✦ 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
Hello everyone!
Since the creation of my "Arthemy Toon" model, I've decided to steer this model even more towards a western aesthetic - diversifying my models and granting you some neat ingredients for you to merge in order to get your desired "half-way point" between these two aeshetics.
You can expect an aesthetic inspired from western videogames aesthetic and old-school graphic novel vibes.
I've introduced a few strong ingredients in the mix so... this is a little more experimental than usual!
Remember to start from my prompts and then change the subject in order to understand how this model react to changes - than feel free to try and change a few aesthetic specific keywords in order to build your own style.
FAQ
Comments (16)
Yeah, it's pretty nice.
It's 6.0! Marvelous!
I've been playing around with this and it's great, much like your other models. Prompt adherence seems pretty good. The only thing is that it sometimes gives me robot-like features around the neck, particularly side view. But excellent work anyway!!!
Oohh, have you tried using my prompts? Maybe there's a problem in my negative!
Thanks for replying. I used the negative as per your prompt, but I changed the positive a lot (obviously). Maybe I missed a keyword somewhere. I'll keep playing with it anyway, so I'll give you more feedback if I find what it is.
As I said, though, great work! Please keep it up!
@lavender69studios Unfortunately this models is very susceptible to some keywords and "gets mad" with the simplest grammar mistake. Check the positive prompt and read every word (ignoring the context) I'm pretty sure you'll find something that might have created that "Robot-like" features.
@Arthemy I'll try, thanks! I could in-paint it out, so no big deal. :) I think I have seen these artifacts in other pics in the showcase, but I can't attach them here unfortunately.
@Arthemy BTW, I think I discovered what causes the robot-like features I mentioned earlier in this conversation. These seem to be related to the word "cyberpunk" in the prompt ("cyberpunk lighting" seems ok, though). So yeah, I can avoid them altogether now. Just wanted to let you know. On a different note, prompts from your earlier models "a 2d western style illustration of..." also seem to work very well with this one. So yeah, keep it up! I love this model! :D :D :D
@lavender69studios Amazing! Thank you for the feedback! I'm working on a new version of my toon model now! :3
Sweeeett!! Can't wait to play with it!!
Bro I've been keeping an eye on this model since v1.0 and let me tell you, v5.0 is where your magnum opus for this model has officially begun.
v6.0 really cements you're style and flexes your muscles
Stunningly good fantasy/comic look.
Gives it that really geeky fantasy vibe I see in comic book stores.
Prompt adherence is .....just, whoa. Amazing.
Style can be mixed with so fluidly with other types of fantasy Loras.
Totally beautiful job on this project.
Now ya cooking with gas bb 🔥
Thank you so much for the positive review!
I've read your article on "Model Merge" and I think it's one of the best one on this website.
(everyone - check that out at https://civitai.com/articles/12114/essential-guide-2-model-merging-sdxl-pony-illustrious !)
In fact, I was thinking to create a similar guide with my workflow (I personally love BlockMerge) - maybe we could work together on that and bring some more creators to provide a very omnicomprensive guide! ^_^
Do you give permission to use it to create my comics?
Of course! Feel free to do it! ✨
This is BY FAR my favorite checkpoint!!! It's INCREDIBLE! Not only is this the only checkpoint I've found that produces a good looking western comic style, but its prompt adherence is AMAZING and anatomy is perfect. Also, for a given prompt, every image is going to be virtually the same--it's very consistent so you don't need to generate 30 times to get a good seed. Just make a tiny tweak to the prompt instead and voila!
The only issue I've noticed is that it creates much better images when the prompts are super short, but honestly I see this as more of a positive than a negative--instead of using the recommended long prompts and negative prompts, I've had MUCH more success using 1-2 lines in the prompt and a few words in the negative, or nothing at all. You don't need to cram "masterpiece" and its many synonyms in the front, or throw in dozens of typical negative prompts. No need to include style info in the prompt. When I just straight up tell it what I want in 1-2 dozen words, it gives me incredibly consistent, high-quality results!
In general, i like to use very detailed prompts just to give more "personality" to a character. By providing many details like "hair over eye" or things like that you can shape a very unique looking character. Still, thank you for the positive feedback, I'll try to improve it further with the next version and try to simplify the suggested prompt a little bit. 💕 Prompt adherence is a must for me and I'm always glad to hear people enjoying that aspect of my models! Have fun!
Details
Files
Available On (3 platforms)
Same model published on other platforms. May have additional downloads or version variants.