Stable Diffusion是一个文本到图像的潜在扩散模型,由CompVis、Stability AI和LAION的研究人员和工程师创建。它使用来自LAION-5B数据库子集的512x512图像进行训练。使用这个模型,可以生成包括人脸在内的任何图像,因为有开源的预训练模型,所以我们也可以在自己的机器上运行它,如下图所示。
!nvidia-smi
!pip install diffusers==0.4.0
!pip install transformers scipy ftfy
!pip install "ipywidgets>=7,<8"
from google.colab import output
output.enable_custom_widget_manager()
from huggingface_hub import notebook_login
notebook_login()
import torch
from diffusers import StableDiffusionPipeline
# make sure you're logged in with `huggingface-cli login`
pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", revision="fp16", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "a photograph of an astronaut riding a horse"
image = pipe(prompt).images[0] # image here is in [PIL format](https://pillow.readthedocs.io/en/stable/)
# Now to display an image you can do either save it such as:
image.save(f"astronaut_rides_horse.png")
import torch
generator = torch.Generator("cuda").manual_seed(1024)
image = pipe(prompt, generator=generator).images[0]
image
import torch
generator = torch.Generator("cuda").manual_seed(1024)
image = pipe(prompt, num_inference_steps=15, generator=generator).images[0]
image
from PIL import Image
def image_grid(imgs, rows, cols):
assert len(imgs) == rows*cols
w, h = imgs[0].size
grid = Image.new('RGB', size=(cols*w, rows*h))
grid_w, grid_h = grid.size
for i, img in enumerate(imgs):
grid.paste(img, box=(i%cols*w, i//cols*h))
return grid
num_images = 3
prompt = ["a photograph of an astronaut riding a horse"] * num_images
images = pipe(prompt).images
grid = image_grid(images, rows=1, cols=3)
grid
num_cols = 3
num_rows = 4
prompt = ["a photograph of an astronaut riding a horse"] * num_cols
all_images = []
for i in range(num_rows):
images = pipe(prompt).images
all_images.extend(images)
grid = image_grid(all_images, rows=num_rows, cols=num_cols)
grid
prompt = "a photograph of an astronaut riding a horse"
image = pipe(prompt, height=512, width=768).images[0]
image
import torch
torch_device = "cuda" if torch.cuda.is_available() else "cpu"
from transformers import CLIPTextModel, CLIPTokenizer
from diffusers import AutoencoderKL, UNet2DConditionModel, PNDMScheduler
# 1. Load the autoencoder model which will be used to decode the latents into image space.
vae = AutoencoderKL.from_pretrained("CompVis/stable-diffusion-v1-4", subfolder="vae")
# 2. Load the tokenizer and text encoder to tokenize and encode the text.
tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-large-patch14")
text_encoder = CLIPTextModel.from_pretrained("openai/clip-vit-large-patch14")
# 3. The UNet model for generating the latents.
unet = UNet2DConditionModel.from_pretrained("CompVis/stable-diffusion-v1-4", subfolder="unet")
from diffusers import LMSDiscreteScheduler
scheduler = LMSDiscreteScheduler(beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", num_train_timesteps=1000)
vae = vae.to(torch_device)
text_encoder = text_encoder.to(torch_device)
unet = 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 = 100 # Number of denoising steps
guidance_scale = 7.5 # Scale for classifier-free guidance
generator = torch.manual_seed(32) # Seed generator to create the inital latent noise
batch_size = 1
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]
max_length = text_input.input_ids.shape[-1]
uncond_input = tokenizer(
[""] * batch_size, padding="max_length", max_length=max_length, return_tensors="pt"
)
with torch.no_grad():
uncond_embeddings = text_encoder(uncond_input.input_ids.to(torch_device))[0]
text_embeddings = torch.cat([uncond_embeddings, text_embeddings])
latents = torch.randn(
(batch_size, unet.in_channels, height // 8, width // 8),
generator=generator,
)
latents = latents.to(torch_device)
scheduler.set_timesteps(num_inference_steps)
latents = latents * scheduler.init_noise_sigma
from tqdm.auto import tqdm
from torch import autocast
for t in tqdm(scheduler.timesteps):
# expand the latents if we are doing classifier-free guidance to avoid doing two forward passes.
latent_model_input = torch.cat([latents] * 2)
latent_model_input = scheduler.scale_model_input(latent_model_input, t)
# predict the noise residual
with torch.no_grad():
noise_pred = unet(latent_model_input, t, encoder_hidden_states=text_embeddings).sample
# perform guidance
noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)
# compute the previous noisy sample x_t -> x_t-1
latents = scheduler.step(noise_pred, t, latents).prev_sample
# 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)
image = image.detach().cpu().permute(0, 2, 3, 1).numpy()
images = (image * 255).round().astype("uint8")
pil_images = [Image.fromarray(image) for image in images]
pil_images[0]