拡散モデルで画像・音声・3D生成するPythonライブラリ

pip install --upgrade diffusers[torch]

from diffusers import DiffusionPipeline
import torch

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

from diffusers import DDPMScheduler, UNet2DModel
from PIL import Image
import torch

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), device="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