import torch
import time

from lyrasd_model import LyraSdTxt2ImgPipeline

# 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，放入其中的 unet_bins 文件夹
#   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"
lora_path = "./models/lyrasd_xiaorenshu_lora"

# 构建 Txt2Img 的 Pipeline
model = LyraSdTxt2ImgPipeline(model_path, lib_path)

# load lora
# 参数分别为 lora 存放位置，名字，lora 强度，lora模型精度
model.load_lora(lora_path, "xiaorenshu", 0.4, "fp32")

# 准备应用的输入和超参数
prompt = "a cat, cute, cartoon, concise, traditional, chinese painting, Tang and Song Dynasties, masterpiece, 4k, 8k, UHD, best quality"
negative_prompt = "(((horrible))), (((scary))), (((naked))), (((large breasts))), high saturation, colorful, human:2, body:2, low quality, bad quality, lowres, out of frame, duplicate, watermark, signature, text, frames, cut, cropped, malformed limbs, extra limbs, (((missing arms))), (((missing legs)))"
height, width = 512, 512
steps = 30
guidance_scale = 7
generator = torch.Generator().manual_seed(123)
num_images = 1

start = time.perf_counter()
# 推理生成
images = model(prompt, height, width, steps,
        guidance_scale, negative_prompt, num_images,
        generator=generator)
print("image gen cost: ",time.perf_counter() - start)
# 存储生成的图片
for i, image in enumerate(images):
    image.save(f"outputs/res_txt2img_lora_{i}.png")

# unload lora，参数为 lora 的名字，是否清除 lora 缓存
# model.unload_lora("xiaorenshu", True)