So, this is the second iteration of Neuro-Evolution. I made a choice to split Neuro-Evolution into two models. The Neuro-Evolution will be more cartoonish, specifically anime and 2D. The Neuro-Reality model, which is more artful and capable of generating portraits, is currently in development and nearing completion.
So, about the model:
To move it closer to Anime style I added a few models to the mix:
RaemuMix 11
weakened unity 6 Sharp
All the settings are still the same:
Width: 512
Height: 768
Sampling Euler A
Sampling steps: 30 normally (more than 30 gives you some stupid stuff)
Hires.fix settings:
Upscaler: 4k-UltraSharp
Steps: (10-20)
Denoising: Strength: 0.34 - 0.45
Upscale: 1.5 or 2
Clip Skip: 2
One more thing. I created all the pictures for this model in Forge, but my program of choice is ComfyUI. I strongly advise you to use it to make pictures with my model. (If you want I can post my workflow).
