benchmark/if.py

#!/usr/bin/env python3
from diffusers import DiffusionPipeline
import torch

run_compile = True  # Set True / False

pipe = DiffusionPipeline.from_pretrained("DeepFloyd/IF-I-M-v1.0", variant="fp16", text_encoder=None, torch_dtype=torch.float16)
pipe.to("cuda")
pipe_2 = DiffusionPipeline.from_pretrained("DeepFloyd/IF-II-M-v1.0", variant="fp16", text_encoder=None, torch_dtype=torch.float16)
pipe_2.to("cuda")
pipe_3 = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-x4-upscaler", torch_dtype=torch.float16)
pipe_3.to("cuda")


pipe.unet.to(memory_format=torch.channels_last)
pipe_2.unet.to(memory_format=torch.channels_last)
pipe_3.unet.to(memory_format=torch.channels_last)

if run_compile:
    pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
    pipe_2.unet = torch.compile(pipe_2.unet, mode="reduce-overhead", fullgraph=True)
    pipe_3.unet = torch.compile(pipe_3.unet, mode="reduce-overhead", fullgraph=True)

prompt = "the blue hulk"

prompt_embeds = torch.randn((1, 2, 4096), dtype=torch.float16)
neg_prompt_embeds = torch.randn((1, 2, 4096), dtype=torch.float16)

for _ in range(3):
    image = pipe(prompt_embeds=prompt_embeds, negative_prompt_embeds=neg_prompt_embeds, output_type="pt").images
    image_2 = pipe_2(image=image, prompt_embeds=prompt_embeds, negative_prompt_embeds=neg_prompt_embeds, output_type="pt").images
    image_3 = pipe_3(prompt=prompt, image=image, noise_level=100).images