ControlNets for Stable Diffusion 3.5 Large
Key Takeaways
Today we are adding new capabilities to Stable Diffusion 3.5 Large with the release of three ControlNets: Blur, Canny, and Depth.
These models are free for both commercial and non-commercial use under the permissive Stability AI Community License.
You can download the model weights now from Hugging Face and code from GitHub, with support by Comfy UI.
Today we are adding new capabilities to Stable Diffusion 3.5 Large with the release of three ControlNets: Blur, Canny, and Depth.
Whether you're a builder or a creator, ControlNets provide the tools you need to create using Stable Diffusion 3.5 Large with precision and ease. These versatile models handle various inputs, making them ideal for a wide range of applications - from designing interiors to character creation. You can download the model weights now from Hugging Face and code from GitHub. The models are also supported by Comfy UI.
What’s being released
Blur
Achieve extremely high fidelity upscaling, including resolutions of 8K and 16K. Perfect for tiling low-resolution images into large, detailed visuals.
Canny
Leverage Canny edge maps to structure your generated images. This control type is particularly useful for illustrations but can be adaptable across all styles.
Depth
Use depth maps, generated by DepthFM, to guide image generation. Great for architectural renderings and texturing 3D assets, and other use cases that require exact control over the composition of an image.
In an ELO comparison study of the same control types with approximately 150 participants, Stable Diffusion 3.5 Large ControlNets ranked first in user preference among similar models.
Available for use under the Stability AI Community License
We are pleased to release this model under our permissive community 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.
Our commitment to 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 Stable Safety page.
Coming Soon
Additional ControlNet models, including Stable Diffusion 3.5 Medium (2B) variants and new control types, are on the way!
To stay updated on our progress follow us on X, LinkedIn, Instagram, and join our Discord Community.
