models/Hassaku XL (Illustrious) - v1.3 - Style A

Hassaku XL (Illustrious) - v1.3 - Style A

|
7/3/2025
|
5:58:34 AM
| Discussion

Recommended Prompts

masterpiece

1girl, masterpiece

Recommended Negative Prompts

worst quality,bad quality,signature

worst quality, bad quality

Recommended Parameters

samplers

Euler a

steps

20

cfg

7

resolution

1024x1024, 1152x896, 896x1152, 1216x832, 832x1216, 1344x768, 768x1344, 1536x640, 640x1536, 832x1224, 832x1216, 864x1184, 928x1168, 960x1152, 832x1248, 848x1216

vae

sdxl_vaeFix.safetensors

Recommended Hires (High-Resolution) Parameters

upscaler

R-ESRGAN 4x+ Anime6B, Latent (nearest-exact)

upscale

1.45 - 1.6

denoising strength

0.55 - 0.59

Tips

Use negative prompt 'signature' to avoid disruptive features like floating texts, logos, and speak bubbles.

Avoid metadata and franchise tags such as 'highres' or character franchise names like 'rem_(re:zero)'.

Join the Discord for anime models and art discussions.

Support the creator on Patreon.

Version Highlights

Whats better:
- Images are overall a bit more brighter

Worse/better for some:
- It is more forced to look more "anime" and less realistic -> mostly less images with visible nostrils/noses without tags like realistic or detailed, especially in use of tags censored/uncensored

Worse:
- Artifacts can appear more
- Because of the second point (looks more "anime"), images getting less of a "cinematic" look with lighting

It is recommended, if you want to use loras, to use it on the style A variant model. Forced Style is light enough, that most artist tags still works and loras can do their thing, including pony loras.

Creator Sponsors

You can run Hassaku XL and use its API on SinkIn: https://sinkin.ai/m/JWknjgr

Check out other models by the same author: hassaku, sudachi(flat 2d), koji(2d), yuzu(light semirealistic), grapefruit

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

V1 use illustrious-xl as base, versions from 0.2M up are trainined with quality prompts like masterpiece or worst quality. Recommended prompts in negative are "worst quality, bad quality" and masterpiece in positiv. There is also my pony xl variant.

My Discord for everything related to anime models and art. You can support me on my patreon.

My models: hassaku, sudachi(flat 2d), koji(2d), yuzu(light semirealistic), grapefruit

_____________________________________________________

Supporters:

Thanks to my supporters Riyu, SETI and Kodokuna on my patreon!

_____________________________________________________

Using the model:

  • Model is trained with images with minimal disruptive features like floating texts, logos, speak bubbles and signatures as possible. If such features appearing in a image, please use prompt "signature" as negative.

  • Excluded metadata and franchise tags, don't use them. meta data -> something like "highres", franchise tags like "re:zero kara hajimeru isekai seikatsu" are pruned on characters like "rem_(re:zero)".

  • Here are some good resolution options for SDXL:

    • 1024 x 1024

    • 1152 x 896

    • 896 x 1152

    • 1216 x 832

    • 832 x 1216 (most recommended)

    • 1344 x 768

    • 768 x 1344

    • 1536 x 640

    • 640 x 1536

License info:

Because it merges ANIMAGINE XL 3.0 below version V1 and Illustrious-XL & WAI-NSFW-illustrious-SDXL beginning from V1:
Fair AI Public License 1.0-SD

V2 is trained on its own and don't include any merge, just Illustrious-XL 0.1, but trained to include newer or missing characters, which also use the Fair AI Public License 1.0-SD license.

Previous
ma1ma1helmes | Shiiro's Styles | Niji - Style_A
Next
Chroma - v.35-detail-calibrated

Model Details

Model type

Checkpoint

Base model

Illustrious

Model version

v1.3 - Style A

Model hash

79408e8b5a

Creator

Discussion

Please log in to leave a comment.