Diffusers | 教程

$ pip install --upgrade diffusers[torch]
# OR
$ conda install -c conda-forge diffusers

# uncomment to install the necessary libraries in Colab
# pip install --upgrade diffusers accelerate transformers

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
pipeline.to("cuda")
image = pipeline("An image of a squirrel in Picasso style").images[0]
image.save("image_of_squirrel_painting.png")

from diffusers import EulerDiscreteScheduler

pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_safetensors=True)
pipeline.scheduler = EulerDiscreteScheduler.from_config(pipeline.scheduler.config)

from diffusers import UNet2DModel
import torch

# load model
repo_id = "google/ddpm-cat-256"
model = UNet2DModel.from_pretrained(repo_id, use_safetensors=True)
model.config

# noise as input
torch.manual_seed(0)
noisy_sample = torch.randn(1, model.config.in_channels, model.config.sample_size, model.config.sample_size)
noisy_sample.shape

# inference
with torch.no_grad():
    noisy_residual = model(sample=noisy_sample, timestep=2).sample

from diffusers import DDPMScheduler

scheduler = DDPMScheduler.from_config(repo_id)
scheduler

less_noisy_sample = scheduler.step(model_output=noisy_residual, timestep=2, sample=noisy_sample).prev_sample
less_noisy_sample.shape

import tqdm
import PIL.Image
import numpy as np


def display_sample(sample, i):
    image_processed = sample.cpu().permute(0, 2, 3, 1)
    image_processed = (image_processed + 1.0) * 127.5
    image_processed = image_processed.numpy().astype(np.uint8)

    image_pil = PIL.Image.fromarray(image_processed[0])
    display(f"Image at step {i}")
    display(image_pil)
    
    
sample = noisy_sample  
for i, t in enumerate(tqdm.tqdm(scheduler.timesteps)):
    # 1. predict noise residual
    with torch.no_grad():
        residual = model(sample, t).sample

    # 2. compute less noisy image and set x_t -> x_t-1
    sample = scheduler.step(residual, t, sample).prev_sample

    # 3. optionally look at image
    if (i + 1) % 50 == 0:
        display_sample(sample, i + 1)

from diffusers import DDPMScheduler, UNet2DModel
from PIL import Image
import torch
import numpy as np

scheduler = DDPMScheduler.from_pretrained("google/ddpm-cat-256")
model = UNet2DModel.from_pretrained("google/ddpm-cat-256").to("cuda")
scheduler.set_timesteps(50)

sample_size = model.config.sample_size
noise = torch.randn((1, 3, sample_size, sample_size)).to("cuda")
input = noise

for t in scheduler.timesteps:
    with torch.no_grad():
        noisy_residual = model(input, t).sample
        prev_noisy_sample = scheduler.step(noisy_residual, t, input).prev_sample
        input = prev_noisy_sample

image = (input / 2 + 0.5).clamp(0, 1)
image = image.cpu().permute(0, 2, 3, 1).numpy()[0]
image = Image.fromarray((image * 255).round().astype("uint8"))
image

from accelerate import Accelerator
from huggingface_hub import HfFolder, Repository, whoami
from tqdm.auto import tqdm
from pathlib import Path
import os


def get_full_repo_name(model_id: str, organization: str = None, token: str = None):
    if token is None:
        token = HfFolder.get_token()
    if organization is None:
        username = whoami(token)["name"]
        return f"{username}/{model_id}"
    else:
        return f"{organization}/{model_id}"


def train_loop(config, model, noise_scheduler, optimizer, train_dataloader, lr_scheduler):
    # Initialize accelerator and tensorboard logging
    accelerator = Accelerator(
        mixed_precision=config.mixed_precision,
        gradient_accumulation_steps=config.gradient_accumulation_steps,
        log_with="tensorboard",
        project_dir=os.path.join(config.output_dir, "logs"),
    )
    if accelerator.is_main_process:
        if config.push_to_hub:
            repo_name = get_full_repo_name(Path(config.output_dir).name)
            repo = Repository(config.output_dir, clone_from=repo_name)
        elif config.output_dir is not None:
            os.makedirs(config.output_dir, exist_ok=True)
        accelerator.init_trackers("train_example")

    # Prepare everything
    # There is no specific order to remember, you just need to unpack the
    # objects in the same order you gave them to the prepare method.
    model, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(
        model, optimizer, train_dataloader, lr_scheduler
    )

    global_step = 0

    # Now you train the model
    for epoch in range(config.num_epochs):
        progress_bar = tqdm(total=len(train_dataloader), disable=not accelerator.is_local_main_process)
        progress_bar.set_description(f"Epoch {epoch}")

        for step, batch in enumerate(train_dataloader):
            clean_images = batch["images"]
            # Sample noise to add to the images
            noise = torch.randn(clean_images.shape).to(clean_images.device)
            bs = clean_images.shape[0]

            # Sample a random timestep for each image
            timesteps = torch.randint(
                0, noise_scheduler.config.num_train_timesteps, (bs,), device=clean_images.device
            ).long()

            # Add noise to the clean images according to the noise magnitude at each timestep
            # (this is the forward diffusion process)
            noisy_images = noise_scheduler.add_noise(clean_images, noise, timesteps)

            with accelerator.accumulate(model):
                # Predict the noise residual
                noise_pred = model(noisy_images, timesteps, return_dict=False)[0]
                loss = F.mse_loss(noise_pred, noise)
                accelerator.backward(loss)

                accelerator.clip_grad_norm_(model.parameters(), 1.0)
                optimizer.step()
                lr_scheduler.step()
                optimizer.zero_grad()

            progress_bar.update(1)
            logs = {"loss": loss.detach().item(), "lr": lr_scheduler.get_last_lr()[0], "step": global_step}
            progress_bar.set_postfix(**logs)
            accelerator.log(logs, step=global_step)
            global_step += 1

        # After each epoch you optionally sample some demo images with evaluate() and save the model
        if accelerator.is_main_process:
            pipeline = DDPMPipeline(unet=accelerator.unwrap_model(model), scheduler=noise_scheduler)

            if (epoch + 1) % config.save_image_epochs == 0 or epoch == config.num_epochs - 1:
                evaluate(config, epoch, pipeline)

            if (epoch + 1) % config.save_model_epochs == 0 or epoch == config.num_epochs - 1:
                if config.push_to_hub:
                    repo.push_to_hub(commit_message=f"Epoch {epoch}", blocking=True)
                else:
                    pipeline.save_pretrained(config.output_dir)

from accelerate import PartialState
from diffusers import DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
)
distributed_state = PartialState()
pipeline.to(distributed_state.device)

with distributed_state.split_between_processes(["a dog", "a cat"]) as prompt:
    result = pipeline(prompt).images[0]
    result.save(f"result_{distributed_state.process_index}.png")

$ accelerate launch run_distributed.py --num_processes=2

import torch
import torch.distributed as dist
import torch.multiprocessing as mp

from diffusers import DiffusionPipeline

sd = DiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
)


def run_inference(rank, world_size):
    dist.init_process_group("nccl", rank=rank, world_size=world_size)

    sd.to(rank)

    if torch.distributed.get_rank() == 0:
        prompt = "a dog"
    elif torch.distributed.get_rank() == 1:
        prompt = "a cat"

    image = sd(prompt).images[0]
    image.save(f"./{'_'.join(prompt)}.png")
    
    
def main():
    world_size = 2
    mp.spawn(run_inference, args=(world_size,), nprocs=world_size, join=True)


if __name__ == "__main__":
    main()

$ torchrun run_distributed.py --nproc_per_node=2

from PIL import Image
import torch
from transformers import CLIPTextModel, CLIPTokenizer
from diffusers import AutoencoderKL, UNet2DConditionModel, PNDMScheduler
from diffusers import UniPCMultistepScheduler

vae = AutoencoderKL.from_pretrained("CompVis/stable-diffusion-v1-4", subfolder="vae", use_safetensors=True)
tokenizer = CLIPTokenizer.from_pretrained("CompVis/stable-diffusion-v1-4", subfolder="tokenizer")
text_encoder = CLIPTextModel.from_pretrained(
    "CompVis/stable-diffusion-v1-4", subfolder="text_encoder", use_safetensors=True
)
unet = UNet2DConditionModel.from_pretrained(
    "CompVis/stable-diffusion-v1-4", subfolder="unet", use_safetensors=True
)

scheduler = UniPCMultistepScheduler.from_pretrained("CompVis/stable-diffusion-v1-4", subfolder="scheduler")

# speed up using gpu
torch_device = "cuda"
vae.to(torch_device)
text_encoder.to(torch_device)
unet.to(torch_device)


prompt = ["a photograph of an astronaut riding a horse"]
height = 512  # default height of Stable Diffusion
width = 512  # default width of Stable Diffusion
num_inference_steps = 25  # Number of denoising steps
guidance_scale = 7.5  # Scale for classifier-free guidance
generator = torch.manual_seed(0)  # Seed generator to create the inital latent noise
batch_size = len(prompt)


# Tokenize the text and generate the embeddings from the prompt
text_input = tokenizer(
    prompt, padding="max_length", max_length=tokenizer.model_max_length, truncation=True, return_tensors="pt"
)

with torch.no_grad():
    text_embeddings = text_encoder(text_input.input_ids.to(torch_device))[0]
    
# Create random noise
latents = torch.randn(
    (batch_size, unet.in_channels, height // 8, width // 8),
    generator=generator,
)
latents = latents.to(torch_device)
# Decode the image
# scale and decode the image latents with vae
latents = 1 / 0.18215 * latents
with torch.no_grad():
    image = vae.decode(latents).sample
    
image = (image / 2 + 0.5).clamp(0, 1).squeeze()
image = (image.permute(1, 2, 0) * 255).to(torch.uint8).cpu().numpy()
images = (image * 255).round().astype("uint8")
image = Image.fromarray(image)
image

$ scheduler.timesteps
tensor([980, 960, 940, 920, 900, 880, 860, 840, 820, 800, 780, 760, 740, 720,
    700, 680, 660, 640, 620, 600, 580, 560, 540, 520, 500, 480, 460, 440,
    420, 400, 380, 360, 340, 320, 300, 280, 260, 240, 220, 200, 180, 160,
    140, 120, 100,  80,  60,  40,  20,   0])