ver.20260610/20260519/20260425/20260329/20260302
Quality tag&Negative prompt:May or may not be used. / 使っても良いし、使わなくても良いかも。
ver.20260610
暗所が出にくくなっていたのでデータセットを作り直して調整。調整後、darkやnight等の画面を暗くするプロンプトを入れると、黒帯がかなり強めに出るようになってしまったので、それも再調整して是正。
現状、黒帯は全く出ないというわけではないですが、かなり出にくくなったはずです。
クオリティタグないしネガティブプロンプトは必須ではありません。サンプル画像は全てクオリティタグとネガティブプロンプトを付けていません。
※2026.6.10 23:50 サンプル画像を調整前のモデルで作成したもので上げてしまっていたので差し替えました。
Since dark areas were becoming less likely to appear, I rebuilt the dataset and made adjustments. After the adjustments, when I included prompts like “dark” or “night” that darken the screen, black bands started appearing quite prominently, so I readjusted the model to correct that as well.
Currently, black bands aren’t completely absent, but they should be much less likely to appear.
Quality tags and negative prompts are not required. None of the sample images include quality tags or negative prompts.
旧版の概要はdescriptionから各ver.のabout this versionへ移動させました。
Description
based on anima(https://huggingface.co/circlestone-labs/Anima).
Special thanks to the authors of the models anima.
ver.20260302
A fine-tuned model based on anima-preview.
Positive/negative prompt quality tags are not required. (All sample images were generated without using quality tags.)
The art style leans toward anime-style coloring.
Additional note
Similar to ver.20260216, we ultimately merged the base model anima-preview after model adjustment. (Merged with a weight of approximately 0.4)
The goal is to suppress the loss of compositional flexibility that occurs due to additional training. However, merging with the base model effectively reverts the model to an untrained state to that extent. Overdoing this diminishes or eliminates the effects of the additional training.
Therefore, this time we employed a technique where we trained the model to produce visually distinguishable anime-style coloring, then increased the base model's merge ratio within the range where the anime-style coloring remains intact (even without a quality tag).
FAQ
Comments (9)
By far the best finetune i have seen of Anima so far!
Gr8 job!
it has good generating model but, its the wors pompt adherence of all anima models
I kinda agree with you. The images are nice but it's very random, it's not worth it
@Tetsuoo yea whats the point of using anima if we cant even get a good prompt result xD,
@Seii1 Just use Anima-Preview or V2, they're both good with prompts. Then you can make it better with Illustrious. I'm testing V2 right now it's not bad at all
@Tetsuoo yea but i use animayume for high resolution
@Seii1 Right, AnimaYume is really good even better than Anima V2, now I have 7 Anima models maybe it's time to delete a few before it gets too confusing lol
This is a really great model! Please update it for anima preview 2!
in forge Neo my output is always the color pink, i have all my settings set the same with the same clip and encoder... what is going wrong with my generations