models/Amanatsu (Illustrious) - V1.1

Amanatsu (Illustrious) - V1.1

8/5/2025

5:36:12 AM

Related Keywords & Tags

amanatsu,amanatsu (illustrious),anime,anime model,base model,characters,checkpoint,detailed anime look,ikena,illustrious,nsfw,v1.1,woman

A cute girl with brown eyes and double bun hairstyle in detailed blue and white hanfu sitting asleep, leaning against a tree in a grassy landscape with mountains in the background.

A tall winged figure in a blue dress adorned with swirling colorful abstract patterns stands against a dark background with artistic splashes and tiny curious characters at her feet.

Adult male with slicked back hair wearing sunglasses and a pink floral Hawaiian shirt sitting indoors at a cafe table, holding a glass of orange juice and smirking.

Anime character Rem with blue hair and eyes, wearing a Roswaal mansion maid uniform, posing dynamically and looking upward.

Anime-style girl with large expressive eyes eating spaghetti with a fork in a warmly lit living room, showing a cute and surprised expression.

A mechanical maid with short white hair and a frilly black and white maid outfit runs energetically while mopping the floor, accompanied by a small floating mecha, set against a white background with motion lines and cleaning bubbles.

Recommended Prompts

1girl, masterpiece

Recommended Negative Prompts

signature

worst quality, bad quality

Recommended Parameters

samplers

Euler a

steps

cfg

resolution

1024x1024, 1152x896, 896x1152, 1216x832, 832x1216, 1344x768, 768x1344, 1536x640, 640x1536, 832x1264, 824x1224, 800x1248, 896x1152, 960x1152, 816x1232, 880x1232

vae

sdxl_vaeFix.safetensors

Recommended Hires (High-Resolution) Parameters

upscaler

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

upscale

1.45 - 1.6

denoising strength

0.42 - 0.54

Tips

Use negative prompt 'signature' to exclude images with signatures or other disruptive features.

Avoid using metadata tags like 'highres' or franchise tags such as 're:zero kara hajimeru isekai seikatsu' when prompting.

The resolution 832 x 1216 is the most recommended for SDXL models.

Version Highlights

Update to Style B that is now amanatsu

Improvements:

- A bit more stable with backgrounds, less random strange extra stuff appears
- Less blurry
- Better eyes (if they don't artifact or used with hires or adetailer)
- Slightly less artifacs (still many, hires or adetailer are recommended)
- Brighter in most occasions, without loosing the ability for darker images

Its based on hassaku 2.1, but have back mergin with style V1. So its a bit of a combo of V1 and hassakuV2.1. The versatility of 2.1 + the style of B in one model.

Creator Sponsors

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

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

Amanatsu aims to be a model with a distinctive detailed anime look.

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

_____________________________________________________

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