Illustrij

hey guys, ☺

as u know I rlly love comic-anime-hybrid based checkpoints and digital art rendering with a touch of 3D on its way to semirealism. So I've thought it would be time to test Illustrious. This is how I wanna present to u ~ Illustrij ~ my first merged Illustrious checkpoint :)

If u like what I do consider leaving me a like or a comment, much appreciated and helps me getting a feeling for tinkering ~♥

NEW 🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸

about v9

Tinkered around a bit with my own models and Loras back to a more balanced anime-semireal style and added a little NSFW touch. ☺

hentai & NSFW

With hentai and NSFW images, the model sometimes has its own idea the less ur pre-prompting ~ maybe u would like to get involved?

These two posts offer a little foretaste:

https://civitai.com/posts/14082774

https://civitai.com/posts/14081639

more animebased: https://civitai.com/posts/14088147

Since Illustrij is based on combining elements of semirealism and anime, the newer versions spawn with more depth and a 2.5 D feeling. Through promptings we can determine the direction a bit, whether more semi-realism or anime ☺ entirely according to ur own taste. For more anime I recommend the following settings:

recommendet resolution

1024*1024 / 832*1216 / 720*1280

recommendet settings examples Anime+

Clip skip 2

Euler 

local: 15-25 steps

CFG 7-10

+prompt

(masterpiece, high_quality, highres, anime_style, flat_colors, gradient), retro_artstyle 1980 \(style\), 2D, sketch, 

- prompt

worst_quality, bad_quality, poorly_detailed, young, realistic, 3D, semireal

recommendet settings examples Semirealism+

Clip skip 2

Euler a

on site: 50 steps / local: 25+

CFG 4 (2-7)

+prompt

(masterpiece, high_quality, highres, flat_colors, gradient),

best_quality, absurdres, ultra-detailed, highly_aesthetic, highly_detailed_eyes, depth_of_field, subject_focus,

(masterpiece, high_quality, highres, flat_colors, gradient), ultra-detailed, highly_aesthetic, highly_detailed_eyes, depth_of_field, subject_focus,

-prompt example

worst_quality, bad_quality, poorly_detailed,

bad_anatomy, low_quality, poor_lighting, out_of_focus, misaligned, poorly_drawn, cluttered_background, unnatural_pose, disproportionate, unattractive_expression, soft_shading, clean_lines, no_background, 

In both variations, Illustrij remains a mix of semi-realism and anime, with different emphasis. ☺ In summary, the more steps and the lower the CFG, the more semi-realism, the fewer steps, and the higher the CFG, the more anime-touched.

I am happy if u enjoy and stay curious abt ur results ♥

💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸

about v8

V8 is an experiment to integrate some of my Loras into Illustrij ~ without triggers of course ;) Let me know if u like the direction and how we can develop Illustrij further. I also tried to ensure that the model's style remained true to itself while leaving out the negative prompt.

V8 can create furry aswell.

I'm looking forward to ur results and hope u have a lot of fun being creative.

recommended settings:

Euler a / Euler

25-30 steps

CFG 5-7

Clip skip 2

_ might wanna be ur friend for tags

☺ Showcase resolution: 720*1280. I would recommend using ADetailer for further distance.

+prompt example

masterpiece,best quality,amazing quality,very aesthetic,absurdres,newest,detailed eyes,

-prompt example

u can leave empty

or

worst_quality, bad_quality,

a little comparison of V7 and V8

💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸

about v7

V7 takes a big step back to the roots and yet somewhere completely different ~ quest: keeping the balance . . . focus on painting a 2.5D lightning effect by drawing the Illustrij faces. I'm curious to see whether u like it and look forward to ur creations ~♥

Please let me know if u like the new direction ☺

recommended settings: 720*1280 / Euler a / CFG 7 / steps 25+ / Clip skip 2

🐰 furry optional

💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸

about v6

The new versions spawns with a touch of 2.5 D remdering ~ with a flat-shaded anime style, but subtle 3D lighting and depth, making images look almost tangible.

I hope you like it and stay tuned for your results ~♥

• showcase resolution: 1040 x 1510

  prompt examples:

Prompting is basically similar to the previous versions. After playn around with and testing old quality prompts ~ at the moment I prefer to use "masterpiece, best quality, amazing quality, very aesthetic, absurd, newest, detailed eyes" or "masterpiece, best quality," for +prompt and "worst quality, bad quality," for -prompt.

Of course these are just examples, u can vary them to suit ur own taste.

~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~

about v5

hey guys, ☺

the gap between v4 and v5 was only a few days ago, but I've been "tinkering around" a bit and didn't want to keep it from you.

Trying to work on getting the quality closer to hires without hires - but there are still a few steps to go ^^
For people who have good hardware and can generally use a lot of Loras etc. at the same time the difference might not be that big, but I feel for the people who have small graphics cards :I 
The quality isn't perfect, but I've been working on it a bit ~ soft filling, clean renderings ~ the plan was to create an own style, subtly painted ~ anime-based, but still kissed by reality.

I hope you like the merge and I'm really looking forward to your results ♥

Belonging to the style u prefer u can switch the promptings 4 sure by ur own taste. In general, I mostly use "masterpiece,best quality,amazing quality,very aesthetic,absurdres,newest,detailed eyes" for general quality prompting, and besides depending on whether I want more anime or anime semi 3D touched I am writing "A professional,high-quality,hyper-realistic portrait of a woman, 3D" for the semianime 3D version and "A professional,high-quality portrait of a woman" for anime e.g. or as a conclusion for semi-anime:

"masterpiece, best quality, high resolution, very aesthetic, absurdres, newest, professional, high-quality, hyper-realistic, portrait of a woman, looking at viewer, detailed eyes, realistic body,"

and neg.:

"(lowres:1.2), (worst quality:1.4), (low quality:1.4), (bad anatomy:1.4), multiple views, jpeg artifacts, artist name, censored, young, 2D"

Sometimes I either leave out the negatives completely or write, for example, "lowres, worst "aesthetic, bad quality, worst quality, bad anatomy, sketch, jpeg artifacts, ugly, young, soft rendering, face marks"

depending on whether I use Euler or Euler a as sampler ^^

Usually I structure my prompts based on this:

• subject description: who or what can be seen? (what does she/it look like? hair, eyes, clothing, description of the scene),

• light and shadow description,

• which angle, perspective, motion? quality

and

• detailed description

or the quality at the very beginning and then the rest of the structure :)

If u're tasty for more? Here is a lil insight into the prompt structure: https://civitai.com/articles/10509/il-portreij-step-by-step

💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸

about v4

hey guys, ☺

for V4 I changed the recipe a little to improve the quality a tiny bit and also to expand the options for prompts.

💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸

about v3

style closer to V1 anime based with a lil qualy upgrade ☺

Showcase images without ADetailer

💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸

about v2

a lil more 3D touched without using 3D in promptings

by writing "realistic" the style will become more into semirealism and without its closer to a semianime based style

furry optional

a lil quality upgrade, just a lil ^.^

🌶️ sidefact for NSFW fans: viewer can interact with character by describing what hands can do (see sample images in the showcase)

💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸~💗~🌺~💗~🌸

about v1

If u like the style in the showcase images, u can add

high-resolution, realistic, 3D,

detailed skin, detailed eyes, shadows, dark light, eyelashes, upper body, cheeky, posing, holographic color,

to ur prompt. Without it the style becomes more anime based.

~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~

At further distance I would recommend using ADetailer.

Today I can't say yet in which direction the merger is developing, but as a pony and flux fan, I can only say that I love the color intensity of Illustrious. I recently tested it and got a taste for it, maybe you'll like it too ☺

I am happy if u enjoy and stay curious abt ur results ♥

~~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*

a small comparison from V1 to V5

⬆️ masterpiece, best quality, 1girl, face, portrait, looking at viewer, closed mouth, close up

worst quality, bad quality

~~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*

I hope it gives a little impression of the development ☺