Stable Diffusion 3.5 Large Controlnet Canny

🚀 Stable Diffusion 3.5 Large Controlnet - Canny

This repository provides the Canny ControlNet for Stable Diffusion 3.5 Large, enabling high - quality text - to - image generation.

🚀 Quick Start

Using Controlnets in SD3.5 Standalone Repo

First, install the repo:

git clone git@github.com:Stability-AI/sd3.5.git
pip install -r requirements.txt

Then, download the models and sample images:

input/sample_cond.png
models/clip_g.safetensors
models/clip_l.safetensors
models/t5xxl.safetensors
models/sd3.5_large.safetensors
models/canny_8b.safetensors

Finally, run the following command:

python sd3_infer.py --controlnet_ckpt models/canny_8b.safetensors --controlnet_cond_image input/sample_cond.png --prompt "An adorable fluffy pastel creature"

The result should be an image similar to this:

Using Controlnets in Diffusers

Make sure you upgrade to the latest version of diffusers: pip install -U diffusers. Then you can run the following Python code:

💻 Usage Examples

Basic Usage

import torch
from diffusers import StableDiffusion3ControlNetPipeline, SD3ControlNetModel
from diffusers.utils import load_image
from diffusers.image_processor import VaeImageProcessor

class SD3CannyImageProcessor(VaeImageProcessor):
    def __init__(self):
        super().__init__(do_normalize=False)
    def preprocess(self, image, **kwargs):
        image = super().preprocess(image, **kwargs)
        image = image * 255 * 0.5 + 0.5
        return image
    def postprocess(self, image, do_denormalize=True, **kwargs):
        do_denormalize = [True] * image.shape[0]
        image = super().postprocess(image, **kwargs, do_denormalize=do_denormalize)
        return image

controlnet = SD3ControlNetModel.from_pretrained("stabilityai/stable-diffusion-3.5-large-controlnet-canny", torch_dtype=torch.float16)
pipe = StableDiffusion3ControlNetPipeline.from_pretrained(
    "stabilityai/stable-diffusion-3.5-large",
    controlnet=controlnet,
    torch_dtype=torch.float16
).to("cuda")
pipe.image_processor = SD3CannyImageProcessor()

control_image = load_image("https://huggingface.co/datasets/diffusers/diffusers-images-docs/resolve/main/canny.png")
prompt =  "A Night time photo taken by Leica M11, portrait of a Japanese woman in a kimono, looking at the camera, Cherry blossoms"

generator = torch.Generator(device="cpu").manual_seed(0)
image = pipe(
    prompt, 
    control_image=control_image, 
    controlnet_conditioning_scale=1.0,
    guidance_scale=3.5,
    num_inference_steps=60,
    generator=generator,
    max_sequence_length=77,
).images[0]
image.save(f'canny-8b.jpg')

Advanced Usage

# Preprocessing an input image for control use
import torchvision.transforms.functional as F
# assuming img is a PIL image
img = F.to_tensor(img)
img = cv2.cvtColor(img.transpose(1, 2, 0), cv2.COLOR_RGB2GRAY)
img = cv2.Canny(img, 100, 200)

Tips

💡 Usage Tip

• We recommend starting with a ControlNet strength of 0.8, and adjusting as needed.
• Euler sampler and a slightly higher step count (50 - 60) gives best results.
• Pass --text_encoder_device <device_name> to load the text encoders directly to VRAM, which can speed up the full inference loop at the cost of extra VRAM usage.

📚 Documentation

Model

This repository provides the Canny ControlNet for Stable Diffusion 3.5 Large..

Please note: This model is released under the Stability Community License. Visit Stability AI to learn or contact us for commercial licensing details.

Uses

All uses of the model must be in accordance with our Acceptable Use Policy.

Out-of-Scope Uses

The model was not trained to be factual or true representations of people or events. As such, using the model to generate such content is out-of-scope of the abilities of this model.

Training Data and Strategy

These models were trained on a wide variety of data, including synthetic data and filtered publicly available data.

Safety

We believe in safe, responsible AI practices and take deliberate measures to ensure Integrity starts at the early stages of development. This means we have taken and continue to take reasonable steps to prevent the misuse of Stable Diffusion 3.5 by bad actors. For more information about our approach to Safety please visit our Safety page.

Integrity Evaluation

Our integrity evaluation methods include structured evaluations and red - teaming testing for certain harms. Testing was conducted primarily in English and may not cover all possible harms.

Risks identified and mitigations:

Acknowledgements

• Lvmin Zhang, Anyi Rao, and Maneesh Agrawala, authors of the original ControlNet paper.
• Lvmin Zhang, who also developed the Tile ControlNet, which inspired the Blur ControlNet.
• Diffusers library authors, whose code was referenced during development.
• InstantX team, whose Flux and SD3 ControlNets were also referenced during training.
• All early testers and raters of the models, and the Stability AI team.

Contact

Please report any issues with the model or contact us:

📄 License

Here are the key components of the license:

• Free for non - commercial use: Individuals and organizations can use the model free of charge for non - commercial use, including scientific research.
• Free for commercial use (up to $1M in annual revenue): Startups, small to medium - sized businesses, and creators can use the model for commercial purposes at no cost, as long as their total annual revenue is less than $1M.
• Ownership of outputs: Retain ownership of the media generated without restrictive licensing implications.

For organizations with annual revenue more than $1M, please contact us here to inquire about an Enterprise License.