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
The pure trained model output. Completly unaltered, as Nature intended.
This model does not have any style merge stabilisation and is intended as base for further training, merges, using Loras, etc. for anyone, that are interested in that.
Be aware that it can have every kind of problem, a base model can have.
But it have a little specialty to it, the style got natively trained into the model, instead of merging it into the model per loras. It enhance the default output of the pure model.
If you compare it with 3.1, you will notice some similar looking images, because of the low style merge of 3.1 itself. In some cases, this pure model may produce better looking images, but it can also create significantly worse images. Results will vary greatly.
It have one trained epoch more (400k images -> not a big differece) in, in compare to 3.1.
With slitly changed training:
Trained now on LION, with Stochastic Rounding, SMMF, C-Optim and higher Alpha1. Before with adafactor Stochastic Rounding and Fused Back Pass.
FAQ
Comments (18)
Definitely worth it
Images made by this model always look blurry. Don't know if this is an intentional choice.
amazing! thank you
Any difference between 3.1 and 3? since 3.1 was released before base 3.
base is the pure trained output weights without any extra altering on it. Look at "About this version" on the right
What is the v3_Base model and how is it better and different from v3.1?
base is the pure trained output weights without any extra altering on it. Look at "About this version" on the right
It's weird, but the pictures I get are of really terrible quality. Everything is blurry, uneven, like a child's scribbles.
this happens to me once in awhile too, like the picture is colored by pencil, but i just gen'd four in a row that looked like this. might be close ups prompt. still love this model though, it usually produces fantastic results. edit: scrolled the comments, I think the creator is aware
Good
This model is awesome — it almost always generates what I want
nice
I'm mostly a big fan of this model, for SFW anime shots it is the absolute best by far. But I noticed something weird while generating lewd arts - did you use lots of Futas to train 31 or something? Over 20 images I generated 8 futanari, despite having ((trans)), ((futa)), ((futanari)) in my negative prompt! I put the same prompt in 30 and over 20 images generated no futanari!
dont put weight on your negatives, sometimes it will cause it to bleed into positives.
I used to be a hassaku regular, but I moved to WAI, after the multiple views capability of the model was butchered esp with loras. It was a good run.
It is a real shame, I started with v11 when I transitioned from SD1.5, V3+ is impossible to use with CFG 2, and text looks all mangled at 7. I would love a v11 with just character loras if that is even possible.
I feel like 3.0 is still better with cleaner and clearer lines...
I like how the colors in this model look less saturated and the rougher linework stands out more. However, it seems that the reproduction quality for some artists—especially those with a flat color style—has dropped significantly.
Am I perhaps using this model incorrectly?