoRA does much better in outdoor settings. Indoors, you'll still get the flat, paper-like effect, but it seems to give you less of the cool-looking layering effect. Outdoors, you'll generally get the whole shebang much more frequently, so that's where this LoRA tends to shine more.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 give you an aesthetic based on the Tengami video game, which has a Japanese paper, watercolor, pop-up book kind of style.Because this LoRA works pretty stably and has a very stylized aesthetic, as long as your initial gen is good, you probably won't need to do much post-processing besides maybe some minor inpainting or upscaling (depending on how much of a perfectionist you are, lol).The LoRA will have some trouble generating characters at the default LoRA weight (1) with certain base models. If that happens to you, just lower the weight of the LoRA a bit and it should get better. I find that AniDosMix and Hassaku work pretty reliably as base models, but the LoRA will work to varying degrees with most base models, so you can get some really neat results by experimenting!Here are some other standard usage tips:1. 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.2. Upscale or use Hires. fix with a quality upscaler. I typically use SwinIR_4x because I've been too lazy to research and test others, lol [much later edit: now I use 4x-UltraSharpV2]. But mainly just don't use the Latent one.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!

Files with SHA256: fed00ab4b7f7aa6042de8bfc37ad8b19edf17990969136f0b48be962975164d5