扩散模型自动管道AutoPipeline

news2024/12/25 2:31:37

推荐：write_own_pipeline.ipynb - Colab (google.com)

为您的任务选择一个 AutoPipeline

首先选择一个检查点。例如，如果您对使用 runwayml/stable-diffusion-v1-5 检查点的文本到图像感兴趣，请使用 AutoPipelineForText2Image：
from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
).to("cuda")
prompt = "peasant and dragon combat, wood cutting style, viking era, bevel with rune"

image = pipeline(prompt, num_inference_steps=25).images[0]
image
在引擎盖下，AutoPipelineForText2Image：

自动检测 model_index.json 文件中的类"stable-diffusion"
根据类名加载对应的文本到图像的 StableDiffusionPipeline"stable-diffusion"

同样，对于图像到图像，AutoPipelineForImage2Image 会从文件中检测检查点，并将在后台加载相应的 StableDiffusionImg2ImgPipeline。还可以传递特定于管道类的任何其他参数，例如，它确定添加到输入图像的噪声或变化量："stable-diffusion"model_index.jsonstrength
from diffusers import AutoPipelineForImage2Image
import torch
import requests
from PIL import Image
from io import BytesIO

pipeline = AutoPipelineForImage2Image.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    torch_dtype=torch.float16,
    use_safetensors=True,
).to("cuda")
prompt = "a portrait of a dog wearing a pearl earring"

url = "https://upload.wikimedia.org/wikipedia/commons/thumb/0/0f/1665_Girl_with_a_Pearl_Earring.jpg/800px-1665_Girl_with_a_Pearl_Earring.jpg"

response = requests.get(url)
image = Image.open(BytesIO(response.content)).convert("RGB")
image.thumbnail((768, 768))

image = pipeline(prompt, image, num_inference_steps=200, strength=0.75, guidance_scale=10.5).images[0]
image
原图：

生图：

如果要进行修复，则 AutoPipelineForInpainting 会以相同的方式加载基础 StableDiffusionInpaintPipeline 类：

from diffusers import AutoPipelineForInpainting
from diffusers.utils import load_image
import torch

pipeline = AutoPipelineForInpainting.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, use_safetensors=True
).to("cuda")

img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png"
mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"

init_image = load_image(img_url).convert("RGB")
mask_image = load_image(mask_url).convert("RGB")

prompt = "A majestic tiger sitting on a bench"
image = pipeline(prompt, image=init_image, mask_image=mask_image, num_inference_steps=50, strength=0.80).images[0]
image

原图：