Recommended versions :"vanilla-newlora-ver1","super-vanilla-v4","nekopara-vanilla-v5", the rest are not recommended
vanilla-newlora-ver1
This version supports multiple people
But it will be affected by Hires. fix
The most popular were chocolate and vanilla
It is forbidden to sell the images generated by this model for profit, and it is forbidden to sell this model. Thank you
禁止将此模型生成出的图片进行出售盈利行为，禁止出售此模型。谢谢
Please watch the release introduction for detailed information
请观看版本介绍 有详细的信息
The model generalizes and transfers very well, and you can use it on almost any submodel (except SDXL).
If you want to restore the original painting style, you need a lot of prompt words to correct, the model's data set contains all nekopara images, the game illustrator artbook and fanclub cover, theoretically it can restore all images
vanilla-newlora-ver1
This version is trained for classification
Older versions of the dataset are discarded
Stronger support for multiple people
Supports the human hand model
The overall painting style shifts towards nekopara4
More rounds of training were performed on high-quality datasets
High-quality data sets trigger the word vanilla
Generalization trigger word xiangcao
Hand trigger word shouban
r18 Trigger word nsfw
Multi-person trigger word girls
Description
FAQ
Comments (5)
It's amusing how you manage to come back with even better models every time.
I have a bit of a problem with the generation having a Chocola and Vanilla. I get either 2 Chocolas or Vanilla and some kind of abomination. It doesn't look like you use any extensions in your generations, so I'm a little confused
I don't highly recommend using this model to directly generate duos, as its compatibility with duos is just much improved from before, but not perfect in generating them. When generating duos, be cautious not to enable plugins like face repair or any that would redraw. They can cause confusion in the concept. When generating duos, ensure your base model supports them better, or else you might get odd images. If the hair color is the same, consider enhancing the "blackhair" tag.
I still suggest generating single characters because handling duos is inherently challenging for AI. Experiment more; the new version of the dataset includes multiple characters, NSFW multiple characters, figurine models, single characters, and concepts.
The better images I generate are posted on Pixiv, and you can check them out. userid:84376185
底模用的哪个啊
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.