Important things:
strongly recommend using speech bubble, simple background in negative prompt with at least 1.0 strength (I've been using 1.5)
You'll get the best results with setting minimum resolution to at least 768x768
Some of my showcase images use ADetailer for faces, but most don't
For showcase images I used 4x-AnimeSharp upscaler for Hires. Fix set to 0.4 denoising strength
This started with trying to answer a bounty but I found it more interesting so continued to work on it - this is a LoRA to try and reproduce the style of JAB Comix. I used this mostly as a learning experience to develop and get more familiar with making LoRA's. It's far from perfect and has lots of it's own issues but I was able to at least make some images that I felt were true to the style with it.
This was trained against the Aniverse 1.5 checkpoint model, so it seems to work best with that but it works to varying degrees with other models in my limited testing.
Version 1.2 Experimental
I tried training in a separate concept to reproduce Laz's art style with a new trigger word. I'm not particularly satisfied with it but I thought I'd just post it as someone may like it better. A few of the captions cause the styles to bleed into each other which modifies output which may not be desirable - you may prefer version 1.1 because of this.
Version 1.1
I originally made a major error in my assumptions about the comics and have corrected that for this version. The trigger word is changed to j4bc0m1x_jab and it should accurately and reliably reproduce his specific style now. Recommended strength is now 0.8.
Version 1.0
This is a mixing of multiple artists due to an error on my part. I'm leaving it available in case someone wants to play with it as it can still make images in that general style but it's not accurate to a specific artist like Jab. It's technically a mixing of Jab and Laz's art styles, you can control it to a degree by invoking other trigger words (based on the comics trained against), they're found in the trigger words info.
Description
initial release version
FAQ
Comments (7)
The linework looks like jab, but the faces don't have his look.
not disagreeing with you but can you point to specific examples that are faces with his look? There seems to be a fair bit of variety between older comics and newer ones and the various series.
@aiask The comics you used are by 4 different artist (LAZ, Mark kleanup, pumpkin, and jab himself) that draw for Jabcomix, so when you train the AI it captures it all as one and you're gonna get messy results.
I'm currently working on a Jab style too, trying to unmix my first two styles.
@Corruptedcupid Thats exactly what I'm seeing.
I don't know off the top of my head but you should check the cover for each issue, thats where it says if Jab actually did it. Like CorruptedCupid said, theres alot of people drawing for him now and I think thats why your training looks like that...almost like a new thing...but not the original jab.
@Corruptedcupid thank you! I am evidently uneducated on the artists and the comics themselves. I will fix this and reorganize in a future version
@AstralNemesis yes I realize my error now thanks, will fix in future versions - this is 100% the issue, that's how my training dataset is set up
@aiask please keep going I love jab! Great idea!
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.