app.py

import gradio as gr
from PIL import Image
import numpy as np
from io import BytesIO
from diffusers import StableDiffusionImg2ImgPipeline, StableDiffusionPipeline, UNet2DConditionModel, AutoencoderKL
from transformers import BertTokenizer, BertModel


device="cuda"
model_id = "IDEA-CCNL/Taiyi-Stable-Diffusion-1B-Chinese-v0.1"

# pipe_img2img = StableDiffusionImg2ImgPipeline.from_pretrained(model_id, tokenizer=tokenizer, text_encoder=text_encoder, vae=vae, unet=unet).to(device)
pipe_text2img = StableDiffusionPipeline.from_pretrained(model_id).to(device)

def resize(w_val,l_val,img):
  img = Image.open(img)
  img = img.resize((w_val,l_val), Image.Resampling.LANCZOS)
  return img


def infer(prompt, guide, steps, width, height): 
    image_list = pipe_text2img([prompt], guidance_scale=guide, num_inference_steps=steps, width=width, height=height)
    images = []
    for i, image in enumerate(image_list["sample"]):
        images.append(image)    
    return image

gr.Interface(fn=infer, inputs=
    [
        # gr.Image(source="upload", type="filepath", label="原始图像"), 
        gr.Textbox(label = '提示词(prompt)'),
        gr.Slider(2, 15, value = 7, label = '文本引导强度'),
        gr.Slider(10, 30, value = 20, step = 1, label = '迭代次数'),
        gr.Slider(256, 768, value = 512, step = 64, label = '宽度'),
        gr.Slider(256, 768, value = 512, step = 64, label = '高度'),
    ],outputs='image').queue(max_size=10).launch(enable_queue=True)