Hassaku aims to be a anime model with a bright and distinct anime style.
My Discord for everything related to anime models and art.
If you'd like to support my work, you can do so at: SubscribeStar, every bit helps and is truly appreciated!
____________________________________________________________
Supporters:
Thanks to my supporters tamashiicolle, pttcot, SETI and Kodokuna
____________________________________________________________
Using the model:
The model was trained primarily on images with minimal disruptive elements, such as floating text, logos, speech bubbles, or signatures. If any of these elements appear in an image, please include "signature" in your negative prompt.
Danbooru Metadata and franchise tags are not used in training, so please avoid using them in prompts. Metadata such as "highres" and franchise tags like "re:zero kara hajimeru isekai seikatsu" are not used in training.
A CFG scale between 3 and 7 is recommended. For best results, use CFG 6 with the Euler a sampler.
Refer to the example images, to understand, how the model should be used.
The model is designed to be simple and straightforward to prompt. Use the following tag order:
Number of characters
Character Tags
All remaining tags
Example: 1girl, rem \(re:zero\), standing, masterpiece, upper body
Here are some resolution options for SDXL:
1536 x 640
1344 x 768
1216 x 832
1152 x 896
1024 x 1024
896 x 1152
832 x 1216 (most recommended)
768 x 1344
640 x 1536
Lora use:
NoobAIs Loras working for the most part better in compare to Illustrious loras
Versions 2 and 3 is less compatible to most loras trained on Illustrious or Noob, because it got further trained away of both. Style A is still the most compatible for it.
______________________________________________________
Version and License info:
Below V1 merges ANIMAGINE XL 3.0
Version V1 use Illustrious-XL & WAI-NSFW-illustrious-SDXL with additional training
V2 is trained on its own and don't include any extra merge. Base was V1, it is trained to include newer or missing characters. It was also used for further training tests
V3 is a merge of Illustrious-XL and V2.2, to fix some issues and was also trained to include newer or missing characters
All Models using the Fair AI Public License 1.0-SD license.
Description
Eyes having a bit more problems, nsfw got a bit more precise.
Bodys have a bit less wingles and stuff, albeit only a little less for te most part.
I noticed that anything in negative goes sometimes a bit crazy, with a drop of quality. Not sure how to change that.
It sadly don't learn faster, changes are not that big inbetween versions.
Concentrating a bit more on sfw now, without negleting nsfw.
FAQ
Comments (4)
Don't know why but I am not being able to generate anything with this model.
I'm not into anime much, but you get a solid like from me because you've paid enough attention to know that the negative prompt isn't supposed to have a complete dictionary in it.
From what I've tested it does quite well.. for sdxl. I swear it loves to fight me when I try to add anything nsfw, it's normally 1/3 pics gives me what I want, though I don't believe that's on you, just how sdxl is. For future versions are you planning to also add in more nsfw concepts, (cunnilingus comes to mind, to my knowledge no lora for sdxl yet of that) or are you just trying to get it to not fight nudity as much? Regardless one thing I can say is that, as someone mentioned in the comments, that you've done a great job with not needing to add many if any negatives into the prompt to get it to gen great images. Great work!
Thanks! Its sdxl, thats why its a alpha version, sdxl fights to get nsfw concepts in, more or less because its completly new to it and sdxl needs quite a bit of training for new concepts. But its already much more then base sdxl can do. Cunnilingus is in planning, but is hard to do, everything where bodys colide is hard to get right