AGGA's Utopia —「illustrious-SDXL」

CHECKPOINT
Original


Updated:

💫 Wanna Try Before You Download?

💻 Try it Online

Just click and generate directly from the browser!


Hi! Here's a quick introduction to the model:

This is a personal model I created some time ago for SDXL, originally based on Animagine and recently refined with the help of Illustrious v0.1, Illustrious WAI NSFW v13, and NTR MIX v13.

It's inspired by some of my testers (like CuteMaster CKPT, various LoRAs, and several style fusions), so you could recreate this style by properly combining several already trained LoRAs with the Illustrious models.

(Although... I already did that for you 😉)

It was originally intended for personal use, since I used it to generate new styles. But as it was built using a variety of community resources and turned out better than expected, I decided to polish it and share it.

In short: I tried a lot of things until I finally captured the style I was looking for. And this is it.

Hope you enjoy it!


📦 UtopiaXL V1.0

My baking method is a bit more involved than just picking models and merging them with Supermerge (although I do use Supermerge too).

I usually convert models into folder format and manually replace the UNet, while sorting or merging the text encoders—assisted by scripts, of course; I’m not a masochist.

Naturally, the easiest way to control the base style is by creating an external LoRA, baking it in heavily, and using it as a control layer… though I went a little overboard with this version and ended up overpowering some other elements. I’ll be fixing that in the next few days.

  • Steps: 15–30

  • CFG Scale: 2.5–7 (4.5 or 5.5 recomended).

  • Sampler: Euler a, DPM++ 2M, etc.

  • Resolution: Larger than 1024x1024 to take advantage of its original resolution.

  • Recommended Upscaling:

    Scale: 1.5

    • Steps: 20

    • Upscaler: R-ESRGAN 4x+ Anime6B

    • Denoising strength: 0.35 – 0.5

📌 Note: The VAE is already integrated; no need to load an external one.


🛡️ Safety Labels

This model may generate content of various types. Users are expected to correctly categorize its use into the following categories:

General / Sensitive / NSFW / Explicit

Please consciously add "NSFW" to negative labels if you wish to avoid explicit content.


🏷️ Prompt Tips

Positive Prompt:

anime, cartoon, shiny skin, shiny, masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, extremely detailed eyes, detailed face, absurdres, newest, best illumination, depth of field, complex background, detailed background

Others More: slutty, sexy, slut:2.1, dynamic angle, dynamic pose

Negative Prompt:

bad quality,worst quality,worst detail,sketch,censor, big nose, 
bad anatomy, ugly, worst aesthetic, old, mismatched pupils, dirty face, extra limbs, bad hands, bad fingers

The model already exists. If you are the creator, please contact us to claim it.
View duplicate model

Version Detail

Illustrious
<p>You really don't need that many triggers, the typical ones (masterpiece,best quality,highly detailed) are enough, but is this what I used to generate the base style? Honestly, I don't know how to activate the generation in the site, but I like how it works with my loras.</p>

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Related Posts