Annie leonhart - Shingeki no kyojin/Attack on Titan - WIT studio S1/S2

When people ask about the checkpoint and prompts I use, I generally prefer Hassaku XL, mainly because it retains the original LoRA styles more faithfully than other checkpoints. I've noticed other checkpoints often slightly distort the intended aesthetics, especially when working with manga-style LoRAs. Regarding prompts, I typically use 'masterpiece' only in the positive prompt and include 'bad quality' and 'worst quality' in the negative prompt. I deliberately avoid adding terms like 'good quality' 'best quality', or 'official style', since these tend to diminish or override the distinctive characteristics and facial details provided by the LoRA.

A huge thank you to everyone who's supported me!

The reason I ask for buzz or support, is because I genuinely want to keep creating and updating better LoRAs. People might have noticed that I've been uploading LoRAs much less frequently lately. This is because I'm running low on the buzz I had saved up (around 200K) before I started creating content.

Although I am still a half rookie as a trainer. But honestly, I didn't have to share any of these, since I could have just kept them for myself. I chose to upload them hoping for at least some encouragement or support, but if I keep receiving no help at all, I may start keeping my work private going forward. I'm seriously considering this option.