Chinese Diffusion Model (Anime, 512 Resolution)

简介 Brief Introduction

我们开源了一个中文 Diffusion 模型,您可以直接输入中文提示词,我们为您呈现精美的动漫风格图片。本模型的默认分辨率是 768*512(竖图)。

We release a Chinese diffusion model, which is able to generate high-quality anime images according to the prompts you input. The default resolution of this model is 768*512.

使用 Usage

本模型支持 diffusers,可以参考以下范例代码:

This model supports diffusers. Please refer to the following code:

from diffusers import StableDiffusionPipeline

model_id = "alibaba-pai/pai-diffusion-anime-large-zh"
pipe = StableDiffusionPipeline.from_pretrained(model_id)
pipe = pipe.to("cuda")

prompt = "1个女孩,玫瑰,猫,蕾丝,音符,轻粒子"
image = pipe(prompt, height=768, width=512).images[0]  
image.save("result.png")

作品展示 Gallery

prompt: 1个女孩,单人,高分辨率,腮红,看着观众,微笑,张开嘴,刘海 prompt: 1个女孩,高分辨率,金发,坐着,紫色的眼睛,蝴蝶结
prompt: 1个女孩,蓝眼睛,白色裙子,大腿,银色头发,百褶裙,天空 prompt: 1个女孩,玫瑰,猫,蕾丝,音符,轻粒子

使用须知 Notice for Use

使用上述模型需遵守AIGC模型开源特别条款

If you want to use this model, please read this document carefully and abide by the terms.

Downloads last month
9
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.