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
Changes
Improved light handlings
Added some character / style knowledges
Handling both dynamic and non-dynamic posing
NoobAI EPS v1.1 + Illustrious v2.0-stable DARE applied
FAQ
Comments (21)
Woah! New version and no early access at that? THANK YOU!
I have a question: does every version that improves stay in the new one, that is, what you added in the 17th stay in the 18th?
For most of them, yes and I adjusted some of them for further improvements
The ones I wrote down as the Update note would be stay improved
Greetings!
The release notes for version 18 say that character lore has been added. Which ones?
Would like to know this too, thanks!
I merged Raehoshi so the latest character list of theirs would be available
@Crody This is really cool! I hope you'll update your other models with this dataset over time. Thanks for your reply.
@Crody really helpful, thanks for this!
V18 is very good for img2img as it captures the atmosphere, the pose and the style of the original image. On the other hand, it won't give you unexpected creativity to spark off your inspiration.
Well, advertised character knowledge is nowhere to be seen. At the very least, the model can't do any of the amphoreus characters from HSR. And it's been over a year.
Yeah, I noticed that too... I tried to make a pic with the rumi \(kpop demon hunters\) tag and the result was nothing like the character xD
大佬，最近的新角色没有加进去呢
If you are making femboys and expect the model to do fingering, dont expect much this model is physically incapable of doing it (v18) just use v17 for that, much better.
ughhhh just an update everything with fingering and old loras that worked is screwed over with this new one just stick with v17
What schedule type?
Visual explorer for 16,000+ Danbooru artist styles. All previews were generated using Nova Anime XL
🔗 Link: https://thetacursed.github.io/Illustrious-NoobAI-Style-Explorer/
goood
Hmmmm, so far it's good