Model Description
A stylized and overly cutified semi-chibi like anime style.
This model extend the list of "Type" prefixed models which all are designed to capture a unique art style.
License
This model is licensed under a modified Fair AI Public License 1.0-SD
(https://freedevproject.org/faipl-1.0-sd/) license.
The following modifications have been added to Fair AI Public License:
You are not permitted to run inference of this model on websites or applications allowing any form of monetization (paid inference, faster tiers, etc.).
Explicit permission for commercial inference has been granted to CivitAi, Tensor.Art and Hugging Face.
Description
This model supports the 4 names of the characters of the original artist.
They were not provided due to them being untested.
FAQ
Comments (4)
Which would you say is the best for 2d generation and/or 2d character lora compatibility?
Of this model?
Both are trained by similar Datasets, v2.0 has just more training images.
So both should result in kinda the same "compat" for 2d
@fearvel No no, I mean of your different "Types". I can eyeball them for when they're obviously 3d but there are some 2d ones that I'd want your opinion on
@Sargovel They are all based on manga, so 2d.
The 3d effect is done by the checkpoint used or the unaestheticXLv31 neg embedding.
You should not have any issue to either generate 2d or 2d comic images with any of those models.
The models with the most training images are Type D and Type F, which should result in the best quality.