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 is trained using images with minimal disruptive elements such as floating text, logos, speech bubbles, and signatures. If any of these elements are present in an image, please include the prompt "signature" as a negative prompt
Metadata and franchise tags are excluded—please do not use them. Tags such as "highres" and franchise-related tags like "re:zero kara hajimeru isekai seikatsu" are not used in training
A CFG of 3 to 7 is recommended, 6 with "Euler a", to be more specific
Look at the example images, to see how the model should be used
Model is trained to be not complicated in use, tag order:
First are the number of person, then character names, rest.
Example: 1girl, rem \(re:zero\), standing, masterpiece, upper bodyNoobAIs Loras working for the most part better in compare to Illustrious loras
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
______________________________________________________
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
Update, mainly focused on fixing issues from v3.3
Better:
- Fewer artifacts and less face/eye melting, especially at a distance
- Cleaner, less blurry outputs
- Additional training on the same dataset af v3.3, some characters working now better
What i noticed in 3.3 + now 3.4:
- Hair color prompts are less reliable (eye colors gets used for the hair, as example)
- Skin can appear extremely bright/shiny again
- Multiple views occurs more often
I believe these issues started after training with Prodigy, it is maybe to agressive. I’ve since switched to ADOPT, and results improved a bit. I may release another update with further fixes and an updated dataset. Problem is that I’m still unsure when Z-Image or Klein will get a proper anime model. I also have several experimental datasets I want to test train, including mixes of natural language and tags (including NSFW, tags combine with natural language, that describe spatial awareness of characters and positions of texts, the exact weakness of tag based models).