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
Only a performance update, no new characters or such.
Improvements:
- Better-formed eyes
- Better hands
- Fewer artifacts overall
Worse:
- Backgrounds can look more blurry, noisy or messy, describing the background a bit more can change that
- It makes sometimes strange dark orange like images
Recommended negatives are "worst quality, bad quality, sketch". With negative "sketch" giving more clean line art (most of the time). Sometimes not using worst quality, bad quality, gives better results, strangely enough.
Style A tends to produce better eyes with a more stable style overall, while Style 2.1 offers more detailed images with a less 2D appearance. If you prefer images with added detail and depth, Style 2.1 might be the better choice for you. Even if you need to kick the model in the balls sometimes.
Note: Some concepts have a strong drawn appearence and others more of a 2.5 feel (especially with character prompts, giving more drawn results). The price of more versatility in general. Don't overload it with quality prompts or a wall of text prompts, its versatility is also its weakness. Overloading it with too much information can cause the model to produce unhinged results, because it don't have a strong "style saveguard".
In maybe 2-3 weeks i have a dataset updated model, but it only offers new genshin characters so far.