Anima Version is Available!!
Nova Anime XL
Nova Anime XL is Nova Anime: Anime/2.5D/3D checkpoint model for SDXL
Pony version aims to get the similar look as both Nova Anime and Nova Domain
All images on example were created with diffusers with custom png tags
PixAI - IL v4.0 Happy Valentine
PixAI - IL v3.0 Happy New Year
PixAI - IL v2.5 Merry Christmas
Rules
You cannot use the generated images for commercial use if it's not edited (or just turning it to black and white)
You can share images without any restriction if you don't monetize it
Advertising this model to outside is always welcome
Recommend Settings
Sampler: Euler a
Steps: 20~30
Clip Skip: 1-2
Denoising Strength: 0.65 - 0.8
(Pony)
CFG Scale: 5~7
Prompt: score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, source_anime, BREAK
Negative Prompts: score_4, score_5, 3d, jpeg artifacts, username, watermark, signature, normal quality, worst quality, large head, low quality, text, error, missing fingers, extra digits, fewer digits, bad eye
(Illustrious)
CFG Scale: 4~6
Prompt: masterpiece, best quality, amazing quality, 4k, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, {Prompt}, BREAK, depth of field, volumetric lighting
Negative Prompts: modern, recent, old, oldest, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured, long body, lowres, bad anatomy, bad hands, missing fingers, extra digits, fewer digits, cropped, very displeasing, (worst quality, bad quality:1.2), bad anatomy, sketch, jpeg artifacts, signature, watermark, username, signature, simple background, conjoined,bad ai-generated
Description
Revert coloring to make it similar with the previous versions
Mixture of both detailed coloring and high contrast
NoobAI EPS v1.1 + Illustrious v2.0-stable DARE applied
FAQ
Comments (27)
This model is very cool! Only thing I personally would like is an updated dataset.
v12.5 has a clear anime style and is closer to v11
i am sorry i am new but whats the trigger word??
This is checkpoint, not LoRA
There's no trigger word to use it
v12.5 is the best version. I love this version.
LOVE 12.5! Better than waiNSFW? Maybe!
Im not really into anime lude but this model is really good ! 12.5
i like the way the dress came out
where is Nova Mature XL?
@Crody thanks, i can't find it in your models.
From my experience, version 12.5 produces great and stable body shapes without requiring much effort in anatomical details, even at high Hires Denoising strength. While I personally prefer the artistic detail of version 12.0, I think this new version is excellent.
I love it! ❤️🎉
The link to "Crody's Illustrious... Tips" page seems dead. It would need to be updated, possibly to this link:
https://civitai.com/articles/19107/crodys-illustrious-noobai-image-generation-tips
To me the link and suggested resource path goes to the correct page
i love this one
v12.5 create more accurate objects, but also more artifacts. Sightly better hand but decoration is more bland compare to v12
v12.5 is my new waifu
Are there any plans to update the dataset?
I cannot assume about when to update since I don't have any information about newer Illustrious but if there's newer datasets I can merge with, yes I'll update it
Apologies for being late, haven't ran this since my tunnel wasn't damn responding and I had to use a backup (it was slow and awful)
I think I like this v12.5, although I never got the chance to test more, it got my character back to normal though
Been loving working with this over the last month or two ❤️
I'm always wondering with the changelog description.
When you mean with "Characters knowledge" it is for the actual characters and more updated dataset ?
It means that I extended the capability of characters up to newest
You can see a part of them on the sample images (for example Reze and Cyrene)
@Crody When you say characters, are you referring to personas or text glyphs?
@HumbleDeer It's about personas
Newer characters on danbooru are available now
For text glyphs, I cannot tell but probably?
You can insert texts (not so greatly) using some prompts like 'COOL' text printed red shirt
@Crody My question was what you're referring to when you say you've improved characters or the likes. That means I'm asking about whether you had changed things about the personas as characters, or whether you were referring to the text prompts for them, which are letters, and we see them on our screens as glyphs.
But your reply seems to heavily imply you're definitely talking about characters as personas, which would go paired with the text prompt that it would result from as well.
So that's clear. :)