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
Much deeper / saturated colors
Dynamic posing
NoobAI EPS v1.1 + Illustrious v2.0-stable DARE applied
Z-Image Base came out last month so I guess I'll switch the base model into it after someone create Z-Image Illustrious model
Nobody knows whether this is the last version or not but I'm looking forward for newer structures
FAQ
Comments (21)
v16 add poses compared to v15 but when I add ribbon between the breast, strange thing like a remote or token was added with around 25% chance.
I am a beginner and can anyone tell me where is the workflow?
이미지를 저장하고, 컴피ui 캔버스에 드래그 앤 드랍하세요. 원본 이미지가 곧 워크플로우 입니다.
I'm struggling to create skinny men without muscles. With this checkpoint, I want to create the classic anime character who has just arrived in an isekai without muscles or six-pack abs. Any suggestions?
Find some Loras with the style you want, using lower weights and higher CFG scales
Hey, I've done a lot of testing, and statistically, this model fails to generate images of men 40% of the time. In a workflow that generates 300 images, 120 of them are women. All 300 images used the same character description; what changed was the point of view and the clothing. Obviously, all the prompts share male clothing. I have strongly reinforced the negative prompt to avoid generating women, and even so, it still creates them. Any suggest?
@endk135 Could you put woman, girl or 1girl in the negative prompt?
Nova Anime is known for not great adherence for male generation and I don't know how to avoid it without changing the style
With the negative prompt, it should provide what you want
Other than that, try using other Nova models like Nova Orange
@Crody yep all the test mentioned before was using a negative prompt for a few tags for girls, nothing works... also a lora didn't prevent the error, talking in fast test for every 33 generated images, 20 was female cada, all the images was generated with the same character description and every 11 with different male clothes.
If you add prompts like: male focus, skinny, skinny fit to your positive keywords - Negative prompts: Muscles, too much muscle, Bara - I know that for me, it usually works by adding a word like this, especially "male focus" which tries to force the model to generate a man.
@Zero30 thanks I will try
Absolute cinema man(woman?)! Thank you a lot for doing this!
... v16 seems nasty. Better posing, but worse adherence and a really messy look. It's like a 1.5 model.
A joy to use
So much better than v15
no se puede utilizar la nueva version en pixAI
Todavía en proceso de carga
@Crody How long does it take to upload the new model to Pixai?
@deivytejada0124 Probably they're having problem with finalizing it
I did it with Nova 3DCG as well but it still doing the process
I'll do it manually
EDIT: Currently, it cannot be done by manual uploading as well
The model is available on SeaArt and OurtAI as well so try them instead
@Crody The thing is, I only use PixAI and I really like this model.
@deivytejada0124 Someone else figured out and uploaded it
https://pixai.art/en/model/1985915954842364857