Child of Light Influence (Illustrious)
- アップロード日時
- 2026/05/31 9:31
- 採用数
- 5
- レビュー
- レビューがありません
- トリガーワード
co1cd0fl1ght, parody, style parody, watercolor effect
- 権限について
- 画像生成と共有を許可
- ユーザーによるモデルのダウンロードを許可する
- 生成画像の商用利用を許可する
詳細説明
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: co1cd0fl1ght
Helper prompts: parody, style parody, watercolor effect
The LoRA can potentially work with no triggers, but it may not be strong/consistent.
For a stronger effect, use the main trigger: co1cd0fl1ght. You can also weight it numerically or with parentheses - I usually do (((co1cd0fl1ght))).
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 (((co1cd0fl1ght, parody, style parody, watercolor effect))).
The "watercolor effect" trigger is not necessary to get the general style, but I feel it makes the style appear a little stronger, so I tend to use it more often than not. You probably won't lose too much by leaving it out though. So if you're trying to declutter your prompts, feel free to cut this one!
At a Glance:
Base model: Something illustrated (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
Description:
This LoRA will give your images an art style in the aesthetic of the video game Child of Light. If you're unfamiliar with the game, the art style is kind of a fantasy/dark fantasy watercolor style. This LoRA not only affects backgrounds, but it also affects the art style of characters noticeably more than my other LoRAs typically do. Luckily, I like how it looks, so I decided not to mess with it. The LoRA does have a few quirks though, so I'll go over those 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 because the aesthetic is pretty stylized, it may not matter quite as much.
Second, it likes to generate unprompted gradient hair sometimes, in some situations more than others. Usually the hair will start off your desired color at the top, and then fade into a more red color near the tips. If this is happening to you, try a few more seeds. Usually I can find a good seed in short order. You can also try including something in your negative prompt to prevent this from happening.
Finally, you will very occasionally get some UI elements from the game in the upper left corner. Just like with the hair issue above, try a few more seeds and you'll likely find a clean one very quickly. You can also try adding something to your negative prompt to prevent it from happening. And if you get an image that you really like but the UI elements ruin it, there's always inpainting!
For more potentially relevant information, you can check out the original SD1.5 description. Below, there's a troubleshooting section in case you're having any problems.
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!