models/Nevolution SDXL - v2-base

Nevolution SDXL - v2-base

7/28/2025

11:37:52 AM

Related Keywords & Tags

artstyle,base model,checkpoint,cyberpunk,diverse results,fantasy,general purpose,necr0x0der,nevolution,nevolution sdxl,sci-fi,scifi,sdxl,sdxl 1.0,selective breeding,semi-realism,stable diffusion model,v2-base

A lone figure stands with an umbrella on a rain-soaked urban street, beneath a grey sky with a large heart-shaped rainbow-colored sun.

A dark, muscular hooded figure with large black wings and horned headpiece, standing in a misty forest surrounded by swirling fiery orange, red, and purple smoke.

Expressionist portrait of a young pirate boy wearing a worn straw hat with vibrant ink splatters and bold brush strokes in an abstract, dynamic composition.

Black and white portrait of a winter goddess adorned with tribal black makeup, feathered headdress resembling a white wolf, and intricate jewelry, set against a snow storm background.

A surreal character with Mickey Mouse ears, vivid tattoos, and glowing red eyes walks through a colorful, psychedelic mushroom forest in a childish, painterly style inspired by Jamie Hewlett.

A humanoid creature with a giant fly agaric mushroom cap head featuring sharp teeth, standing in a vibrant deep forest with moss, holding a wooden staff.

Recommended Parameters

samplers

DPM*, Euler a

steps

30 - 45

cfg

5 - 8

Tips

To enhance the 2.0-anim version, use keywords such as "anime", "illustration", "manga", and "painting" to amplify illustration-oriented capabilities.

Version Highlights

The version evolved to be more versatile and sometimes more detailed

Nevolution

FaeTastic family of checkpoints is great, but in some cases it lacks diversity of results. This checkpoint (Nevolution) is an attempt to mix in some checkpoints with other styles and effects. A few checkpoints (including in particular DucHaiten-AIart) were taken as initial ancestors and were mated with secondary checkpoints from other "breeds" (Pilgrim Midjourney for visual effects, DucHaitenNiji for some artistic effects, etc). Then, there descendants were mated further and further. Selection took place to reject offsprings producing artefacts. And some other checkpoints (both base and merges, including, e.g. Animagine) were merged with low weights for tweaking the result, which proves itself to be good enough.

The checkpoint is general-purpose, but it was asserted mostly on sci-fi / cyberpunk / fantasy content.

Version 1.0 is the initial result of selective breeding of multiple checkpoint. This version provides more stable, but slightly less diverse results.

Version 2.0-base is the version, which was obtain form breeding Version 1.0 with a number of more recent models (e.g., realismFromHadesXL, PixelAlchemy, NovaAnime, etc.) These models were taken with 0.05-0.1 weight, so it's still the same Nevolution model, but somewhat more versatile, and in some cases more detailed.

Version 2.0-anim is a sister of 2.0-base. These checkpoints share all the parents, but with different weights. Their "genomes" are similar, but different. 2.0-anim version got higher contribution from illustration-oriented parents. To amplify its capabilities, such words as "anime", "illustration", "manga", "painting", etc. are better to use. The checkpoint is still quite versatile and not specifically anime-oriented, which may let it produce unique results.

Sampler: I typically use DPM* or Euler a, but others may also work

Steps: around 30 for v1.0; 30-45 for v2.0

CFG Scale: 5~8