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

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

|
6/30/2025
|
1:25:35 PM
| Discussion

Zalecane podpowiedzi

masterpiece

1girl, masterpiece

Zalecane negatywne podpowiedzi

worst quality,bad quality,signature

worst quality, bad quality

Zalecane parametry

samplers

Euler a

steps

20

cfg

7

resolution

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

vae

sdxl_vaeFix.safetensors

Zalecane parametry wysokiej rozdzielczości

upscaler

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

upscale

1.45 - 1.6

denoising strength

0.55 - 0.59

Wskazówki

Use the negative prompt "signature" to avoid images with signatures or disruptive features.

Avoid using metadata tags like "highres" and franchise tags such as "re:zero kara hajimeru isekai seikatsu" to improve results.

Among recommended resolutions, 832 x 1216 is considered the most recommended.

Najważniejsze informacje o wersji

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.

Sponsorzy twórcy

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

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.

Poprzedni
Dark Cinematic Style (Low-Key Lighting) - v1.0
Następny
MoriiMee Gothic Niji | LoRA Style - V1 Ilustrious

Szczegóły modelu

Typ modelu

Checkpoint

Model bazowy

Illustrious

Wersja modelu

v1.3 - Style A

Hash modelu

79408e8b5a

Twórca

Dyskusja

Proszę się log in, aby dodać komentarz.