models/Nevolution XL/IL - v2-anim

Nevolution XL/IL - v2-anim

7/18/2025

3:19:10 AM

Related Keywords & Tags

artstyle,base model,checkpoint,checkpoint blending,cyberpunk,fantasy,general purpose,image generation,necr0x0der,nevolution,nevolution xl/il,sci-fi,scifi,sdxl,sdxl 1.0,semi-realism,stable diffusion model,v2-anim

A hyperrealistic eye with a cosmic iris swirling in bioluminescent blues, surrounded by colorful planets and nebula clouds in a deep space scene.

A man wearing a grey robe stands inside a dark, damaged room looking out through a large window at a glowing cityscape with many warm yellow lights illuminating buildings at night.

Cubism style portrait of a woman’s face composed of traffic lights, set in a vibrant night metropolis with red and white pulse-shaped lights

Watercolor painting of a highly detailed modern suburban house during sunset, featuring large glass windows and warm interior lighting, surrounded by landscaped greenery.

Iwakura Lain standing in a neon-lit cyberpunk alley wearing a digital binary code hoodie with a glowing smiley face and a soft, happy expression.

A detailed cybernetic robot with a large glowing blue and yellow eye standing in a vibrant, neon-lit futuristic city street at night, surrounded by colorful signs and people.

Anime-style boy character Ashitaka wearing a red crystal helmet, with a blue and green outfit, set against a vibrant, glowing, digital otherworld background.

Cybernetic astronaut floating dynamically in a vibrant cosmic space scene with bioluminescent colors and distant planets, painted in watercolor style.

Anime-style dark street scene with a figure having translucent insect wings, glowing orbs resembling planets on a dress, surrounded by cosmic elements and strange creatures.

A swirling bioluminescent blue magical vortex rising inside a dark industrial factory, with two silhouetted figures observing amidst glowing machinery and structures.

Silhouette of a large tree in front of a countryside house under a dramatic red silk sky with clouds and foggy fields in watercolor style

Detailed green ink illustration on parchment depicting a caravan of travelers along a stone road passing ancient stone archways, surrounded by a forested glade and mountainous landscape with stone shrines and moody skies.

Recommended Parameters

samplers

DPM, Euler a

steps

30 - 45

cfg

5 - 8

Tips

Use keywords like 'anime', 'illustration', 'manga', and 'painting' to amplify capabilities of the 2.0-anim version.

Version Highlights

Illustration-friendly version

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.

Version IL-v1 is an independent merge of Illustrious checkpoints. However, I tried to make the resulting checkpoint to work similar (up to the difference of the base models) to other Nevolution checkpoints. So, it's a kind of convergent evolution.

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

Steps: around 30 for v1.0; 30-45 for v2.0, 30 is enough for IL-v1

CFG Scale: 5~8