Controlnet - v1.1 - Scribble Version

Controlnet v1.1 is the successor model of Controlnet v1.0 and was released in lllyasviel/ControlNet-v1-1 by Lvmin Zhang.

This checkpoint is a conversion of the original checkpoint into diffusers format. It can be used in combination with Stable Diffusion, such as runwayml/stable-diffusion-v1-5.

For more details, please also have a look at the 🧨 Diffusers docs.

ControlNet is a neural network structure to control diffusion models by adding extra conditions.

This checkpoint corresponds to the ControlNet conditioned on Scribble images

Model Details

• Developed by: Lvmin Zhang, Maneesh Agrawala

• Model type: Diffusion-based text-to-image generation model

• Language(s): English

• License: The CreativeML OpenRAIL M license is an Open RAIL M license, adapted from the work that BigScience and the RAIL Initiative are jointly carrying in the area of responsible AI licensing. See also the article about the BLOOM Open RAIL license on which our license is based.

• Resources for more information: GitHub Repository, Paper.

• Cite as:

  @misc{zhang2023adding, title={Adding Conditional Control to Text-to-Image Diffusion Models}, author={Lvmin Zhang and Maneesh Agrawala}, year={2023}, eprint={2302.05543}, archivePrefix={arXiv}, primaryClass={cs.CV} }

Introduction

Controlnet was proposed in Adding Conditional Control to Text-to-Image Diffusion Models by Lvmin Zhang, Maneesh Agrawala.

The abstract reads as follows:

We present a neural network structure, ControlNet, to control pretrained large diffusion models to support additional input conditions. The ControlNet learns task-specific conditions in an end-to-end way, and the learning is robust even when the training dataset is small (< 50k). Moreover, training a ControlNet is as fast as fine-tuning a diffusion model, and the model can be trained on a personal devices. Alternatively, if powerful computation clusters are available, the model can scale to large amounts (millions to billions) of data. We report that large diffusion models like Stable Diffusion can be augmented with ControlNets to enable conditional inputs like edge maps, segmentation maps, keypoints, etc. This may enrich the methods to control large diffusion models and further facilitate related applications.

Example

It is recommended to use the checkpoint with Stable Diffusion v1-5 as the checkpoint has been trained on it. Experimentally, the checkpoint can be used with other diffusion models such as dreamboothed stable diffusion.

Note: If you want to process an image to create the auxiliary conditioning, external dependencies are required as shown below:

1. Install https://github.com/patrickvonplaten/controlnet_aux

$ pip install controlnet_aux==0.3.0

2. Let's install diffusers and related packages:

$ pip install diffusers transformers accelerate

3. Run code:

import torch
import os
from huggingface_hub import HfApi
from pathlib import Path
from diffusers.utils import load_image
from PIL import Image
import numpy as np
from controlnet_aux import PidiNetDetector, HEDdetector

from diffusers import (
    ControlNetModel,
    StableDiffusionControlNetPipeline,
    UniPCMultistepScheduler,
)

checkpoint = "lllyasviel/control_v11p_sd15_scribble"

image = load_image(
    "https://huggingface.co/lllyasviel/control_v11p_sd15_scribble/resolve/main/images/input.png"
)

prompt = "royal chamber with fancy bed"

processor = HEDdetector.from_pretrained('lllyasviel/Annotators')

control_image = processor(image, scribble=True)

control_image.save("./images/control.png")
controlnet = ControlNetModel.from_pretrained(checkpoint, torch_dtype=torch.float16)
pipe = StableDiffusionControlNetPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16
)

pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
pipe.enable_model_cpu_offload()

generator = torch.manual_seed(0)
image = pipe(prompt, num_inference_steps=30, generator=generator, image=control_image).images[0]

image.save('images/image_out.png')

Other released checkpoints v1-1

The authors released 14 different checkpoints, each trained with Stable Diffusion v1-5 on a different type of conditioning:

Improvements in Scribble 1.1:

• The training dataset of previous cnet 1.0 has several problems including (1) a small group of greyscale human images are duplicated thousands of times (!!), causing the previous model somewhat likely to generate grayscale human images; (2) some images has low quality, very blurry, or significant JPEG artifacts; (3) a small group of images has wrong paired prompts caused by a mistake in our data processing scripts. The new model fixed all problems of the training dataset and should be more reasonable in many cases.
• We find out that users sometimes like to draw very thick scribbles. Because of that, we used more aggressive random morphological transforms to synthesize scribbles. This model should work well even when the scribbles are relatively thick (the maximum width of training data is 24-pixel-width scribble in a 512 canvas, but it seems to work well even for a bit wider scribbles; the minimum width is 1 pixel).
• Resumed from Scribble 1.0, continued with 200 GPU hours of A100 80G.

More information

For more information, please also have a look at the Diffusers ControlNet Blog Post and have a look at the official docs.