| 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/rev-animated" | |
| torch.classes.load_library(lib_path) | |
| # 构建 Img2Img 的 Pipeline | |
| model = LyraSDImg2ImgPipeline() | |
| model.reload_pipe(model_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") | |