This is the Linux app named ControlNet whose latest release can be downloaded as ControlNetsourcecode.tar.gz. It can be run online in the free hosting provider OnWorks for workstations.
Download and run online this app named ControlNet with OnWorks for free.
请按照以下说明运行此应用程序：
- 1. 在您的 PC 中下载此应用程序。
- 2. 在我们的文件管理器 https://www.onworks.net/myfiles.php?username=XXXXX 中输入您想要的用户名。
- 3. 在这样的文件管理器中上传这个应用程序。
- 4. 从此网站启动OnWorks Linux online 或Windows online emulator 或MACOS online emulator。
- 5. 从您刚刚启动的 OnWorks Linux 操作系统，使用您想要的用户名转到我们的文件管理器 https://www.onworks.net/myfiles.php?username=XXXXX。
- 6. 下载应用程序，安装并运行。
SCREENSHOTS
Ad
控制网
商品描述
ControlNet is a neural network architecture designed to add conditional control to text-to-image diffusion models. Rather than training from scratch, ControlNet “locks” the weights of a pre-trained diffusion model and introduces a parallel trainable branch that learns additional conditions—like edges, depth maps, segmentation, human pose, scribbles, or other guidance signals. This allows the system to control where and how the model should focus during generation, enabling users to steer layout, structure, and content more precisely than prompt text alone. The project includes many trained model variants that accept different types of conditioning (e.g., canny edge input, normal maps, skeletal pose) and produce improved fidelity in stable diffusion outputs. It is widely adopted in the community as a go-to tool for semi-automatic image generation workflows, especially when users want structure plus creative freedom.
功能
- Adds spatial and structural conditioning to pre-trained text-to-image diffusion models
- Support for multiple input conditions: edge maps, depth maps, semantic segmentation, pose, scribbles
- Uses “locked” backbone weights plus a parallel “trainable” branch for stability and flexibility
- Allows users to reuse large diffusion models while extending them with custom controls
- Community-ready with numerous model variants and support for popular UIs
- Suitable for generating images with precise layout, structure, or user-specified input
程式语言
Python
分类
This is an application that can also be fetched from https://sourceforge.net/projects/controlnet.mirror/. It has been hosted in OnWorks in order to be run online in an easiest way from one of our free Operative Systems.
