These loras were trained on images from Megami Magazine from late 2018 to 2026. Anima already knows the Megami Magazine tag but it's riddled with japanese text. These loras were trained with the text manually removed. Please read the About This Version for more information.
To get the results you see in the images above, these are the settings I used.
Visit My Site For Models I Can't Post On CivitAI: https://qtgurl.com/
The loras for Anima V1 were trained at 1792 resolution. So they're capable of generating at around 1792x1792 or higher.(I use 1600x1984) The P2 and P3 loras were trained at 1536 resolution, so they're capable of generating around 1536x1536. (I use 1408x1792 for most gallery images.) All of the loras are capable of generating smaller sizes just fine.
MeMaAni - V2+B
Trained on 51-68 (mostly) new and old images. Dataset was re-collected and edited for the best possible quality.
MeMaAni - V1
Trained on the same data used in Preview 3.
MeMaAni - Anima Preview 3
Trained on the same data used in Preview 2 with slight changes to improve results. Most of the improvements come from the Anima P3.
MeMaAni - Anima Preview 2
Trained on the same data used in 2d Gold Fish. I guess you could call it MeMa F, but I suppose that would make it A for this model. It uses a lot of images from the A dataset so it's close enough.
Comment On Anima
The final release of Anima 1.0 is fantastic. The model has so much capability. If you haven't made the switch, now is the time. It doesn't matter if all you post is one girl, the jump in quality, prompt comprehension, 16 channel VAE, newer anime knowledge and just raw stable performance makes it the worth while model to switch to as an anime genner.
Description
This version was trained on Anima Preview 3. I don't expect it to work well on difference versions.
I made some very small changes to the dataset but it's mostly the same as P2. The biggest difference is achieved thanks to Anima P3. Results are noticeably better. The images are noticeably cleaner. I decided to have a little fun with the images this time around.
FAQ
Comments (8)
Ty
Still couldn't find a nice upscaler for Anima. Anyone has a good recommendation?
@neclordx If you just need a one to one upscaler, I've just tried SeedVR2 in Forge Neo and it's a damn near flawless job. If you're using Forge Neo like me, some kind soul created an extension. https://github.com/yamosin/seedvr2-webui-neo-extension Just install it like normal and manually create the seedvr2 folder inside the models folder. Download whichever version of seedvr2 model works for your machine. If you use Comfy, they have their own setup with many options. Give it a try.
Can you do more anime styles from a real shows
If something interest me I might consider it but I don't plan to do any additional Anima loras until the final version is released.
Pls update :3 They released the final version
Coming soon. :)
@Fish788 excited