Hassaku aims to be a anime model with a bright and distinct anime style.
You can run Hassaku XL and use its API on SinkIn: https://sinkin.ai/m/JWknjgr
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
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
- Trained on up-to-date data, data cut last month. However, characters such as Ye Shunguang (ZZZ) still require many support tags and it will only depict her head right.
- Slightly improved prompt adherence.
- Brighter faces, less in shadows.
- More stable overall output, though somewhat more restrictive.
- Fewer unintended multiple-view compositions.
- Characters previously trained new in version 3.2 are now better trained in.
Worse:
- More sensitive to poorly structured prompts or a low number of prompt tags.
- Eye colors may occasionally differ from what is specified in the prompt.
- Style can be more inconsistent on some concepts, especially for characters.
Notes:
- Style can be inconsistent, especially for characters. Because the style merge is only strong enough to avoid breaking artist and character tags and that additional loras don't break the model to much.
- Use "Euler a" as the sampler, this is the sampler the model was primarily tested on.
- If only one character is desired, use “1girl” and add “solo” if necessary.
- To avoid nsfw art, put "nude" into the negative
The model was additional trained longer on a more unbiased dataset.
Now trained on bf16, prodigy with simplified ademamix, Factored + stachastic rounding, OrthoGrad to prevent overfitting and active Kourkotas Beta.