ControlNet

ControlNet 通过结构控制图像（边缘、深度或姿态）来引导预训练的扩散模型，同时保留文本提示。它冻结基础模型，并添加一个并行网络，其残差用于引导去噪器，从而无需微调即可实现布局控制。

加载适用于所需控制类型（例如 canny）的 ControlNet，然后将其作为 controlnet= 参数传递给 from_pretrained()。使用 controlnet_conditioning_scale 来设置控制对生成过程的引导强度。

ControlNet 可用于许多模型，例如 Flux、Hunyuan-DiT、Stable Diffusion 3 等。本指南中的示例使用 Flux 和 Stable Diffusion XL。对于旧版 Stable Diffusion 系列检查点上的 T2I-Adapter，请参阅 Legacy adapters。对于新的可控生成任务，建议优先使用 ControlNet。

下方的选项卡分别展示了用于文生图、图生图和图像修复的 ControlNet。

文本到图像

图像到图像

inpainting

使用 opencv-python 生成 canny 图像。

import cv2
import numpy as np
from PIL import Image
from diffusers.utils import load_image

original_image = load_image(
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/non-enhanced-prompt.png"
)

image = np.array(original_image)

low_threshold = 100
high_threshold = 200

image = cv2.Canny(image, low_threshold, high_threshold)
image = image[:, :, None]
image = np.concatenate([image, image, image], axis=2)
canny_image = Image.fromarray(image)

将 Canny 图像传入 pipeline。使用 controlnet_conditioning_scale 参数来确定分配给控制信号的权重。

import torch
from diffusers.utils import load_image
from diffusers import FluxControlNetPipeline, FluxControlNetModel

controlnet = FluxControlNetModel.from_pretrained(
    "InstantX/FLUX.1-dev-Controlnet-Canny", dtype=torch.bfloat16
)
pipeline = FluxControlNetPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-dev", controlnet=controlnet, dtype=torch.bfloat16
).to("cuda")  # or "mps", "xpu", "cpu"

prompt = """
A photorealistic overhead image of a cat reclining sideways in a flamingo pool floatie holding a margarita. 
The cat is floating leisurely in the pool and completely relaxed and happy.
"""

pipeline(
    prompt, 
    control_image=canny_image,
    controlnet_conditioning_scale=0.5,
    num_inference_steps=50, 
    guidance_scale=3.5,
).images[0]

Generated image (ControlNet + prompt) — 生成的图像

使用 Transformers 中的深度估计流水线生成深度图。

import torch
import numpy as np
from PIL import Image
from transformers import DPTImageProcessor, DPTForDepthEstimation
from diffusers import ControlNetModel, StableDiffusionXLControlNetImg2ImgPipeline, AutoencoderKL
from diffusers.utils import load_image


device = "cuda"  # or "mps", "xpu", "cpu"
depth_estimator = DPTForDepthEstimation.from_pretrained("Intel/dpt-hybrid-midas").to(device)
feature_extractor = DPTImageProcessor.from_pretrained("Intel/dpt-hybrid-midas")

def get_depth_map(image):
    image = feature_extractor(images=image, return_tensors="pt").pixel_values.to(device)
    with torch.no_grad(), torch.autocast(device):
        depth_map = depth_estimator(image).predicted_depth

    depth_map = torch.nn.functional.interpolate(
        depth_map.unsqueeze(1),
        size=(1024, 1024),
        mode="bicubic",
        align_corners=False,
    )
    depth_min = torch.amin(depth_map, dim=[1, 2, 3], keepdim=True)
    depth_max = torch.amax(depth_map, dim=[1, 2, 3], keepdim=True)
    depth_map = (depth_map - depth_min) / (depth_max - depth_min)
    image = torch.cat([depth_map] * 3, dim=1)
    image = image.permute(0, 2, 3, 1).cpu().numpy()[0]
    image = Image.fromarray((image * 255.0).clip(0, 255).astype(np.uint8))
    return image

image = load_image(
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/non-enhanced-prompt.png"
).resize((1024, 1024))
depth_image = get_depth_map(image)

将深度图传入 pipeline。使用 controlnet_conditioning_scale 参数来确定分配给该控制条件的权重。

controlnet = ControlNetModel.from_pretrained(
    "diffusers/controlnet-depth-sdxl-1.0-small",
    dtype=torch.float16,
)
vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", dtype=torch.float16)
pipeline = StableDiffusionXLControlNetImg2ImgPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    controlnet=controlnet,
    vae=vae,
    dtype=torch.float16,
).to(device)

prompt = """
A photorealistic overhead image of a cat reclining sideways in a flamingo pool floatie holding a margarita. 
The cat is floating leisurely in the pool and completely relaxed and happy.
"""
controlnet_conditioning_scale = 0.5
pipeline(
    prompt,
    image=image,
    control_image=depth_image,
    controlnet_conditioning_scale=controlnet_conditioning_scale,
    strength=0.99,
    num_inference_steps=100,
).images[0]

Multi-ControlNet

通过传入列表来组合多个 ControlNet（例如 canny + depth）。在可能的情况下，对重叠区域进行遮罩，并调整每个 controlnet_conditioning_scale。使用 OpenCV Canny（与文生图相同）构建 canny_image，使用 DPT（与图生图相同）构建 depth_image。在调用 pipeline 之前，将每个控制图像调整至 pipeline 的尺寸。

import cv2
import torch
import numpy as np
from PIL import Image
from transformers import DPTImageProcessor, DPTForDepthEstimation
from diffusers import StableDiffusionXLControlNetPipeline, ControlNetModel, AutoencoderKL
from diffusers.utils import load_image

original_image = load_image(
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/non-enhanced-prompt.png"
)
image = np.array(original_image)
canny_image = Image.fromarray(
    np.concatenate([cv2.Canny(image, 100, 200)[:, :, None]] * 3, axis=2)
)

device = "cuda"  # or "mps", "xpu", "cpu"
depth_estimator = DPTForDepthEstimation.from_pretrained("Intel/dpt-hybrid-midas").to(device)
feature_extractor = DPTImageProcessor.from_pretrained("Intel/dpt-hybrid-midas")

def get_depth_map(image):
    image = feature_extractor(images=image, return_tensors="pt").pixel_values.to(device)
    with torch.no_grad(), torch.autocast(device):
        depth_map = depth_estimator(image).predicted_depth

    depth_map = torch.nn.functional.interpolate(
        depth_map.unsqueeze(1),
        size=(1024, 1024),
        mode="bicubic",
        align_corners=False,
    )
    depth_min = torch.amin(depth_map, dim=[1, 2, 3], keepdim=True)
    depth_max = torch.amax(depth_map, dim=[1, 2, 3], keepdim=True)
    depth_map = (depth_map - depth_min) / (depth_max - depth_min)
    image = torch.cat([depth_map] * 3, dim=1)
    image = image.permute(0, 2, 3, 1).cpu().numpy()[0]
    image = Image.fromarray((image * 255.0).clip(0, 255).astype(np.uint8))
    return image

depth_image = get_depth_map(original_image.resize((1024, 1024)))

controlnets = [
    ControlNetModel.from_pretrained(
        "diffusers/controlnet-canny-sdxl-1.0", dtype=torch.float16
    ),
    ControlNetModel.from_pretrained(
        "diffusers/controlnet-depth-sdxl-1.0-small", dtype=torch.float16
    ),
]

vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", dtype=torch.float16)
pipeline = StableDiffusionXLControlNetPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0", controlnet=controlnets, vae=vae, dtype=torch.float16
).to(device)

prompt = """
a relaxed rabbit sitting on a striped towel next to a pool with a tropical drink nearby, 
bright sunny day, vacation scene, 35mm photograph, film, professional, 4k, highly detailed
"""
negative_prompt = "lowres, bad anatomy, worst quality, low quality, deformed, ugly"

images = [canny_image.resize((1024, 1024)), depth_image.resize((1024, 1024))]

pipeline(
    prompt,
    negative_prompt=negative_prompt,
    image=images,
    num_inference_steps=100,
    controlnet_conditioning_scale=[0.5, 0.5],
).images[0]

猜测模式

Guess mode 在缺少（或不需要）文本提示时，仅凭控制信号即可生成图像。它按块深度对 ControlNet 残差进行缩放，从早期下采样块中约 0.1 的权重，逐步提升至中间块的 1.0。这样既能避免早期层过度约束，又能让更深层的块继续承载结构信息。

import torch
from diffusers.utils import load_image
from diffusers import StableDiffusionXLControlNetPipeline, ControlNetModel

controlnet = ControlNetModel.from_pretrained(
  "diffusers/controlnet-canny-sdxl-1.0", dtype=torch.float16
)
pipeline = StableDiffusionXLControlNetPipeline.from_pretrained(
  "stabilityai/stable-diffusion-xl-base-1.0",
  controlnet=controlnet,
  dtype=torch.float16
).to("cuda")  # or "mps", "xpu", "cpu"

canny_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/canny-cat.png")
pipeline(
  "",
  image=canny_image,
  guess_mode=True
).images[0]

Update on GitHub

Diffusers

ControlNet

Multi-ControlNet

猜测模式