■This is an experimental ground for Anima LoRAs.
The LoRAs I create serve more of a role in stylistic tuning rather than reinforcing single concepts.There is no inherent superiority among the LoRAs; they simply serve different purposes. You can find the description for each LoRA in its respective tab.
■I would like to share the possibilities of anima with everyone.
My wish is for many people to discover basemodels with potential and to see their possibilities unfold even further. I would be happy if I can help make that happen.
■The anima architecture has been heavily modified and retrained from scratch—almost like a radical overhaul—but the base architecture is Cosmos-Predict2-2B. To put it simply, you could compare it to a lightweight version of Flux 1.
I think it’s a great architecture capable of generating high-quality images despite its small size.
I have a very good impression of Anima when it comes to color vibrancy, lighting, and prompt adherence.
Its knowledge regarding NSFW concepts, characters, and styles is at least on par with SDXL. The overall feel of using it is also quite similar to SDXL.
Furthermore, it is lightweight and easy to train. I believe large-scale training is also a viable option.
Since we are provided with a base model that already contains a vast amount of knowledge, we rarely need to teach the model completely unknown concepts from scratch.
Basically, our work mostly comes down to adjusting styles or reinforcing minor concepts and characters. You can achieve great results without having to do any heavy lifting.
The developer has also ensured transparency by sharing the training settings, which means you are less likely to stumble over black-box issues.
Because of this, the burden of training is low, making it an option well worth nurturing together as a community.
■The LoRA has a stronger influence when used with shorter prompts.
Since longer prompts often carry their own inherent style, the LoRA will primarily take on a supporting role to refine and unify the overall image.
■https://github.com/gazingstars123/Anima-Standalone-Trainer
This is a great tool that allows for easy training, even on Windows. It has everything you need for LoRA training.
Even if you run into any issues, you should be able to get your LoRA training up and running by troubleshooting with ChatGPT or Gemini.
If you find the tool useful, you might want to consider making a donation to him. It allows the developer to focus more on development and deliver even better tools, which ultimately benefits you in the long run.
■If you have any questions, please feel free to ask!
日本語での質問も大丈夫ですのでご気軽にお声がけください～
Description
Overview
This is a style LoRA based on the masterpiece Gundam OVA, Mobile Suit Gundam 0083: Stardust Memory. It was trained on a carefully curated dataset of 2,500 screenshots taken from across all episodes.
Recommended Settings
A LoRA weight between 0.5 and 0.8 should be just right. A weight of 1.0 might be a bit too strong.
Style Characteristics & Merging Potential
A highly notable feature of this LoRA is how faithfully it reproduces the stunning background art. It truly captures the authentic atmosphere of the original series.
Please note that the character style is fairly locked. Female characters will likely resemble Nina Purpleton or Cima Garahau, while male characters will often look like Kou Uraki, Anavel Gato, or South Burning. To be honest, because these characters appear so frequently in the training data, their features have essentially become the default style regardless of gender. As a result, this LoRA naturally produces an older, more mature adult vibe.
The outputs often turn out dark or have low contrast, but this is because the source screenshots naturally share these characteristics. I considered applying level correction to the dataset, but decided to leave it as is to avoid ruining the authentic atmosphere of the original work.
Lowering the LoRA weight will reduce this strict stylization and give you more flexibility.
Additionally, this LoRA has great potential as an ingredient for model merging. A LoRA that offers such excellent background generation alongside a mature character style is quite rare, so mixing a little bit of it into your models could add a really nice spice to your generations.
I'm also sharing some backups from different steps. You might find other steps easier to work with, so feel free to try them out.
A Final Personal Note
On a side note: The Gundam OVA series are all absolute masterpieces. Works like 0080: War in the Pocket, 0083: Stardust Memory, and The 08th MS Team represent the absolute pinnacle of cel-animated Gundam.
The animation in these shows is so meticulously detailed it borders on madness, and every single cut is like a work of art, even by today's standards. If you've never watched them, they are absolutely worth your time. Even if you know nothing about the Gundam franchise, you can dive right in and understand the story without any issues—and watching them will leave you with the same deep satisfaction as eating a premium, high-quality steak.