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: biboochiHelper prompts: chibi, huge breastsExtra help: chibi only<ul><li>You can try the LoRA with no triggers, but it probably won't work too well.</li><li>For a stronger effect, use the main trigger: biboochi. You can also weight it numerically or with parentheses - I usually do (((biboochi))).</li><li>If the (weighted) main trigger is 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 (((biboochi, chibi, huge breasts))).</li><li>I didn't include it as an official trigger because it's usually not necessary, but you can also add chibi only to the other trigger words if you're still not getting the right body proportions, or if you're getting a normal-sized main character with background chibis and/or chibi insets present.</li><li>The "huge breasts" prompt is not necessary, but it does help to get the intended style. If you want different sizes, prompt accordingly, or just leave it unspecified and see what happens!</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 do work for SD1.5 though, and are strongly recommended!</li></ul>At a Glance (Illustrious):<ul><li>Base model: Anime style (I use WAI-illustrious-SDXL)</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:The goal of this LoRA is to produce more curvy chibi(-ish) characters. Compared to my previous <a target="_blank" rel="ugc" href="https://civarchive.com/models/151609/amplechibi">AmpleChibi</a> LoRA, this LoRA has a slightly different aesthetic, and also sacrifices a bit of chibiness in exchange for a bit more curviness. In fact, the curviness can be a bit much, even compared to the SD1.5 version. You may want to prompt it down a bit.As a side use, if you focus only on the chibi aspect of this LoRA, it can also work as just a general chibi helper, as I got really inconsistent results trying to generate chibis using the WAI-illustrious-SDXL model alone. The aforementioned AmpleChibi LoRA is probably better as a chibi helper though, so if that's what you're looking for, also check out that LoRA!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:The goal of this LoRA is to produce curvy chibi(-ish) characters. Compared to my other curvy chibi LoRA, <a target="_blank" rel="ugc" href="https://civarchive.com/models/151609?modelVersionId=169539">AmpleChibi</a>, this LoRA sacrifices some chibiness in order to allow for more curviness. The general aesthetic is also a bit different.For best results, use the trigger words: chibi, huge breasts (the breast size can be adjusted up or down to suit your needs).The LoRA generally works well with a variety of models, as long as they are anime or (sometimes) semi-realistic. It will not work well with realistic models. Either it will have no effect, or you will get some serious nightmare fuel, lol.If your generations are not coming out chibi, or not chibi enough, try increasing the weight of the trigger word or switching to a different base model. The LoRA will sometimes give you a hard time getting what you want, but if you stick with it, you will eventually get some really nice results!If you have any questions, feel free to ask! I will try my best to help! This is just the second LoRA I've made, so I'm sure it's not perfect. If you have any ideas for future LoRAs, please don't hesitate to share them with me!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: eb48b5edade2d0126b24dd7f94eb1e7eb64acaab3aecc0a9605b09dd1a490cbc