LoRA of Chinese Diffusion Model (2.5D)

简介 Brief Introduction

我们开源了适配中文 Diffusion 模型 alibaba-pai/pai-diffusion-artist-large-zh 的 LoRA,这个 LoRA 可以将模型生成的图像转换成 2.5D 风格。

We release a LoRA for our Chinese diffusion model alibaba-pai/pai-diffusion-artist-large-zh. This LoRA can synthesize images in 2.5D style.

使用 Usage

from diffusers import StableDiffusionPipeline

model_id = "alibaba-pai/pai-diffusion-artist-large-zh"
pipe = StableDiffusionPipeline.from_pretrained(model_id)
pipe.unet.load_attn_procs("alibaba-pai/pai-diffusion-artist-large-zh-lora-25D")
pipe = pipe.to("cuda")

prompt = "蓝天,白云,大草原"
image = pipe(prompt, cross_attention_kwargs={"scale": 0.4}).images[0]
image.save("result.png")

作品展示 Gallery

样例1 Example1

日系风景风格 -> 2.5D 风格

Japanese landscape style -> 2.5D style

prompt: 蓝天,白云,大草原

scale: 0.0 scale: 0.4

样例2 Example2

写实人像风格 -> 2.5D 风格

Realistic portrait style -> 2.5D style

prompt: 抱着猫的少女

scale: 0.0 scale: 0.4

样例3 Example3

写实动物风格 -> 2.5D 风格

Realistic animal style -> 2.5D style

prompt: 柴犬,狗

scale: 0.0 scale: 0.4

样例4 Example4

漫画风格 -> 2.5D 风格

Comic style -> 2.5D style

prompt: 赛博朋克,霓虹灯,兜帽,黑衣人

scale: 0.0 scale: 0.4

样例5 Example5

中国画风格 -> 2.5D 风格

Chinese painting style -> 2.5D style

prompt: 山川,河海,大雁

scale: 0.0 scale: 0.4

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
10
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.