✦ Arthemy Comics Illustrious - Quick Start ✦
I suggest you to use my quick prompts as a "quick start" and then move from there in the directions you prefere.
Afterall - they are called Checkpoints for a reason!
___________________________________________________________________________________
1_____Size: Around 1024 x 1344
2_____Prompt: Start from the prompts present here and tune the keywords based on your needs:
Quick Prompt
masterpiece, complex shadows, dynamic pose, solo, western comics \(style\) , linear hatching, flat color, perspective, (insert your prompt here!)
Quick Negative Prompt
big head, anime, low quality, worst quality, jpeg artifacts, fused elements, (no_lineart), blurry, bad anatomy, greyscale, (insert your prompt here)
3_____CFG: 5.5 to 7.0
4_____Steps: 45 to 50
(I've noticed that 30-40 steps are not usually enough to solve the image completely)
I hope you like my models and I can't wait to see what you all are going to create with it!
____________________________________
Merged / subtracted / inspired by Models:
Nova Furry - https://civarchive.com/models/503815/nova-furry-xl
Toonify - https://civarchive.com/models/36281/toonify
Ri-Mix - https://civarchive.com/models/996495/ri-mix-pony-illustrious
Velvet Paradox - https://civarchive.com/models/1734917
IllustraVersa - AdV3nt - https://civarchive.com/models/1888661/illustraversa?modelVersionId=2233553
UltraComix - https://civarchive.com/models/1798149?modelVersionId=2034957
Unholy Desire Mix - https://civarchive.com/models/1494558?modelVersionId=2200584
+ A lot of my own trained LoRA
If you like Arthemy Comics, remember to check these other models and consider to support their creators!
Description
The objectives with this version were:
+ More Creativity: the heavy use of small LoRAs in my first version collapsed most of its generations into the same shapes. Now, with the help of many personally trained LoRA I've been able to push the creativity of this model further and have more variation of characters and poses.
+ More Flexibility: It's still a heavily comicbook inspired model, but if you write for example "Realistic" it will provide a more realistic comicbook style and so on. So, now you can explore different aesthetic with the same model - while keeping it "Comicbooky"!
- Less reliable hands: Unfortunately, training this model on cartoons and fantasy illustrations compromised its ability to provide five fingers consistently - I think it can be easily fixed with a LoRA.
This is going to be the last version for a while, since I'm quite satisfied with the results and, unless your feedback will make me change my mind, I think I'll take a small break.
Have fun! I can't wait to see what you're going to create with this model!
FAQ
Comments (13)
First model for which I purchase early access. Worth it.
💕✨ You're too kind! Thank you!!
@Arthemy your work is amazing. Those willing to make something original like yourself are the ones making this community great.
I wasn’t sure at first because the Illustrious models I tried before didn’t really work for me, but this one is exactly what I was hoping for. Really impressive—thanks a lot!
You welcome! I'm glad you're enjoying it 💕✨
THANK U.
i was sick of these anime nsfw models all around
Check out my newest "Arthemy Painter Illustrious" if you want a more general "western aesthetic" not limited to 2D illustration.
I see many comments thanking you for giving us resources that allow some diversion from the omnipresent anime in AI image gen. Count me among them.
I get such cool outputs from these. So good that, when I occasionally try a style LoRA, I usually remove it again because I get better outputs using native prompting! Amazing models.
P.S. I can't wait to see what you'll come up with, when you go with NAI! =D
Thank you so much for the positivity! Right now I'm also interested into Flux, but NAI could be a fun challenge too! 🤩✨
@Arthemy I'm very impressed by Flux' prompt adherence, it's good at 3d and realism... until you take a closer look. Then after a while you start to notice that the same distinct visuals always come back. Either you like that, or not. Since I delved a lot deeper into Illustrious and NAI, I've started disliking that typical Flux visual.
(PS: when it comes to prompt adherence, take a look at HiDream!)
As for NAI, depending on the vpred version, it can do advanced lighting unlike anything I've seen elsewhere! With the right checkpoint, it's pretty good at realism, too. NAI is definitely interesting, it's an overall upgrade of IL in every way, and more versatile.
@Otto_Mattiq well, you got me interested. I'll spend a few days playing with NAI and Hi-Dream in order to see if I can give them an "Arthemy" spin on them!
@Arthemy
For realism, you might want to check this one: https://civitai.com/models/1252962/nailove-noobai-real-sdxl-merge. I only do realism on occasion, but I haven't found an IL that comes even close.
https://civitai.com/models/833294/noobai-xl-nai-xl is the original (?) vpred NAI that has those amazing lighting abilities, but it does require some prompt rethinking just because of the extra lighting prompts required.
https://civitai.com/models/989367/wai-shuffle-noob is more accessible and a bit in between. I used it (and NAI's superior prompt adherence) for the ... peculiar Star Wars weapons systems in my last post. lol I couldn't get that result in (your) IL models.
The sole reason I'm not using NAI models exclusively is because they haven't become known and or popular enough...? Whatever the reason, at this time there are better dedicated IL models for 3D and western comic styles, but I'd looooove to see those driven by NAI prompting.
Great lora crisp and clear images with that sweet comic feeling, responds well to prompts great for story telling of any kind.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.