Version 2.0 and a anima version based on the latest anima_baseV10.safetensors is out! I worked a lot on the LoRA to prevent overfitting while keeping the appearance stable.

IL-Version:

Read this if you interested:

https://civarchive.com/articles/29783/lora-training-for-anime-characters

Important Note: Do NOT use Automatic Scheduler! It will mess up the eye color! Use Karras instead.

Update 14.05.26: Little Note on v2.0 i forgot to mention:
If you use the "hcm-dress" tag, you should add “hcmt-dress” and “torn clothes” to the negative prompt to prevent both outfits from merging.

Anima-Version:

Some words about the Anima model:

If the image drifts (bright color, oversaturation) use (anime coloring:X.Y) you have to play with the multiplier though... or use another trained checkpoint like Wai_anima!!!

I spent a lot of time learning about the base model and training the LoRA. Here’s my opinion on Anima.

Pros:

• Incredible tag responsiveness (way better than IL, in my opinion)

• Great outfit awareness during training: with IL, you often have to use tags like “white hakama,” while Anima handled the outfit very well despite the lack of many full-body shots in the dataset

• Great output quality (for short prompts!)

• Natural language prompting worked well

Before I start with the cons, I want to mention that I’m not entirely sure whether I trained my models correctly. Regardless, I tried many different things, but I couldn’t get better results. Also, don’t forget that Anima is still in beta!

Cons:

• A bit complicated, since you have to include the VAE and text encoder manually

• The models I create tend to drift when using many tags not with trained checkpoint based on anima (like Wai_anima)

• No full Hires.fix support yet also works with other trained checkpoint

• Complicated prompt order (and it seems to matter a lot for output quality) turns out don't using the pony quality tags (score8, score_9 etc.) worked well for me, no changes between IL

• More generation parameters to handle (e.g. Shift)

Conclusion for now:

I’ll stick with IL until Anima becomes more stable (or until I find the right training parameters—so I’m not putting all the blame on the base model 😅).

That said, I can create Anima-based models on request.

I'll keep an eye on whether most people switch to Anima or continue using IL and will decide flexibly which base model to use going forward.

Text for 1.0: I KNOW, I KNOW!

“There are tons of versions of her on Civitai, so why bother making another one — especially when you always say you prefer creating models of characters who don’t already exist on Civitai!?”

But hear me out: I didn’t make another version because the existing ones are bad. It’s just that Orihime Inoue is one of my all-time favorite characters, and I wanted to make my own version of her.

This is only (140 EP) the Hueco Mundo version of her, because that’s my favorite look — though I’ll probably make a Shinigami disguise version at some point too.

Prompt: look at "Trigger Words" on the right side 👉

Changelog: look at "About this Version" on the right side 👉

My Settings (forge)*:

*note, the example images only use high-res fix.

Checkpoint: waiNSFWIllustrious_v170 for IL, waiANIMA_v10Base10 for anima

Sampler: Euler a for both IL and Anima

Scheduler: Automatic Karras for IL, Normal for Anima

Samplings Steps: 30 for both IL and Anima

Hires.fix: R-ERSGAN 4x+Anime6B, 20 Hires steps for both IL and Anima, Denoising Strength: 0.3-0.5 for IL and 0.2-0.4 for anima

Extensions (nice to have for little more Details):

Adetailer (highly recommended)