controlnet_img2img_demo.py

from io import BytesIO

import requests
import torch
from PIL import Image

from lyrasd_model import LyraSdControlnetImg2ImgPipeline

# 存放模型文件的路径，应该包含一下结构：
#   1. clip 模型
#   2. 转换好的优化后的 unet 模型
#   3. vae 模型
#   4. scheduler 配置

# LyraSD 的 C++ 编译动态链接库，其中包含 C++ CUDA 计算的细节
lib_path = "./lyrasd_model/lyrasd_lib/libth_lyrasd_cu12_sm86.so"
model_path = "./models/rev-animated"
canny_controlnet_path = "./models/canny"
torch.classes.load_library(lib_path)

# 构建 Img2Img 的 Pipeline
model = LyraSdControlnetImg2ImgPipeline()
model.reload_pipe(model_path)

# load Controlnet 模型，最多load 3个
model.load_controlnet_model_v2("canny", canny_controlnet_path)

control_img = Image.open("control_bird_canny.png")

# 准备应用的输入和超参数
prompt = "a bird"
negative_prompt = "NSFW"
height, width = 512, 512
steps = 20
guidance_scale = 7.5
generator = torch.Generator().manual_seed(123)
num_images = 1

# 可以一次性load 3 个 Controlnets，达到multi Controlnet的效果，这里的参数的长度需要对其
# Controlnet 所输入的img list 长度应该和 controlnet scale 与 Controlnet name 一致，而内部的list长度需要和batch size一致
# 对应的index 可以对其
controlnet_images = [[control_img]] 
controlnet_scale= [0.5]
controlnet_names= ['canny'] 

# 从 cos 上拿个图作为初始化图片
init_image_url = "https://chuangxin-research-1258344705.cos.ap-guangzhou.myqcloud.com/share/files/seaside_town.png?q-sign-algorithm=sha1&q-ak=AKIDBF6i7GCtKWS8ZkgOtACzX3MQDl37xYty&q-sign-time=1692601590;1865401590&q-key-time=1692601590;1865401590&q-header-list=&q-url-param-list=&q-signature=ca04ca92d990d94813029c0d9ef29537e5f4637c"
init_image = BytesIO(requests.get(init_image_url).content)
init_image = Image.open(init_image).convert('RGB')
init_image = init_image.resize((width, height), Image.Resampling.LANCZOS)
guess_mode = False
strength = 0.8

# 推理生成
images = model(prompt, init_image, strength, height, width, steps,
               guidance_scale, negative_prompt, num_images,
               generator=generator, controlnet_images=controlnet_images,
               controlnet_scale=controlnet_scale, controlnet_names=controlnet_names,
               guess_mode=guess_mode
               )

# 存储生成的图片
for i, image in enumerate(images):
    image.save(f"outputs/res_controlnet_img2img_{i}.png")