pai-diffusion-artist-large-zh-lora-25d

alibaba-pai/pai-diffusion-artist-large-zh-lora-25d

pai-diffusion-artist-large-zh-lora-25d is a text-to-image model from alibaba-pai. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.

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。

Downloads · 30 days

3% of all-time downloads

All-time downloads

539

Public

Repo size

102 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin102 MB · 96%

At a glance

Task: Text-to-Image
Library: diffusers
License: apache-2.0
Access: Public
Created: Jul 19, 2023
Updated: Jul 19, 2023
SHA: 80bf8089

Model card

From the Hugging Face model README

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.

Github: EasyNLP

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")