ControlNet Pose

Description

ControlNet Pose tool is used to generate images that have the same pose as the person in the input image. It uses Stable Diffusion and Controlnet to copy weights of neural network blocks into a "locked" and "trainable" copy. The user can define the number of samples, image resolution, guidance scale, seed, eta, added prompt, negative prompt, and resolution for detection. The predictions usually complete within 21 seconds.