Anima official release!
released BASE1.
This model is based on anima-base-v1.0.
CottonAnima is a merged model based on Anima, combined with a style LoRA (trained on 100 + 60 AI-generated images).
This model adopts a fixed art style, resulting in improved style consistency. Please note that this comes at the cost of some of Anima’s original strength in diversity.
Recommended settings
Sampler: er_sde
CFG: 5
Steps: 24～30
Quality tags:
masterpiece, highres, absurdres, newestNegative prompt:
worst quality, low quality, score_1, score_2, score_3, blurry, jpeg artifacts, sepia, username, watermark, chibi, source_pony,source_furry,source_cartoon, monochrome, greyscale, 3d, realistic, backlighting,Description
FAQ
Comments (9)
I am truly impressed by their ability to execute rapid updates
高速更新の実行能力に敬服する
Random Thoughts
This model really enhances the bust. It gives a “peko” effect to the chest. It does this even without the ‘breasts’ tag. I suspect that characters who haven’t been labeled as “flat-chested”—or whose data hasn’t been trained on that—generally have a bust size larger than “medium.”
I don’t mind it one bit!!
雑感
このモデルはめっちゃ盛る。胸を盛るペコする。breastsタグなしでも盛るペコ。 おそらく「このキャラクターはフラットチェストだ」と思われていない学習されていないキャラは総じてmediumより盛る。
わたしは一向にかまわんッッ
may i ask how you merged this?
It's not very friendly to men, and there's a high probability of it being used to support women or femboy
Can you drop the Lora as well? I want to dial in weight myself depending on the artstyle i'm going for.
I’ve got the perfect model for someone like you who wants to tweak the art style yourself — it’s called anima-preview
@uraoto ...Seriously bro? I specifically like your artstyle, for example if i'm having trouble with text for a particular image having control to lower the weight bit by bit to increase text accuracy would be beneficial or simply lowering weight so that an artist "mixes" differently. Secondly how did you get your anime layer patch to use values higher than what is set for the node?