import torch

torch.backends.cudnn.benchmark = True

import torch

torch.backends.cuda.matmul.allow_tf32 = True

pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    
    torch_dtype=torch.float16,
)
pipe = pipe.to("cuda")

prompt = "a photo of an astronaut riding a horse on mars"
image = pipe(prompt).images[0]

import torch
from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    
    torch_dtype=torch.float16,
)
pipe = pipe.to("cuda")

prompt = "a photo of an astronaut riding a horse on mars"
pipe.enable_attention_slicing()
image = pipe(prompt).images[0]

import torch
from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    
    torch_dtype=torch.float16,
)
pipe = pipe.to("cuda")

prompt = "a photo of an astronaut riding a horse on mars"
pipe.enable_vae_slicing()
images = pipe([prompt] * 32).images

import torch
from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    
    torch_dtype=torch.float16,
)

prompt = "a photo of an astronaut riding a horse on mars"
pipe.enable_sequential_cpu_offload()
image = pipe(prompt).images[0]

import torch
from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    
    torch_dtype=torch.float16,
)

prompt = "a photo of an astronaut riding a horse on mars"
pipe.enable_sequential_cpu_offload()
pipe.enable_attention_slicing(1)

image = pipe(prompt).images[0]

import torch
from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",  
    torch_dtype=torch.float16,
)

prompt = "a photo of an astronaut riding a horse on mars"
pipe.enable_model_cpu_offload()
image = pipe(prompt).images[0]

import torch
from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    torch_dtype=torch.float16,
)

prompt = "a photo of an astronaut riding a horse on mars"
pipe.enable_model_cpu_offload()
pipe.enable_attention_slicing(1)

image = pipe(prompt).images[0]

print(pipe.unet.conv_out.state_dict()["weight"].stride())  # (2880, 9, 3, 1)
pipe.unet.to(memory_format=torch.channels_last)  # in-place 연산
# 2번째 차원에서 스트라이드 1을 가지는 (2880, 1, 960, 320)로, 연산이 작동함을 증명합니다.
print(pipe.unet.conv_out.state_dict()["weight"].stride())

import time
import torch
from diffusers import StableDiffusionPipeline
import functools

# torch 기울기 비활성화
torch.set_grad_enabled(False)

# 변수 설정
n_experiments = 2
unet_runs_per_experiment = 50


# 입력 불러오기
def generate_inputs():
    sample = torch.randn(2, 4, 64, 64).half().cuda()
    timestep = torch.rand(1).half().cuda() * 999
    encoder_hidden_states = torch.randn(2, 77, 768).half().cuda()
    return sample, timestep, encoder_hidden_states


pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    torch_dtype=torch.float16,
).to("cuda")
unet = pipe.unet
unet.eval()
unet.to(memory_format=torch.channels_last)  # Channels Last 메모리 형식 사용
unet.forward = functools.partial(unet.forward, return_dict=False)  # return_dict=False을 기본값으로 설정

# 워밍업
for _ in range(3):
    with torch.inference_mode():
        inputs = generate_inputs()
        orig_output = unet(*inputs)

# 추적
print("tracing..")
unet_traced = torch.jit.trace(unet, inputs)
unet_traced.eval()
print("done tracing")


# 워밍업 및 그래프 최적화
for _ in range(5):
    with torch.inference_mode():
        inputs = generate_inputs()
        orig_output = unet_traced(*inputs)


# 벤치마킹
with torch.inference_mode():
    for _ in range(n_experiments):
        torch.cuda.synchronize()
        start_time = time.time()
        for _ in range(unet_runs_per_experiment):
            orig_output = unet_traced(*inputs)
        torch.cuda.synchronize()
        print(f"unet traced inference took {time.time() - start_time:.2f} seconds")
    for _ in range(n_experiments):
        torch.cuda.synchronize()
        start_time = time.time()
        for _ in range(unet_runs_per_experiment):
            orig_output = unet(*inputs)
        torch.cuda.synchronize()
        print(f"unet inference took {time.time() - start_time:.2f} seconds")

# 모델 저장
unet_traced.save("unet_traced.pt")

from diffusers import StableDiffusionPipeline
import torch
from dataclasses import dataclass


@dataclass
class UNet2DConditionOutput:
    sample: torch.FloatTensor


pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    torch_dtype=torch.float16,
).to("cuda")

# jitted unet 사용
unet_traced = torch.jit.load("unet_traced.pt")


# pipe.unet 삭제
class TracedUNet(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.in_channels = pipe.unet.in_channels
        self.device = pipe.unet.device

    def forward(self, latent_model_input, t, encoder_hidden_states):
        sample = unet_traced(latent_model_input, t, encoder_hidden_states)[0]
        return UNet2DConditionOutput(sample=sample)


pipe.unet = TracedUNet()

with torch.inference_mode():
    image = pipe([prompt] * 1, num_inference_steps=50).images[0]

from diffusers import StableDiffusionPipeline
import torch

pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    torch_dtype=torch.float16,
).to("cuda")

pipe.enable_xformers_memory_efficient_attention()

with torch.inference_mode():
    sample = pipe("a small cat")

# 선택: 이를 비활성화 하기 위해 다음을 사용할 수 있습니다.
# pipe.disable_xformers_memory_efficient_attention()