README.md

---
language:
- ko
license: creativeml-openrail-m
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- korean
inference: true
duplicated_from: andite/anything-v4.0
---

Fantasy.ai is the official and exclusive hosted AI generation platform that holds a commercial use license for Anything V4.0, you can use their service at https://Fantasy.ai/

# Note
- Github: [KOrean-stable-diffusion-anything](https://github.com/KyujinHan/KO-stable-diffusion-anything)
- I use [bingsu's CLIP](https://huggingface.co/Bingsu/clip-vit-large-patch14-ko)

## Examples
![](image1.png)
**Prompt: 걸작, 최고 품질, 1소녀, 흰 머리, 고양이 귀, 눈을 감고, 보는 사람, 귀여운, 스카프, 재킷, 옥외, 거리**

![](image2.png)
**Prompt: 풍경, 집, 야외, 하늘, 구름**

![](image3.png)
**Prompt: 1소년, 잘생긴, 실내, 앉아있는, 커피 숍, 커피 한 잔**

![](image4.png)
**Prompt: 1소년, 강아지 귀, 귀여운, 흰색 스카프, 눈, 관찰자**


# KO-Anything-V4.5

Welcome to Anything V4 - a latent diffusion model for weebs. The newest version of Anything. This model is intended to produce high-quality, highly detailed anime style with just a few prompts. Like other anime-style Stable Diffusion models, it also supports danbooru tags to generate images.

e.g. **_1girl, white hair, golden eyes, beautiful eyes, detail, flower meadow, cumulonimbus clouds, lighting, detailed sky, garden_** 

**Korean ver.** 
e.g. **_걸작, 최고 품질, 1소녀, 흰 머리, 고양이 귀, 눈을 감고, 보는 사람, 귀여운, 스카프, 재킷, 옥외, 거리_**


## 🧨 Diffusers

This model can be used just like any other Stable Diffusion model. For more information,
please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).

You can also export the model to [ONNX](https://huggingface.co/docs/diffusers/optimization/onnx), [MPS](https://huggingface.co/docs/diffusers/optimization/mps) and/or [FLAX/JAX]().

```python
from diffusers import StableDiffusionPipeline
import torch

model_id = "kyujinpy/KO-anything-v4.5"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "1소년, 강아지 귀, 귀여운, 흰색 스카프, 눈, 관찰자"
image = pipe(prompt).images[0]

image.save("./hatsune_miku.png")
```

## License

This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
The CreativeML OpenRAIL License specifies: 
[Please read the full license here](https://huggingface.co/spaces/CompVis/stable-diffusion-license)