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
Fixing hand issue by merging Nova Orange and Nova Unreal
FAQ
Comments (24)
Is it really Illustrious 2.0 with 20M arts finetune on 1536x1536 res?
No, it's a 2.0 model of Nova based on Illustrious, which hasn't even released a 1.0 version, let alone a 2.0.
Too bad Noob AI 1.0 just dropped, would you train a new one around it?
I'll probably post it around next week
With others as well (Orange, Unreal and Furry)
No comment on 2.5, it's almost there, still a bit mushy... But it's there!
May I ask how to use this model........This model produces good results online. I want to try running it locally. How should I do it.........(∂ω∂)I only know that this is related to stable diffusion
This model is based on SDXL, which model size gets much larger compared to SD1.5 models thus VRAM as well
If you want to use it locally but you don't have much VRAM, I suggest using it on online
I always use this on Kaggle using Diffusers + sd_embed which I explained in the article on Suggested Resources
If you have NVIDIA GPU you can easily use this model with Forge UI, use the latest version it has optimized VRAM usage that could run even on 4GB VRAM. There's a one click installer on the github repo.
@Crody thank u bro :) i understand
@nz ok .(∂ω∂) Unfortunately I only have Integrated graphics
2.5v is just outstanding, prompt adherence is close to flux level, is a breeze to prompt on it, the only "downside" is a bit low contrast, but it's my favourite model so far!
Full body shots ruin the eyes. Any fix with this?
honestly, adetailer works with eyes
@Noxy_ Wanted to avoid loras, but I guess you're right. Ty.
@GhostR7 it's actually different from loras, there's a good few adetailers in here that still works (even if they were months ago) try it and see the difference!
@Noxy_ Could you suggest some of them please? If it's not a bother ofcourse.
@GhostR7 https://civitai.com/models/150925 is my used one thus far, even with age it still works well for fine, there's another recent one (6 months tho) but it maybe good too
@Noxy_ Thank you, I will try it. Happy new year btw, and thanks for your time!
@GhostR7 https://civitai.com/models/330727?modelVersionId=373036 I recommend this one as it detects a pair of eyes and makes them look correct together/matching.
@HaloSkull Looks good! Thing is, I'm using Fooocus and I don't know where I should place the file. Any idea or should I check further? Thanks for your time and the suggestiong btw!
@GhostR7 It should go in models/adetailer if its not there make it. I don't think installing adetailer necessarily makes that folder. I haven't used fooocus tho so your mileage may vary.
@HaloSkull I will try it when I open fooocus again. Thanks for your time and the link!
Just tried out Nova AI 2.5
PLEASE PLEASE PLEASEEEEEEEE
FIND A WAY TO PUT THIS ON THE ON-SITE GENERATOR SO I CAN USE IT WITH MY LORA's ITS TOO GOOD, I WILL PAY BUZZ FOR YOU TO DO IT
The most awesome retro style model so far
Details
Files
novaAnimeXL_ilV25MerryChristmas.safetensors
Mirrors
novaAnimeXL_ilV25MerryChristmas.safetensors
novaAnimeXL_ilV25MerryChristmas.safetensors
novaAnimeXL_ilV25MerryChristmas.safetensors
novaAnimeXL_ilV25MerryChristmas.safetensors
novaAnimeXL_ilV25MerryChristmas.safetensors
novaAnimeXL_ilV25MerryChristmas.safetensors
NovaAnimeILV30.safetensors
novaAnimeXL_ilV25MerryChristmas.safetensors
novaAnimeXL_ilV25MerryChristmas.safetensors
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.