README.md

---
license: openrail++
language:
- en
library_name: diffusers
pipeline_tag: text-to-image
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: ch1b1n1me
tags:
- lora
- stable-diffusion-xl
- text-to-image
- diffusers
- style
- anime
- chibi
- cute
- super-deformed
- kawaii
- vibrant
- simple
- sdxl lora
- style-lora
- portrait
- illustration
- pop art
- flat design
- colorful
widget:
  - text: "ch1b1n1me, a tiny pirate with a treasure map"
  - text: "ch1b1n1me, a chibi cat-girl waving hello"
  - text: "ch1b1n1me, a tiny knight on a horse"
---

# Chibi Super-Deformed Anime SDXL LoRA

## What it does
Transform your text-to-image generation into adorable chibi super-deformed anime style with oversized round heads, tiny bodies, huge expressive eyes, simplified features, bold outlines, vivid flat colors, and cute exaggerated emotions.
## How to use
Add the trigger word 'ch1b1n1me' to your prompt for instant chibi transformation. For best results, set strength between 0.75-0.9 and use a sampler that works well with LoRA models like Euler or Heun with around 20 steps.
## Best for
- Tiny pirates with treasure maps
- Chibi cat-girls waving hello
- Miniature knights riding horses
- Small sorcerers casting spells
- Petite ninjas sneaking through grass
## Tips
- Increase the strength parameter to emphasize chibi features over base model styles. Decrease it if you want a subtler transformation.
- Experiment with different samplers and step counts for unique results.
## Example Prompts

```
ch1b1n1me cute chibi anime girl sitting on a park bench with cherry blossoms in full bloom behind her
```

```
ch1b1n1me cozy room interior with chibi characters relaxing, soft lighting and pastel colors
```

```
ch1b1n1me super-deformed robot holding a giant ice cream cone, vibrant sunset background
```

```
ch1b1n1me chibi ninja jumping through trees in motion blur, dramatic forest scene at dusk
```

```
ch1b1n1me happy-go-lucky chibi alien floating in space with stars and planets all around
```

```
ch1b1n1me abstract pattern of colorful chibi faces, bold outlines and flat colors
```

## Trigger word

Activate with `ch1b1n1me`. Recommended strength: **0.9**.

## Showcase

![showcase 1](./showcase/showcase_01.png)
![showcase 2](./showcase/showcase_02.png)
![showcase 3](./showcase/showcase_03.png)
![showcase 4](./showcase/showcase_04.png)
![showcase 5](./showcase/showcase_05.png)
![showcase 6](./showcase/showcase_06.png)
![showcase 7](./showcase/showcase_07.png)
![showcase 8](./showcase/showcase_08.png)

## Usage with `diffusers`

```python
from diffusers import AutoPipelineForText2Image
import torch

pipe = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16).to("cuda")
pipe.load_lora_weights("strkyyy/anime-chibi")
image = pipe("ch1b1n1me, your prompt", num_inference_steps=30).images[0]
```