Nix comic is a flexible comic base - with a core style mixture of 1990s Disney animation and 2000s Marvel Comics. It is tuned to be used at 0.7-0.85 strength on most prompts, giving headroom for mixing in other LoRA or style guidance. No keywords, just add, enable, and generate.
Overbaked Variant
Author's note: These are left up for historical purpose only - their output is poor (saturation/shadows/details are all a mess). They were an attempt to apply the style in some of the NSFW and artsy checkpoints - but really just don't do well anywhere.
Why not Nix Toon v2?
This started as Nix Toon v2, but the core style drifted quite heavily. This is what I intended Nix Toon to be - extensible, but a strong core style. While re-tuning that model, I worked to eliminate same-face and the unintentional loss of cultural identity. While it's not perfect, Nix Comic is much more open to more body shapes/sizes/colours.
What's different from other Comic/Toon LoRA?
Nix Comic has a strong visual identity, with ability to take direction from other LoRA and additional style prompting (without getting too crunchy, overbaked, or breaking style). It's also built for diversity, where possible.
Special callout to @ZairaSass - some of their LoRA stack was used for inspiration.
Description
Use only if you have a realism or NSFW model that isn't playing nice with 1.1 - in models that support illustration, this will have poor shadowing and contrast.
Same changes as 1.1, just more passes.
FAQ
Comments (8)
Thx for these, I've been very pleased with v1.0 regular (I read the description for overbaked, but don't seem to need it).
Any word on what's different between 1.0 and 1.1?
Yeah, overbaked is for a couple of the NSFW or Realism models that strip/reduce the illustration side of the data for the skin/camera/hair/posing. Doesn't always work, but gets closer.
1.1 most importantly has a re-rendered set of images of the women to remove the blush and eye shadow that one of my source models applied. It means that 1.0 will almost always force a cheek blush and purple eye shadow on women in the images, 1.1 reduces that significantly (and allows for more control over makeup and blemishes/freckles). Also I removed 2 images from my data set I believe caused some strange colour application in certain scenarios.
1.1 also seems to have a slightly bigger base breast size (one of my removed images must have been influencing the sizing a little), but plays MUCH nicer with breast sliders
@xFennec777 Thx for the quick replies! =) I'll be downloading the 1.1, then. I'll be sure to post any good images that won't upset the delicate Civ rater too much. LoRA's like these I definitely want to try and help give some exposure.
@Otto_Mattiq Cheers! Post anything. The NSFW stuff keeps to CivRed. Any sharing/exposure is great! Appreciate the feedback :)
Thanks for all the work, I love this lora :)
I like the style and versatility of this LoRA. I have a feeling our style goals align. Your article on LoRA-training was very enlightening.
Oh, and thanks for the buzz ;)
Thanks! Yeah, I think there are similar goals - yours tends to come out more painterly in my tests (which is really kinda cool). Zass and 1990s/2000s Disney animation are my base + any versatility for people to direct it :)