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
A true return to form - this is quite similar to the previous 6.0 model but it's improved by a... quite important 5%. Images will be similar, but I trained a few LoRAs that I've merged with the model in order to tell it what types to images to avoid. This has been quite a long journey and after more than 250 iterations I've finally reached a new high for this model.
The whole point for this and other models I create is to bring results that don't really looks like AI, they might be a little bit stubborn and might require multiple img2img evolutions to get exactly what you're looking for - but if you're still a fan of SD1.5, you probably know what you're going to get.
FAQ
Comments (32)
I hope more D&D races will come up next - alluring Drow girls is a must 😜 Though wouldn't mind WoW races either - Night Elves, mmmm...
I think that a LoRA for that would be the best solution for that, in my experience, pressing the model even more towards the fantasy aesthetic might result in less generalistic applications.
Even though, I have to say, I might try to do a fantasy focused model. ✨
@Arthemy LoRA doesn't always work with every model well. Glowing eyes of Blood Elves LoRA tend to get messy for example or Orcs sometimes have only green skin on head with regular skin on hands. Model built-in solutions would be appreciated. At least with this model leaning towards elves there could be more variety in elven spectre without breaking it in other fields, hopefully 🤔
Well, thanks anyways, for spending time on reply and for giving hope for more fantasy focused model with those aethsetics 👍
@ExePriest well, for that you can draw two simple red dots on the eyes of the characters and then use img2img in order to course-correct the generations. ☺️
guys! can anybody share their experience with hires-fix settings??
I suggest using a 0.4 noise (I know, it's a lot, but it grants the AI enough space to generate new details) and a lanczos upscaler.
Usually the best results are given by a secondary "ultimate SD upscale" in img2img with a 0.35 noise.
Do you plan to do a baked vae version of v7.0?
there is literally generic VAE
I'm just in love with Arthemy Comics. It turns any of your prompts into a very stylish western illustrative picture. At the same time, with good anatomy and diversity. Of course, it can't do everything, but for such a cool style, we'll forgive it.
Great job, thanks!
Thank you very much! <3 unfortunately I think I'm reaching the limits of SD1.5 for this style and aesthetic, I'm trying to create some LoRAs and Embeddings in order to push this model even further but I might end up finally working on a SDXL model soon!
But I'm really glad that you're into my model <3
@Arthemy An ArthemyXL would be really exciting to see!
Great model. You may want to add the 'western art' and 'western animation' tags so others can discover your excellent work.
I'm going to do that Right now! :D
bro, i was thinking....
i need a hyperSD version...
I think you want to check this out: https://civitai.com/models/462532/arthemy-comics-xl
@Arthemy i can't run this locally due to using rx590 yet, but if that is on ur website i'd love to check this out
i'm sure it's gonna blow my mind, mate
@sprawlhare Man, I'm using this with 4GB of GPU on a laptop. ComfyUI is very optimized if you want a local generator.
I suggest to download Stability Matrix, use that to install ComfyUI, which makes some things easier and then, if you don't know how to use it, I can send you one of my workflows ^_^
@Arthemy stability matrix? i'll check this out, thanks, mate
but i must say, 4 gb on nvidia isn't the same thing which 8 gb on amd
i think nvidia would still win
but if it might help i'd be happy
@sprawlhare try and let me know 🤟🏻✨
you should've announced it somehow, pin it in recommended resources for example, I was waiting for XL-version and had no way to know it's here
@oddKoodoo sorry, I thought most of my followers already received an automatic message! I'll pin it right now!
it seems incompatible with hyperSD loras :((((((((((((
but still best model i've used
Oh no! I'll try to understand how to optimize it for that! :D
@Arthemy i think i've just figured it out today, but it seems it feels fine only with euler a or euler dy and normal scheduler, i'm still trying to find a perfect balance
One of the best models I've used! thank you for making it :)
Thank you for the positive feedback! Create something memorable with it 💪🏻✨
My all time favourite 1.5 model. No matter what the quality is top notch.
Thank you for the positive feedback! Usually it's the negative feedback that I crave for in order to improve my models but this... This is actually doney fresh air every once in a while. ✨
This is an amazing model but my outputs tend to be very desaturated - is there a recommended VAE for v 7? Thanks!
I just uploaded a Baked VAE version that should fix that issue! :D
Thanks so much what a hero- I'd merged you with ToonTune which fixed the VAE but now I can try some pure Art ;-)