7/8/2026 Anima 5.1 Update
Another update... I was not satisfied with the previous version, despite it being actually pretty solid. I've made some major changes, I cut out a ton of the dataset that wasn't good, and did a major focus on any art that accurately depicted her fishnets for substantially better wraps! I tried a new training method, which might be a little overtuned, my bad if it's not quite as good. If anyone wants lower-epoch versions of this model, let me know in the comments and I can upload it.
Notes:
- Fishnets are MUCH better in this version, prompt with "kanna classic outfit" for significantly improved fishnet-wraps. This tag is all art in the dataset where she is wearing her standout bodysuit outfit WITH fishnets.
- Fixed images being zoomed-in, this was because a previous software I used did some auto-cropping on my dataset, and screwed everything up... I only noticed after I posted the model. Oops.
- It's a bit strong, sorry if the colors are messed with, try lowering the strength, or put more emphasis on artist tags to remedy this.
- Yup.
Older Descriptions:
7/1/2026 Anima Update
Anima Update! It's been so long since I've trained anything... But I see this Kanna lora as a special thing for me, so I had to come back at least for this. It has the same dataset, which was mostly due to me being lazy, since it uses E621-style tags. Oops. Either way, it seems to still work pretty good.
Notes:
- For some reason, it seems to focus the image a bit closer to her if used at full strength... Like, images are more likely to be upper-body or headshot portrait without specifying. I have no idea why it does this, you can help fight it by slightly lowering the strength or prompting for 'full length' or 'full body' shots. I'll try and fix this in future versions.
- Hopefully this isn't too overtrained, Anima seems to have very minor knowledge of this character.
- Her 'fishnets' are still pretty inconsistent... Try writing sentences out describing them