Search Results for "image text input"

PersonaLive is an open-source diffusion-based portrait animation framework focused on generating expressive, long-duration animated sequences in real time, primarily for live streaming or interactive applications. It leverages deep generative models that condition on a static reference image and a driving input (such as motion or expression cues) to produce a seamless animated portrait sequence that can run indefinitely without segmentation artifacts. The framework prioritizes low-latency and streamable output, making it suitable for real-time creative workflows, broadcast overlays, or interactive avatars on consumer-grade GPUs. ...

AnimateDiff is an open-source project designed to enhance text-to-image diffusion models by adding animation capabilities. It allows users to turn static images generated by popular text-to-image models into animated sequences without requiring additional model training. This plug-and-play tool is compatible with a wide range of community models and facilitates the generation of animation directly from pre-existing text-to-image models. ...

A Python Script I made to split a starfield image into several layers. To be able to use the script, PixInsight with an installed Gaia data catalogue is required, as it needs the exported astrometry data text file.

A Stick figure animation program written with Python(www.python.org) and PyGame(www.pygame.org). It is similar to Pivot, except with a much wider variety of animation features, such as keyframes.