GANravel: User-Driven Direction Disentanglement in Generative Adversarial Networks

PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement

“…For instance, Matejka et al proposed DreamLens, an interactive system for exploring and visualizing large-scale generative design datasets [43]. The most related generative design work to us includes those using AI models to support user's design [11,17,31,37,38,64,73]. Evirgen et al proposed GANzilla, a tool that allows users to discover image manipulation directions in Generative Adversarial Networks (GANs) [16].…”

“…Evirgen et al proposed GANzilla, a tool that allows users to discover image manipulation directions in Generative Adversarial Networks (GANs) [16]. Its follow-up work, GANravel, focuses on disentangling editing directions in GANs [17]. To achieve this, both GANzilla and GANravel adjust the coefficients in GAN's latent space.…”