img2img_demo.py

from io import BytesIO

import requests
import torch
from PIL import Image

from lyrasd_model import LyraSDImg2ImgPipeline

# 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/lyrasd_rev_animated"

# 构建 Img2Img 的 Pipeline
model = LyraSDImg2ImgPipeline(model_path, lib_path)

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

# 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)

strength = 0.8

# 推理生成
images = model(prompt, init_image, strength, steps,
               guidance_scale, negative_prompt, num_images,
               generator=generator
               )

# 存储生成的图片
for i, image in enumerate(images):
    image.save(f"./outputs/res_img2img_{i}.png")