■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.
■If you notice pixel patterns in your generated images, try the VAE below. It removes the pixelation typical of the qwen_vae and makes the images much sharper.
https://civarchive.com/models/2718533/hdr-vae-anima-qwen-image
■If the VAE looks a bit too saturated for your taste, try using this VAE merge node to blend it with the original qwen_vae to dial it in. A 0.5 merge should be just right.
https://civarchive.com/models/2487550/vae-merger-for-comfyui-anima
■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～
If you enjoy my work and feel like making a donation, I would be incredibly grateful. Even the smallest token of support goes a long way in helping me lighten the load.
Whether I receive donations or not, I will keep doing what I love and pursuing my interests just as I always have. However, simply knowing that this kind of support exists brings me immense joy and serves as a huge driving force for me.
Description
This LoRA was trained on 5,250 carefully selected images from all episodes of the masterpiece Gundam OVAs: The 08th MS Team and 0083: Stardust Memory.
Style Characteristics
It perfectly blends the breathtaking background art and profound atmosphere of 0083 with the cute character designs and lush, vibrant energy of The 08th MS Team.
I absolutely love the art styles of both series, so combining their best elements has resulted in a style that is very close to my personal ideal.
Flexibility & Usage
Because both works were trained together in a single run, the bias toward specific characters or scenes has been mitigated. As a result, this is a highly versatile and flexible LoRA.
Tip: If you want to faithfully recreate the exact style of either individual show, I recommend using the dedicated style LoRAs I created previously, or perhaps mixing them into your merges as a little extra spice!
About the Files & Backups
To stabilize the style, this main LoRA is a merge of several different training steps.
I am also sharing the unmerged backup LoRAs that were used as ingredients for this merge. Included in these files is a version trained all the way up to 5250 steps, so I highly recommend experimenting with them to find the exact strength and look you prefer.
A Personal Note on the Anime
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.
FAQ
Comments (10)
Very well made loras! Is it possible to make a general 90s/Retro anime style? I know there are a few already, but your loras seems to have really good quality comparatively.
Thank you! I don't have a 90s dataset put together right now, so it might take some time, but I might give it a try.
It's hard to find images with highly detailed, quality backgrounds on Danbooru, so I might build a dataset focusing mostly on 90s OVAs and anime movies. I'm not a huge expert on that era, but titles like Evangelion, Ghost in the Shell, and Akira could be good candidates. Since those tend to lean towards a more realistic aesthetic, I feel like I should probably include some cuter styles with bigger eyes as well...
My knowledge is a bit limited, so if you have any favorite works from that era, I'd love to hear your recommendations! I might include them in the dataset too.
@hjhf Hi, Thanks for responding.
Regarding what styles, hmmm in addition to what you've already mentioned, I'd say -- Gunbuster, Trigun, Evangelion, Plastic Little, GITS, Genocyber, Cyber City Oedo 808, Goku Midnight Eye, Vampire Hunter D, Spriggan, Cowboy Bebop, Gunsmith Cats, Agent Aika, Angel Cop, Bubblegum Crisis, Project AKo, Ninja Scroll, Venus Wars, Wicked City.
I don't know if that helps. But that's the vibe I like.
Maybe you can add more... Going by how you've done the last lora, I say you have a great eye for the style hehe!
And no worries, take your time and let it cook!
@bl4ckfyr3
Thanks for sharing! I definitely get the style you're going for now. Those are all absolute masterpieces of cel animation!
Fortunately, I already own the DVD for Gunbuster, Vampire Hunter D, Cowboy Bebop, Gunsmith Cats, Ninja Scroll, and Wicked City. There are quite a few others on your list that I haven't seen before, so I'll be sure to check them out.
I'm really glad to hear from someone who knows so much about anime. Thanks to you, I got some amazing inspiration!
Right now, I'm thinking I might need to make three versions: a "cool/mature" version, a "cute" version with bigger eyes, and a version that mixes everything together. It will take some time, but I'll get it done eventually!
@hjhf Glad to hear that! Take your time!
I'd love a retro anime checkpoint!
I don't think I'll be able to do a full fine-tune on a checkpoint, but I'll try putting together a dataset to test out a 90s LoRA. If you have any favorite titles you'd like me to include in the dataset, please feel free to let me know! I'd love to use them as a reference.
vampire hunter D movie?
Oh, that might be good too. It might be worth including in the dataset.
@hjhf ooo can't wait!