Steaming Hot Generative Coffee
Created using Stability AI Stable Video Diffusion 1.1 Image-to-Video latent diffusion model (SVD 1.1), available on Hugging Face. I created this video on Amazon Web Services (AWS) from a single image from Pexels using the SVD 1.1 model and ComfyUI. The output was an MP4 file with 25 frames at a resolution of 1024 x 576 pixels. Photo by Ehioma Osih. Audio by Kabbalistic_Village from Pixabay.