Wan2.2-S2V-14B is a 14-billion parameter open-weight diffusion model for image-to-video and audio-driven video generation. It enables developers to create videos from still images and audio prompts using the Diffusers library. The model is hosted on Hugging Face, comes with Apache-2.0 licensing, and supports local inference on compatible hardware.
Wan2.2 S2V 14B sits in PulseGate's Image to video category. It focuses on generating high-quality videos from images or audio inputs without proprietary APIs or closed models. It is built as an open-source project for developers. Wan2.2 S2V 14B is open source under the Apache-2.0 license. It ships for the web, the command line, and API.
Wan-AI builds and maintains Wan2.2 S2V 14B, and it first shipped in 2025. The project is developed in the open on GitHub with 16.8k stars. PulseGate's similarity index places it among 6 comparable projects. Key capabilities include image-to-Video, Audio-Driven Generation, and Diffusers Integration.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do