robb-0/Kawaii_chibi_avatar_IllustriousXL

Kawaii Chibi Avatar - Illustrious Version

Prompt

a kawaii chibi avatar of a cat, detailed, inside plastic circle, flat 3d, on a starry sky background , colorful, highres, absurdres, best quality, amazing quality, masterpiece

Negative Prompt

(lowres:1.3), low quality, worst quality, blurry, multiple views, abstract, text, watermark, signature, website,

Prompt

a kawaii chibi avatar of 1boy in mage shirt pants holding staff, detailed, inside plastic circle, flat 3d, on flat metallic reflective background , colorful, highres, absurdres, best quality, amazing quality, masterpiece

Prompt

a kawaii chibi avatar of a princess, detailed, inside plastic bubble circle, flat 3d, on a starry sky background , colorful, highres, absurdres, best quality, amazing quality, masterpiece

Prompt

a kawaii chibi avatar of a puppy, detailed, inside plastic circle, flat 3d, on a starry sky background , colorful, highres, absurdres, best quality, amazing quality, masterpiece

Negative Prompt

(lowres:1.3), low quality, worst quality, blurry, , abstract, text, watermark, signature, website,

Prompt

a kawaii chibi avatar cute human princess in dress, long hair, detailed, inside plastic circle, flat 3d, on a starry sky background , colorful, highres, absurdres, best quality, amazing quality, masterpiece

Prompt

(masterpiece, highres, highquality), a chibi avatar shark swiming inside a mini ocean, plastic circle, black background, 3d

Model description

Kawaii Chibi Avatar 🐻✨

Illustrious version of

Kawaii Chibi Avatar for SDXL:

https://huggingface.co/robb-0/kawaii-chibi-avatar

For extra information, please read the card link above.

As Illustrious works differently, and the dataset did not have many humanoids, this version works best with animals and robots. YET, you can generate humans if you add "human" in the prompt as seen in the sample.

---

Tips for usage

• As per usual, it's not recommended running it on Illustrious 0.1 (neither 1.0 to 2.0,) because the 0.1 will render poor images and the others have a tendency of creating unspeakable horrors, at least here on my end.
• I always prefer running my image LoRAs on any NoobAI EPSILON. Then, if possible use those as base model.
• If you set (lowres:1.x) in the negatives, you can lower the number of steps and maybe lower the weight of this LoRA to 0.8. But it seems to work best at 0.9 ~ 1.0.
• Illustrious does not work as SDXL, then the "trigger words" can be added in any part of the prompt to possibly make the LoRA work the way it was trained for.
• Without "trigger words", it still can perform other effects, such as adding that nice plastic/glass bubble, which in case it is much stronger on Illustrious than on SDXL.
• You can use in the prompt "a mini [enter landscape here]" before "plastic circle", and it is possible that the mini "background" will be rendered only inside the "bubble", as you can check in the samples above.

---

License: CC BY 4.0

Attribution:

Kawaii Chibi Avatar © 2025 by Robb-0 is licensed under CC BY 4.0

---

Disclaimer:

This model is provided “as is” without any warranty. The creator is not responsible for any misuse or unintended consequences of using this model.

---

Trigger words

You should use kawaii chibi avatar to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.