Dark_Demon

Hi~!

Here I am again.

This time, I used a new model as a base for merging, and I'll admit — I was a bit worried it wouldn't turn out well since it's quite different from what I usually work with. But everything went smoothly, and I'm honestly pretty satisfied with the results. After 200+ generations, I can confidently say this merge works really well for me.

It's a blend of @EarthboundAI's Icarus and @RetsTheMadScientist's Aperion from the Escaped Containment LAB Series. If you haven't checked out these models yet, you definitely should — both are excellent, and you can really feel the care and vision the authors put into them.

This merge carries something from both. It's hard to put into words, even after quite a bit of testing, I still don't fully understand it. Most of the time, it seems to take the detailed structure and large-scale behavior from Aperion, while keeping a pretty visible touch of Icarus in the overall feel.

I didn't run into any issues during generation — everything went smoothly. As always, here's a quick rundown of my settings:

First Pass (Base Generation):

• CFG Scale: 5.

• Sampler/Scheduler: I use res_3m and beta57, but standard euler with normal or beta should also work fine if you prefer simplicity.

Upscaling (I use Latent Iterative):

• CFG Scale: 4.

• Sampler/Scheduler: dpmpp_2m with beta worked well for me. I haven't tested other combinations yet.

The outputs look pretty clean to my eye — finely detailed, with sharp lines. And damn, when you try a complex scene, it can lead to some really interesting results. Just adding the tag complex scene can shake things up in a fun way. I tested it with my old, familiar prompts and sometimes got very different outputs — which I absolutely loved. It's not as wild as my previous merges, but it's cleaner, smoother, and somehow sweeter.

Please, have fun with this little creation.
And, as always, have a good day :3