Generate pictures with Arthemy
Searching for an AI characters generator?
Arthemy, my AI image generator now has all of my models loaded and ready to be tried on your browser - no GPU required
----> https://arthemy.ai
✦ Comics Arthemy - Quick Start ✦
1_____ I highly suggest to use this embeddings:
verybadimagenegative_v1.3 https://civarchive.com/models/11772/verybadimagenegativehttps://civarchive.com/models/11772/verybadimagenegative
2_____Size: Around 640 x 768
3_____Prompt: Start from the prompt present here and tune the results based on your needs:
Quick Prompt:
[How],[what/who],[where],[other] exaple: (ultradetailed fantasy illustration:1.3), elf witch woman with a large hat and purple dress, on a snow-covered mountain with blowing wind, complex lighting and strong sense of movementQuick Negative Prompt:
verybadimagenegative_v1.3, (worst quality:1.4),(low quality:1.4),(normal quality:1.3),lowres,watermark, title, (jpeg-artifacts:1.3)
4_____Upscale: to get crisp results like the one shown in the pictures use HiResFix and Lanczos. I suggest to use this step only on the preferred pictures, since it's quite heavy on the performance side.
I hope you like my merge and I can't wait to see what you all are going to create with it!
For future update, about the AI Editor I'm building with an italian team and my models you can check:
https://www.instagram.com/arthemy_ai/
____________________________________
Merged / subtracted / inspired by Models:
DarkArtsStyle - https://civarchive.com/models/109?modelVersionId=124
DiffusionBrushEverything - https://civarchive.com/models/46294?modelVersionId=50908
ForgottenMixtheNovelist - https://civarchive.com/models/81644?modelVersionId=86640
Icantbelieveits - https://civarchive.com/models/81644?modelVersionId=86640
icomix - https://civarchive.com/models/16164/icomix
mcbsMachinecodesComics - https://civarchive.com/models/71404?modelVersionId=76148
OccidentalMix V2.0 - https://civarchive.com/models/63920?modelVersionId=68515
vividwatercolors - https://civarchive.com/models/4998/vivid-watercolors
westerncartoontypeA - https://civarchive.com/models/62060?modelVersionId=66582
Babes - https://civarchive.com/models/2220/babes
Diffusion Brush Everything - https://civarchive.com/models/46294/diffusion-brush-everything-sfw-nsfw-all-purpose-checkpoint-nuclear-diffusion-anime-hybrid
Cute Cartoon - https://civarchive.com/models/85547/cute-cartoon-illustration
Western animation diffusion - https://civarchive.com/models/86546?modelVersionId=92044
IdentityCrisis - https://civarchive.com/models/89075?modelVersionId=94798
Vivid Watercolors - https://civarchive.com/models/4998/vivid-watercolors
Exquisite details极致华彩 - https://civarchive.com/models/118495/exquisite-details
SXZ Luma - https://civarchive.com/models/25831/sxz-luma
+ some of my old mix
Some of these models have been used for subtraction, but they all have been useful in order to create this model.
If you like Comics Vision, remember to check these other models and consider to support their creators!
Description
Like Dragonball GT isn't really what we expected from a new Dragonball serie, this Arthemy Comics GT is quite an unusual upgrade - in fact, for some, this model might be seen as a downgrade compared to the previous one (which is why I added the "Beta" surname for it)
Let's talk about Upsides and Downsides:
UPSIDE:
The heads are now more proportional to the bodies
It is near perfect to recreate a "handmade" feeling - images looks a lot less AI made in both textures and "roughness".
DOWNSIDE:
Hands and fingers are a step back from the previous model, which is a bummer that I need to figure out how to fix soon.
The images made in Txt2img are usually less clean than the previous version, it is suggested to develop them in a chain of Img2Img
Let me know what you think.
"Maybe I've gone too far in a few places" George Lucas
_________________________________________
Changes to the List of models merged:
Nope, I've only added and/or subtracted several Loras made by myself.
FAQ
Comments (11)
i don't know, man
i can't get ur results, all of my pics with new model are low detailed
creating with 24, 30 and 50 steps, no difference
with ur VAE blessed
i really don't know what am doing wrong, that sucks, mate, because i love arthemy comics v6
This is an interesting feedback, I'll try to improve on that, but this model does great things with img2img. Try to do that as well! 🤟🏻✨
It's a beta after all! ✨
EDIT: Wait, damn, I set the wrong VAE, try the one you can see right now!
@Arthemy thx, mate
now it's much better
gonna fill up the gallery of this model
@sprawlhare honestly, this model has a lot of worse results compared to the previous one, but its highs are really high.
I'm torn between a more "stable" version like v.60 and a very unstable yet creative version like this.
I'm starting to see this model more as an "Arthemy-painting" what do you think?
@Arthemy am gonna test it tomorrow all day, it really looks like some ReV Animated or Art&Eros models but with friendly prompting, and as i see with a few pics i created it still got this ~arthemy vibe, idk how to say
it had a lot of ART, now it's gonna have more i guess
i think you should try to improve this new one, and it's charming you ask us to generate 640x768
others are really unstable
anyway, i hope you will keep doing what ur doing
because that's what i really like
it's hard to use any other models for me, they can't give me what i want
maybe I'm dumb, but it's not really flexible as v6, but still incredibly creative
anyway pics what I'm getting are really cool, can't wait for release
UPD:
I'm taking it all back, I've got it now, i can't stop anymore from using it
Yeah, I'm noticing that it's a little bit stubborn on some aesthetics. I'm honestly thinking to keep the previous model as base and mix a small percentage of this into it... More on that in the next days! Thank you for the feedback! 💕
@Arthemy i'm sure civitai is gonna blow