controlnet-union-sdxl-1.0
Omnipotent Image Generation and Editing Model
- Supports 10+control types, such as OpenPose, Depth, Canny, etc
- Generate high-resolution images based on text conditions
- Using the same network parameters to support different image conditions
- Support multi condition input without adding additional calculations or parameters
- Designers can edit detailed images
- Open source community, easy to contribute and use
Product Details
ControlNet++is a novel network design based on the ControlNet architecture, supporting over 10 control types for conditional text to image generation, and capable of generating high-resolution images comparable to midjourney vision. It extends the original ControlNet with two new modules, supporting different image conditions using the same network parameters, and supporting multi condition input without increasing computational burden. This model is open source and aims to enable more people to enjoy the convenience of image generation and editing.
