Project Icon

T-GATE

Enhance the Speed of Text-to-Image Diffusion Models Using Temporally Gated Attention

Product DescriptionExplore a training-free method to improve text-to-image diffusion models using T-GATE. It utilizes temporally gated attention to streamline the inference process into semantics-planning and fidelity-improving phases, enhancing model speed by 10-50% without compromising image quality. T-GATE integrates easily with existing frameworks and is compatible with CNN-based U-Net, Transformer, and Consistency Models. It now supports PixArt-Sigma and StableVideoDiffusion models, providing a valuable option for efficient image generation in various applications.
Project Details