Hey there,
it was about time to make an Anime based Checkpoint for IL also so here is Anillustrious ☺
V5 is made with several checkpoints and unpublished/ published Lora´s to enhance the quality and colors to get back into the IL direction ☺
V5 Showcase is made on Civitai settings apart from hi-res upscaler:
832 x 1216 / Euler a / 40 steps / CFG 7 / Hi-res x 1,526 / clip skip 2 / no adetailer
General prompt recommendation:
positive: high_quality, highres, beautiful, detailed, (masterpiece, best quality:1.2), absurdres, 8k, HDR
negative: worst_quality, bad_quality, poorly_detailed,
I hope you like it and im tense about the results !
If you like what i do consider leaving me a like or a comment , much appreciated and helps me to continue 🖤
You can also follow me or buy me a coffee ☕ at: https://ko-fi.com/jedas
stay healthy and have a great day ! :)
Description
FAQ
Comments (6)
Avoid using 'gorgeous' in +ve prompt, it gave you ugly detailed & face.
Can NOT confirm!
((EDIT: hold on, what is '+ve'? I somehow overread that... // my statement is at least for regular prompting))
You are aware that this CAN happen literaly with any prompt?
-> "gorgeous" is one of my most used adverbs included in my DynamicPrompts to generate random women descriptions, they're all looking great.
EDIT2:
Ok, figured, that (+ve) is comfy related... i'm using forge, where it (gorgeous) has absolute no bad effect (aka has the desired effect)
@Sephrajin Why would it matter what one is used, comfy or forge, whether "gorgeous" in positive would produce terrible results? Is there a link you can share?
@sansmia idk.. all i know is: i dont have a +ve prompt in Forge, AND gorgeous does faces just fine in my prompts.
Links? check the images i shared on this checkpoint, there sure is at least one with that word. :D
no problems for me neither with gorgeous in prompt
isnt gorgeous a copium placebo tag that does nothing other than adding random noise that can make faces look better or worse by chance?