This description was translated using GPT and may not be perfect.

[Intro]

Hi there.

Although it hasn’t been long since [Illustrious] was released, we’ve already seen its power and potential in action.

However, humans are naturally greedy, and I’m no exception. Even when we’re satisfied, we always want more.

In this light, I created this model by merging a few others to address some personal shortcomings I felt with [Illustrious].

The two main models I used for this merge are [Illustrious-XL SmoothFT] and [T-illunai3].

When generating images with the [Illustrious] model, I often noticed that using certain illustrations or characters caused the art style to shift or led to unnatural colors and contrast. I believe [T-illunai3] helps resolve some of these issues, so I continuously experimented with merging the UNETs of [Illustrious-XL SmoothFT] and [T-illunai3].

Ultimately, my goal was to maintain the core performance of [Illustrious] while achieving a slight quality improvement. However, as an average person without special techniques or high-end hardware, I aimed for “good” rather than “perfect.” As a result, some outcomes may lean in a particular direction, but I believe they’re still enjoyable.

The improvements I focused on are:

• Slightly better hands

• More consistent quality

• More natural compositions

• Balanced, non-overwhelming color tones

• Aesthetic adjustments, and more.

So, was I successful?

Well, I’m not entirely sure.

But if I had to evaluate it subjectively, I’d say it little works somewhat.(It happens often now, too...)

I hope you try it out and share your thoughts.

Merging Process

Step 01: Illustrious-XL SmoothFT + T-illunai3

Step 02: Step 01 + [personal anime model]

a little pepper

How to Use

You can use this model just like [Illustrious].

License

This model adheres to the following [license] and is available for non-commercial use only. Commercial use is prohibited.

Thank you.