ControlNet Pose

Category: Generative Art
Field: Technology
Type: API
Use Cases:
- Generative art generation
- Image modification with pose detection
Summary: ControlNet Pose is a generative art tool that utilizes pose detection to modify images with humans. It allows the user to input an image and prompt the model to generate an image using pose detection. The model is based on ControlNet, which adapts Stable Diffusion to use a pose map of humans in an input image in addition to a text input to generate an output image. This neural network structure enables control of pretrained large diffusion models to support additional input conditions beyond prompts, and the learning is robust even with a small training dataset. ControlNet Pose can be run on Replicate with an API, and it is open source, allowing users to run it on their own computer with Docker.
Learn more