Version 1.5:

Regretfully, I didn't get proper permissions to some of the resources used in Version 1.0. The original creators were very gracious about it, but I have decided to take the model off the site and uploaded this alternative version instead.

Changed the merge to use Illustrij - v17 by @reijlita instead of EVO.  Added dmd2-lighting8step_cfg1.5 by @871587665 to speed up the generation on my slow system.  Overall, there should be a noticeable improvement in textures, composition, and speed.

New Settings:

Steps: 8

CFG: 1.5

Sampler: Euler a

Scheduler: exponential

Version 1.0:

A merge that is meant to generate semirealistic images with nice aesthetic and composition. Example images did not use Hi-res fix, refiner, or Adetailer because my machine is a potato. Feel free to provide feedback on the look of the model. Do people prefer more realistic or more stylistic outputs?

Resources used:

CLIP: NO MERGE - Universal CLIP by @Felldude - This should improve natural language, but tags are still preferred.

Models in the mix:

• Plant Milk Walnut by @Ocean3: Everybody loves this style, including me

• Illustrij EVO by @reijlita: Nice character aesthetics

• Hyphoria [Illu & NAI] by @ecaj: Reinforce character knowledge and help with prompt adherence

• JAVn - Real Merge - Envy IL by @WeBeJavn: Realistic Illustrious models usually have a certain default face shape. This is one of the models where that default shape is less prevalent.

Settings:

Steps: 25

CFG: 4

Sampler: Euler a

Scheduler: exponential

I am no expert so feel free to share better settings for generation. I also use Lazy Embeddings by @janxd. Add photo-realistic, realistic shading, realistic texture to the prompt if you want more realistic output.

What to improve:

• Eyes and fingers can be messy sometimes.

• Character knowledge is inconsistent.