Nova Anime AM
Nova Anime Anima is Nova Anime: Anime/2.5D/3D checkpoint model for Anima
All images on example were created with diffusers with custom png tags
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 Normal
Steps: 20~30
Clip Skip: 1-2
Denoising Strength: 0.65 - 0.8
CFG Scale: 4~6
Prompt: masterpiece, best quality, score_9, score_8, score_7, year 2025, newest, highres, absurdres, very aesthetic, scenery, {Prompt}
Negative Prompts: worst quality, low quality, early, old, score_1, score_2, score_3, cartoon, graphic, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured, long body, bad anatomy, bad hands, missing fingers, extra fingers, extra digits, fewer digits, cropped, very displeasing, artist name, blurry, jpeg artifacts, lowres, censor
Description
Initial Version
Anima-preview3 base
FAQ
Comments (16)
v1.0 got released!
This doesn't mean that Nova Anime XL will be discontinued: both XL and AM will be updated
Crody thank you so much for all the hard work you've done over the years. It's been a pleasure using your XL models. Anima is such an exciting model and it's great to see big creators on here like you, WAI0731, reakaakasky, duongve13112002... Join the world of anima. Can't wait to try this.
So what are pros and cons compared to AnimaYume one ? And how it was finetuned from base preview model ?
@Lynx2025 I don't compare with other models but in terms of details within background and clothing, this model is great
Other than that, Nova Anime AM supports much better NSFW situations as well
I really like Anima, but it’s a model that REALLY needs to be refined! especially compositions involving more than one character. It’s a model with INCREDIBLE potential!
I agree however that's why it's still in preview stage. Each preview has been a big improvement to the last.
Feedback: v1 appears to be overfitted to one character in the center of the image. Prompting more than one characters the model often put other characters in the background.
v1 also seems to be a distilled model, probably merged anima turbo. I loaded anima turbo with strength 0.2, found the model can already generate clear output with cfg 1 and 12 steps. With LoRA strength 1 I got oversaturated output.
I might be mistaken. But it would be nice if we have some info about merged distilled LoRA. So we won't under/over apply distilled LoRA again. Or don't merge distilled model. Distilled model often looks sloppier, less flexibility.
what is the difference between nova anime and nova orange checkpoints?
Just an art style as far as I know.
Has some trouble making characters in more complex positions/situations compared to WAI, but still a rather good model (especially a first iteration). Does background much better than WAI imo.
Super cool ! came from a image posted in RTBT i was waiting on your first release on anima version ! Can't wait to test and use it x)
Am I hallucinating, or this model has some green tint? Not much, but if you generate dozen or so pictures you will notice that resulting pictures has greenish hue.
A short hint on which vae and clip model we actually need would be helpful, for everyone else
https://huggingface.co/circlestone-labs/Anima/tree/main
I mean that's on them for not knowing this about anima. Not a gatekeeper but at least look up the model
Anima 1.0?
Yes, you can see in the "About this version" tab